Deploy GitHub main 8c9fc27f33a5

app.py

@@ -1,548 +0,0 @@
-import json
-import os
-import sys
-from html import escape
-from pathlib import Path
-
-import gradio as gr
-
-# Gradio checks its own HTTP endpoint at startup; keep loopback off outbound proxies.
-os.environ["NO_PROXY"] = ",".join(filter(None, [os.getenv("NO_PROXY", os.getenv("no_proxy", "")),
-                                               "localhost,127.0.0.1,0.0.0.0"]))
-
-SPACE_DIR = Path(__file__).resolve().parent
-if str(SPACE_DIR) not in sys.path:
-    sys.path.insert(0, str(SPACE_DIR))
-
-from src.about import (
-    CITATION_BUTTON_LABEL,
-    CITATION_BUTTON_TEXT,
-    INTRODUCTION_TEXT,
-    LLM_BENCHMARKS_TEXT,
-    TITLE,
-)
-from src.display.css_html_js import custom_css
-from src.utils import (
-    build_leaderboard_summary_html,
-    build_domain_status_md,
-    dataset_section_title,
-    get_grouped_dfs,
-    group_datasets_by_domain,
-    load_fixed_window_table,
-    load_gift_aggregate_metadata_md,
-    load_gift_aggregate_table,
-    load_forecast_snapshots,
-    forecast_snapshot_status,
-    make_domain_pie_chart,
-    make_forecast_plot,
-    prepare_ranks_table,
-    prepare_values_table,
-)
-
-RESULTS_PATH = os.getenv("TSFM_RESULTS_PATH", str(SPACE_DIR / "results"))
-from src.result_feed import ResultFeed
-RESULT_FEED = ResultFeed(RESULTS_PATH)
-RESULTS_PATH = RESULT_FEED.refresh()
-REFRESH_SECONDS = int(os.getenv("TSFM_REFRESH_SECONDS", "300"))
-DOMAIN_OUTPUT_OFFSET = 14
-MODEL_COLUMN_WIDTH = "180px"
-RANK_MODEL_COLUMN_WIDTH = MODEL_COLUMN_WIDTH
-RANK_INDEX_COLUMN_WIDTH = MODEL_COLUMN_WIDTH
-METRIC_COLUMN_WIDTH = "118px"
-MODEL_COLUMN_NAMES = {"model"}
-
-def _fixed_window_outputs(window: str) -> tuple[str, str]:
-    return (
-        _rank_table_html(load_fixed_window_table(RESULTS_PATH, window, "rank")),
-        _rank_table_html(load_fixed_window_table(RESULTS_PATH, window, "overall")),
-    )
-
-
-def _model_column_index(value) -> int | None:
-    columns = getattr(value, "columns", None)
-    if columns is None:
-        return None
-    for idx, column in enumerate(columns):
-        if str(column).strip().lower() in MODEL_COLUMN_NAMES:
-            return idx
-    return None
-
-
-def _model_cell_html(value) -> str:
-    text = "" if value is None else str(value)
-    return (
-        '<div class="leaderboard-model-cell" title="'
-        + escape(text, quote=True)
-        + '">'
-        + escape(text)
-        + "</div>"
-    )
-
-
-def _rank_display_table(value):
-    model_col_idx = _model_column_index(value)
-    if model_col_idx is None:
-        return value
-    columns = getattr(value, "columns", None)
-    if columns is None:
-        return value
-    table = value.copy()
-    model_col = columns[model_col_idx]
-    table[model_col] = table[model_col].map(_model_cell_html)
-    return table
-
-
-def _dataframe_datatypes(value, *, rank_table: bool = False) -> list[str] | None:
-    columns = getattr(value, "columns", None)
-    if columns is None:
-        return None
-    try:
-        column_count = len(columns)
-    except TypeError:
-        return None
-    if column_count <= 0:
-        return None
-    datatypes = ["str"] * column_count
-    model_col_idx = _model_column_index(value)
-    if rank_table and model_col_idx is not None:
-        datatypes[model_col_idx] = "html"
-    return datatypes
-
-
-def _dataframe_column_widths(value, *, rank_table: bool = False) -> list[str] | None:
-    columns = getattr(value, "columns", None)
-    if columns is None:
-        return None
-    try:
-        column_count = len(columns)
-    except TypeError:
-        return None
-    if column_count <= 0:
-        return None
-    model_width = RANK_MODEL_COLUMN_WIDTH if rank_table else MODEL_COLUMN_WIDTH
-    widths = [METRIC_COLUMN_WIDTH] * column_count
-    model_col_idx = _model_column_index(value)
-    if model_col_idx is None:
-        model_col_idx = 0
-    widths[model_col_idx] = model_width
-    return widths
-
-
-def _leaderboard_dataframe(value, *, rank_table: bool = False, **kwargs):
-    classes = kwargs.pop("elem_classes", []) or []
-    if isinstance(classes, str):
-        classes = [classes]
-    if "leaderboard-dataframe" not in classes:
-        classes.append("leaderboard-dataframe")
-    if rank_table and "rank-leaderboard-dataframe" not in classes:
-        classes.append("rank-leaderboard-dataframe")
-    model_col_idx = _model_column_index(value)
-    if model_col_idx is not None:
-        model_col_class = f"leaderboard-model-col-{model_col_idx}"
-        if model_col_class not in classes:
-            classes.append(model_col_class)
-    kwargs["elem_classes"] = classes
-    kwargs["interactive"] = False
-    kwargs["wrap"] = False
-    kwargs["line_breaks"] = False
-    kwargs.setdefault("datatype", _dataframe_datatypes(value, rank_table=rank_table))
-    kwargs.setdefault("column_widths", _dataframe_column_widths(value, rank_table=rank_table))
-    return gr.Dataframe(value=value, **kwargs)
-
-
-def _rank_table_html(table) -> str:
-    columns = list(getattr(table, "columns", []))
-    if not columns:
-        return '<div class="rank-table-scroll"><table class="rank-html-table"></table></div>'
-
-    model_col_idx = _model_column_index(table)
-    if model_col_idx is None:
-        fixed_col_idx = 0
-        fixed_col_width = RANK_INDEX_COLUMN_WIDTH
-    else:
-        fixed_col_idx = model_col_idx
-        fixed_col_width = RANK_MODEL_COLUMN_WIDTH
-
-    colgroup = []
-    for idx in range(len(columns)):
-        width = fixed_col_width if idx == fixed_col_idx else METRIC_COLUMN_WIDTH
-        colgroup.append(f'<col style="width: {width}; min-width: {width};">')
-
-    header_cells = []
-    for idx, column in enumerate(columns):
-        class_name = ' class="rank-fixed-column"' if idx == fixed_col_idx else ""
-        header_cells.append(f"<th{class_name}>{escape(str(column))}</th>")
-
-    body_rows = []
-    for _, row in table.iterrows():
-        cells = []
-        for idx, column in enumerate(columns):
-            text = "" if row[column] is None else str(row[column])
-            if idx == fixed_col_idx:
-                cells.append(
-                    '<td class="rank-fixed-column"><div class="rank-fixed-window" title="'
-                    + escape(text, quote=True)
-                    + '">'
-                    + escape(text)
-                    + "</div></td>"
-                )
-            else:
-                cells.append(f"<td>{escape(text)}</td>")
-        body_rows.append("<tr>" + "".join(cells) + "</tr>")
-
-    return (
-        '<div class="rank-table-scroll">'
-        '<table class="rank-html-table">'
-        "<colgroup>"
-        + "".join(colgroup)
-        + "</colgroup><thead><tr>"
-        + "".join(header_cells)
-        + "</tr></thead><tbody>"
-        + "".join(body_rows)
-        + "</tbody></table></div>"
-    )
-
-
-def _dataset_tables(grouped: dict, datasets: list[str]) -> tuple[list, list]:
-    values_tables = [
-        prepare_values_table(grouped["dataset_values"].get(dataset, None))
-        for dataset in datasets
-    ]
-    rank_tables = [
-        _rank_table_html(prepare_ranks_table(grouped["dataset_ranks"].get(dataset, None)))
-        for dataset in datasets
-    ]
-    return values_tables, rank_tables
-
-
-def _model_label(root: Path, model_slug: str) -> str:
-    config_path = root / model_slug / "config.json"
-    if not config_path.exists():
-        return model_slug
-    try:
-        config = json.loads(config_path.read_text())
-        return str(config.get("model") or model_slug)
-    except Exception:
-        return model_slug
-
-
-def _forecast_choices(root_dir: str, datasets: list[str]) -> dict[str, dict[str, dict]]:
-    dataset_keys = {dataset.split("/")[0] for dataset in datasets}
-    choices: dict[str, dict[str, dict]] = {dataset_key: {} for dataset_key in dataset_keys}
-    root = Path(root_dir)
-    if not root.exists():
-        return choices
-
-    model_slugs = {p.name for p in root.iterdir() if p.is_dir()}
-    model_slugs.update(p.name for p in (root / "public_snapshots").glob("*") if p.is_dir())
-    for slug in sorted(model_slugs):
-        for snapshot_dataset, snapshot in load_forecast_snapshots(root_dir, slug).items():
-            dataset_key = str(snapshot_dataset).split("/")[0]
-            if dataset_key not in choices:
-                continue
-            model_label = str(snapshot.get("model") or _model_label(root, slug))
-            choices[dataset_key][model_label] = snapshot
-
-    return choices
-
-
-def _available_forecast_models(dataset_key: str) -> list[str]:
-    return sorted(FORECAST_CHOICES.get(dataset_key, {}).keys())
-
-
-def _forecast_plot_for(dataset_key: str, model_label: str):
-    if not model_label:
-        return None
-    return make_forecast_plot(FORECAST_CHOICES.get(dataset_key, {}).get(model_label))
-
-
-def _make_forecast_plotter(dataset_key: str):
-    def update_forecast_plot(model_label: str):
-        choices = _forecast_choices(RESULT_FEED.refresh(), DATASETS)
-        snapshot = choices.get(dataset_key, {}).get(model_label)
-        return make_forecast_plot(snapshot), forecast_snapshot_status(snapshot)
-
-    return update_forecast_plot
-
-
-def refresh_forecasts(*selected_models) -> tuple:
-    """Reload the published catalog, preserving each visitor's model selections."""
-    catalog = _forecast_choices(RESULT_FEED.refresh(), DATASETS)
-    outputs = []
-    for index, key in enumerate(FORECAST_DATASET_KEYS):
-        choices = sorted(catalog.get(key, {}))
-        selected = selected_models[index] if index < len(selected_models) else None
-        selected = selected if selected in choices else (choices[0] if choices else None)
-        snapshot = catalog.get(key, {}).get(selected)
-        outputs.extend([gr.update(choices=choices, value=selected, interactive=bool(choices)),
-                        make_forecast_plot(snapshot), forecast_snapshot_status(snapshot)])
-    return tuple(outputs)
-
-
-def refresh_leaderboard() -> tuple:
-    global RESULTS_PATH
-    RESULTS_PATH = RESULT_FEED.refresh()
-    grouped = get_grouped_dfs(RESULTS_PATH)
-    # Gradio outputs are fixed at startup; missing/new datasets must not change
-    # callback arity or shift another dataset's values into an existing table.
-    datasets = DATASETS
-    one_day_rank, one_day_metrics = _fixed_window_outputs("1d")
-    seven_day_rank, seven_day_metrics = _fixed_window_outputs("7d")
-    thirty_day_rank, thirty_day_metrics = _fixed_window_outputs("30d")
-
-    outputs: list = [
-        build_leaderboard_summary_html(RESULTS_PATH),       # [0]
-        prepare_values_table(grouped["overall_values"]),    # [1]
-        _rank_table_html(prepare_ranks_table(grouped["overall_ranks"])),  # [2]
-        make_domain_pie_chart(RESULTS_PATH),                # [3]
-        one_day_rank,                                       # [4]
-        one_day_metrics,                                    # [5]
-        seven_day_rank,                                     # [6]
-        seven_day_metrics,                                  # [7]
-        thirty_day_rank,                                    # [8]
-        thirty_day_metrics,                                 # [9]
-        load_gift_aggregate_metadata_md(RESULTS_PATH),       # [10]
-        load_gift_aggregate_table(RESULTS_PATH, "prediction_length"),  # [11]
-        load_gift_aggregate_table(RESULTS_PATH, "domain"),             # [12]
-        load_gift_aggregate_table(RESULTS_PATH, "frequency"),          # [13]
-    ]
-
-    # [14 .. 14+D-1] per-domain status lines
-    for domain, domain_datasets in DOMAIN_GROUPS.items():
-        outputs.append(build_domain_status_md(domain, domain_datasets, RESULTS_PATH))
-
-    value_tables, rank_tables = _dataset_tables(grouped, datasets)
-    # [14+D .. 14+D+N-1] value tables
-    outputs.extend(value_tables)
-    # [14+D+N .. 14+D+2N-1] rank tables
-    outputs.extend(rank_tables)
-    return tuple(outputs)
-
-
-grouped_initial = get_grouped_dfs(RESULTS_PATH)
-DATASETS: list[str] = grouped_initial["datasets"]
-FORECAST_CHOICES = _forecast_choices(RESULTS_PATH, DATASETS)
-DOMAIN_GROUPS = group_datasets_by_domain(DATASETS, RESULTS_PATH)
-N_DOMAINS = len(DOMAIN_GROUPS)
-FORECAST_DATASET_KEYS = [ds.split("/")[0] for datasets in DOMAIN_GROUPS.values() for ds in datasets]
-INITIAL_OUTPUTS = refresh_leaderboard()
-
-demo = gr.Blocks(css=custom_css)
-with demo:
-    gr.HTML(TITLE)
-    gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
-    summary_html = gr.HTML(INITIAL_OUTPUTS[0])
-
-    dataset_value_dfs: list[gr.Dataframe] = []
-    dataset_rank_dfs: list[gr.HTML] = []
-    domain_status_mds: list[gr.Markdown] = []
-    forecast_dropdowns = []
-    forecast_outputs = []
-    dataset_idx = 0
-
-    with gr.Tabs(elem_classes="tab-buttons"):
-        # ── Overall Tab ──────────────────────────────────────────────────────
-        with gr.TabItem("Overall"):
-            gr.Markdown(
-                "**Latest evaluation snapshot**",
-                elem_classes="markdown-text",
-            )
-            gr.Markdown(
-                "**Overall summary.** Geometric mean of absolute metric values across the latest dataset snapshot. MSE/CRPS are lower-is-better; RankScore is higher-is-better.",
-                elem_classes="markdown-text",
-            )
-            overall_values_df = _leaderboard_dataframe(
-                value=INITIAL_OUTPUTS[1],
-                label="Metric values and RankScore",
-            )
-            gr.Markdown(
-                "**Latest snapshot ranks.** Per-metric ranks derived from the snapshot values above; lower rank is better.",
-                elem_classes="markdown-text",
-            )
-            overall_ranks_df = gr.HTML(
-                value=INITIAL_OUTPUTS[2],
-                elem_classes="rank-html-output",
-            )
-            gr.Markdown(
-                "**Evaluated timestamps by domain** · hover for dataset names",
-                elem_classes="markdown-text",
-            )
-            domain_pie_plot = gr.Plot(
-                value=INITIAL_OUTPUTS[3],
-                label="Domain distribution",
-            )
-
-            gr.Markdown(
-                "**Pairwise historical ranking.** Every Ranking table uses all shared releases completed through the current cutoff, balanced equally across datasets. The 24-hour, 7-day, and 30-day windows apply only to their Metrics tables. Official ranks require at least 30 shared releases, 5 shared datasets, 7 days of shared coverage, 3 eligible opponents, and membership in the main comparison component. Absolute metrics remain descriptive and do not determine rank.",
-                elem_classes="markdown-text",
-            )
-            gr.Markdown(
-                "**Last 24 hours** · cumulative historical ranking; metrics use releases whose target window ended in the trailing 24 hours.",
-                elem_classes="markdown-text",
-            )
-            gr.Markdown("**Ranking**", elem_classes="markdown-text")
-            last_24h_rank_df = gr.HTML(
-                value=INITIAL_OUTPUTS[4],
-                elem_classes="rank-html-output",
-            )
-            gr.Markdown("**Metrics**", elem_classes="markdown-text")
-            last_24h_metrics_df = gr.HTML(
-                value=INITIAL_OUTPUTS[5],
-                elem_classes="rank-html-output",
-            )
-            gr.Markdown(
-                "**Last 7 days** · cumulative historical ranking; metrics use a fixed trailing seven-day window.",
-                elem_classes="markdown-text",
-            )
-            gr.Markdown("**Ranking**", elem_classes="markdown-text")
-            last_7d_rank_df = gr.HTML(
-                value=INITIAL_OUTPUTS[6],
-                elem_classes="rank-html-output",
-            )
-            gr.Markdown("**Metrics**", elem_classes="markdown-text")
-            last_7d_metrics_df = gr.HTML(
-                value=INITIAL_OUTPUTS[7],
-                elem_classes="rank-html-output",
-            )
-            gr.Markdown(
-                "**Last 30 days** · cumulative historical ranking; metrics use a fixed trailing thirty-day window.",
-                elem_classes="markdown-text",
-            )
-            gr.Markdown("**Ranking**", elem_classes="markdown-text")
-            last_30d_rank_df = gr.HTML(
-                value=INITIAL_OUTPUTS[8],
-                elem_classes="rank-html-output",
-            )
-            gr.Markdown("**Metrics**", elem_classes="markdown-text")
-            last_30d_metrics_df = gr.HTML(
-                value=INITIAL_OUTPUTS[9],
-                elem_classes="rank-html-output",
-            )
-
-        # ── GIFT-style grouped result tables ────────────────────────────────
-        with gr.TabItem("GIFT-style Aggregates"):
-            aggregate_metadata_md = gr.Markdown(
-                INITIAL_OUTPUTS[10],
-                elem_classes="markdown-text",
-            )
-            gr.Markdown(
-                "MSE and CRPS are normalized per dataset configuration against Seasonal-Naive (1.0 = baseline). Rank is the mean per-configuration CRPS rank. Lower is better for all three metrics.",
-                elem_classes="markdown-text",
-            )
-            with gr.Tabs():
-                with gr.TabItem("Prediction Length"):
-                    prediction_length_aggregate_df = _leaderboard_dataframe(
-                        value=INITIAL_OUTPUTS[11],
-                        label="Results on TSFM_Bench aggregated by Prediction Length",
-                    )
-                with gr.TabItem("Domain"):
-                    domain_aggregate_df = _leaderboard_dataframe(
-                        value=INITIAL_OUTPUTS[12],
-                        label="Results on TSFM_Bench aggregated by Domain",
-                    )
-                with gr.TabItem("Frequency"):
-                    frequency_aggregate_df = _leaderboard_dataframe(
-                        value=INITIAL_OUTPUTS[13],
-                        label="Results on TSFM_Bench aggregated by Frequency",
-                    )
-
-        # ── Domain Tabs ───────────────────────────────────────────────────────
-        domain_idx = 0
-        for domain, domain_datasets in DOMAIN_GROUPS.items():
-            domain_label = f"{domain} ({len(domain_datasets)})"
-            with gr.TabItem(domain_label):
-                # Per-domain status line (data source, last eval, refresh intervals)
-                domain_status_mds.append(
-                    gr.Markdown(
-                        INITIAL_OUTPUTS[DOMAIN_OUTPUT_OFFSET + domain_idx],
-                        elem_classes="markdown-text",
-                    )
-                )
-                domain_idx += 1
-
-                for dataset in domain_datasets:
-                    gr.Markdown(
-                        dataset_section_title(dataset, RESULTS_PATH),
-                        elem_classes="dataset-heading",
-                    )
-                    dataset_value_dfs.append(
-                        _leaderboard_dataframe(
-                            value=INITIAL_OUTPUTS[DOMAIN_OUTPUT_OFFSET + N_DOMAINS + dataset_idx],
-                            show_label=False,
-                        )
-                    )
-                    gr.Markdown(
-                        dataset_section_title(dataset, RESULTS_PATH, ranks=True),
-                        elem_classes="dataset-heading",
-                    )
-                    dataset_rank_dfs.append(
-                        gr.HTML(
-                            value=INITIAL_OUTPUTS[DOMAIN_OUTPUT_OFFSET + N_DOMAINS + len(DATASETS) + dataset_idx],
-                            elem_classes="rank-html-output",
-                        )
-                    )
-                    dataset_key = dataset.split("/")[0]
-                    forecast_model_choices = _available_forecast_models(dataset_key)
-                    default_forecast_model = forecast_model_choices[0] if forecast_model_choices else None
-                    forecast_model_dropdown = gr.Dropdown(
-                        choices=forecast_model_choices,
-                        value=default_forecast_model,
-                        label="Model",
-                        interactive=bool(forecast_model_choices),
-                    )
-                    forecast_plot = gr.Plot(
-                        value=_forecast_plot_for(dataset_key, default_forecast_model),
-                        label="Forecast snapshot",
-                    )
-                    forecast_status = gr.Markdown(forecast_snapshot_status(
-                        FORECAST_CHOICES.get(dataset_key, {}).get(default_forecast_model)))
-                    forecast_dropdowns.append(forecast_model_dropdown)
-                    forecast_outputs.extend([forecast_model_dropdown, forecast_plot, forecast_status])
-                    forecast_model_dropdown.input(
-                        fn=_make_forecast_plotter(dataset_key),
-                        inputs=[forecast_model_dropdown],
-                        outputs=[forecast_plot, forecast_status],
-                        api_name=f"forecast_{dataset_key}",
-                    )
-
-                    dataset_idx += 1
-
-    with gr.Accordion("About", open=False):
-        gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
-
-    with gr.Accordion("Citation", open=False):
-        gr.Textbox(
-            value=CITATION_BUTTON_TEXT,
-            label=CITATION_BUTTON_LABEL,
-            lines=12,
-            show_copy_button=True,
-        )
-
-    refresh_outputs = [
-        summary_html,
-        overall_values_df,
-        overall_ranks_df,
-        domain_pie_plot,
-        last_24h_rank_df,
-        last_24h_metrics_df,
-        last_7d_rank_df,
-        last_7d_metrics_df,
-        last_30d_rank_df,
-        last_30d_metrics_df,
-        aggregate_metadata_md,
-        prediction_length_aggregate_df,
-        domain_aggregate_df,
-        frequency_aggregate_df,
-        *domain_status_mds,
-        *dataset_value_dfs,
-        *dataset_rank_dfs,
-    ]
-
-    demo.load(refresh_leaderboard, inputs=[], outputs=refresh_outputs)
-    demo.load(refresh_forecasts, inputs=forecast_dropdowns, outputs=forecast_outputs)
-    refresh_timer = gr.Timer(value=REFRESH_SECONDS)
-    refresh_timer.tick(refresh_leaderboard, inputs=[], outputs=refresh_outputs)
-    refresh_timer.tick(refresh_forecasts, inputs=forecast_dropdowns, outputs=forecast_outputs)
-
-if __name__ == "__main__":
-    demo.queue(default_concurrency_limit=20).launch()

cloud/acceptance.py

@@ -12,7 +12,7 @@ import tempfile
 import time
 
 ROOT = Path(__file__).resolve().parents[1]
-sys.path[:0] = [str(ROOT), str(ROOT / "src")]
+sys.path[:0] = [str(ROOT / "src"), str(ROOT)]
 BRANCH = "acceptance"
 
 

cloud/worker.py

@@ -4,7 +4,7 @@ from pathlib import Path
 import sys
 
 ROOT = Path(__file__).resolve().parents[1]
-sys.path[:0] = [str(ROOT), str(ROOT / "src")]
+sys.path[:0] = [str(ROOT / "src"), str(ROOT)]
 os.chdir(ROOT)
 
 from tsfm_bench.remote_state import RemoteState

constraints.txt

@@ -1,72 +0,0 @@
-# Tested deployment dependency constraints, generated 2026-09-05 on Python 3.11.
-# Regenerate in a clean environment after running CI and smoke tests.
-aiofiles==23.2.1
-annotated-doc==0.0.5
-annotated-types==0.8.0
-anyio==4.15.0
-certifi==2026.7.22
-charset-normalizer==3.5.1
-click==8.5.0
-contourpy==1.3.3; python_version >= "3.11"
-contourpy==1.3.2; python_version < "3.11"
-cycler==0.12.1
-fastapi==0.112.4
-ffmpy==1.0.0
-filelock==3.32.5
-fonttools==4.64.0
-fsspec==2026.7.0
-gluonts==0.16.3
-gradio==4.44.0
-gradio_client==1.3.0
-h11==0.16.0
-hf-xet==1.6.0
-httpcore==1.0.9
-httpx==0.28.1
-huggingface-hub==0.35.2
-idna==3.19
-importlib_resources==6.5.2
-iniconfig==2.3.0
-Jinja2==3.1.6
-kiwisolver==1.5.1
-markdown-it-py==4.2.0
-MarkupSafe==2.1.5
-matplotlib==3.9.4
-mdurl==0.1.2
-numpy==1.26.4
-orjson==3.12.0
-packaging==26.3
-pandas==2.2.3
-patsy==1.0.3
-pillow==10.4.0
-plotly==5.24.1
-pluggy==1.6.0
-pydantic==2.10.6
-pydantic_core==2.27.2
-pydub==0.25.1
-Pygments==2.21.0
-pyparsing==3.3.2
-pytest==8.4.2
-python-dateutil==2.9.0.post0
-python-dotenv==1.2.3
-python-multipart==0.0.32
-pytz==2026.3.post1
-PyYAML==6.0.3
-requests==2.34.2
-rich==15.0.0
-ruff==0.16.6
-scipy==1.11.4
-semantic-version==2.10.0
-shellingham==1.5.4
-six==1.17.0
-starlette==0.37.2
-statsmodels==0.14.6
-tenacity==9.1.4
-tomlkit==0.12.0
-toolz==0.12.1
-tqdm==4.70.0
-typer==0.27.2
-typing_extensions==4.16.0
-tzdata==2026.3
-urllib3==2.7.0
-uvicorn==0.30.6
-websockets==12.0

deployment.json

@@ -1,5 +1,5 @@
 {
   "source_repository": "https://github.com/Thinkcat-Lab/LiveHouse-TS",
   "source_branch": "main",
-  "source_revision": "0d2efcf4a46bffe86cd0bf965a279c46cb2ecc27"
+  "source_revision": "8c9fc27f33a5bfd1b3e4c4d1ff5e7d8c2aa05361"
 }

paper/livehouse_up_to_now_tables.tex

@@ -1,129 +0,0 @@
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset RMSE ($\downarrow$) on the online benchmark. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_rmse}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & \textcolor{red}{\textbf{483.614}} & 11.420 & \textcolor{blue}{\underline{2.830}} & 19.675 & 0.318 & 0.892 & 1.293 & 1.078 & 1.074 & \textcolor{red}{\textbf{8.420}} \\
-TiRex & 497.749 & \textcolor{red}{\textbf{10.843}} & 2.882 & \textcolor{red}{\textbf{16.958}} & 0.339 & 0.899 & 1.329 & 1.003 & \textcolor{blue}{\underline{1.025}} & 9.889 \\
-TimesFM-2.5 & \textcolor{blue}{\underline{485.407}} & \textcolor{blue}{\underline{11.156}} & \textcolor{red}{\textbf{2.812}} & \textcolor{blue}{\underline{17.502}} & \textcolor{red}{\textbf{0.234}} & 0.844 & 1.332 & 1.060 & \textcolor{red}{\textbf{0.988}} & \textcolor{blue}{\underline{8.711}} \\
-Toto-1.0 & 1.162e+03 & 40.693 & 5.314 & 58.600 & 0.539 & 1.093 & 1.578 & 1.208 & 1.835 & 96.250 \\
-Moirai-2.0 & 569.016 & 19.226 & 3.619 & 24.663 & 0.361 & 0.308 & \textcolor{red}{\textbf{0.909}} & \textcolor{blue}{\underline{0.568}} & 1.511 & 13.782 \\
-Chronos-Bolt & 802.832 & 20.359 & 3.917 & 28.495 & 0.634 & \textcolor{red}{\textbf{0.299}} & \textcolor{blue}{\underline{0.943}} & 0.578 & 1.630 & 33.431 \\
-TabPFN-TS & 716.183 & 19.586 & 3.934 & 27.656 & 0.518 & \textcolor{blue}{\underline{0.307}} & 1.141 & \textcolor{red}{\textbf{0.515}} & 1.538 & 20.472 \\
-Sundial & 1.344e+03 & 19.184 & 4.298 & 24.235 & \textcolor{blue}{\underline{0.294}} & 0.410 & 1.313 & 0.890 & 1.539 & 20.726 \\
-\midrule
-Moving-Average & 774.684 & 16.576 & 3.263 & 24.945 & 0.731 & 0.808 & 2.119 & 1.285 & 1.702 & 26.906 \\
-ETS & 543.172 & 18.520 & 3.176 & 23.910 & 0.865 & 0.979 & 5.053 & 0.964 & 7.677 & 28.427 \\
-ARIMA & 665.233 & 15.283 & 3.271 & 26.375 & 0.731 & 0.807 & 3.096 & 0.930 & 2.616 & 29.245 \\
-Seasonal-Naive & 847.250 & 18.334 & 3.983 & 28.209 & 0.755 & 0.873 & 1.500 & 1.329 & 1.373 & 53.966 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset MAPE ($\downarrow$) on the online benchmark. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_mape}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & 0.010 & 0.329 & 0.565 & 0.009 & 0.469 & 0.158 & 0.043 & 0.043 & 0.043 & 0.061 \\
-TiRex & 0.010 & 0.315 & 0.578 & \textcolor{red}{\textbf{0.007}} & 0.591 & 0.164 & 0.043 & 0.038 & \textcolor{blue}{\underline{0.042}} & \textcolor{blue}{\underline{0.057}} \\
-TimesFM-2.5 & 0.010 & \textcolor{blue}{\underline{0.314}} & \textcolor{blue}{\underline{0.493}} & \textcolor{blue}{\underline{0.008}} & \textcolor{red}{\textbf{0.283}} & \textcolor{red}{\textbf{0.145}} & 0.046 & 0.040 & 0.049 & 0.060 \\
-Toto-1.0 & 0.011 & 0.333 & 0.509 & 0.010 & \textcolor{blue}{\underline{0.426}} & 0.171 & 0.034 & 0.031 & \textcolor{red}{\textbf{0.040}} & 0.210 \\
-Moirai-2.0 & \textcolor{red}{\textbf{0.008}} & 0.341 & \textcolor{red}{\textbf{0.483}} & 0.009 & 0.437 & 0.178 & \textcolor{blue}{\underline{0.031}} & \textcolor{blue}{\underline{0.031}} & 0.045 & \textcolor{red}{\textbf{0.046}} \\
-Chronos-Bolt & 0.011 & 0.364 & 0.546 & 0.010 & 0.722 & 0.176 & \textcolor{red}{\textbf{0.030}} & 0.031 & 0.045 & 0.134 \\
-TabPFN-TS & 0.010 & 0.348 & 0.556 & 0.009 & 0.547 & 0.179 & 0.035 & \textcolor{red}{\textbf{0.026}} & 0.044 & 0.066 \\
-Sundial & 0.020 & \textcolor{red}{\textbf{0.282}} & 0.534 & 0.008 & 0.600 & 0.204 & 0.040 & 0.046 & 0.045 & 0.073 \\
-\midrule
-Moving-Average & 0.014 & 0.477 & 0.628 & 0.011 & 1.858 & 0.158 & 0.075 & 0.067 & 0.068 & 0.200 \\
-ETS & \textcolor{blue}{\underline{0.010}} & 0.713 & 0.585 & 0.010 & 1.340 & 0.213 & 0.176 & 0.044 & 0.321 & 0.203 \\
-ARIMA & 0.014 & 0.439 & 0.580 & 0.012 & 1.378 & \textcolor{blue}{\underline{0.155}} & 0.100 & 0.038 & 0.115 & 0.191 \\
-Seasonal-Naive & 0.015 & 0.518 & 0.641 & 0.011 & 1.863 & 0.166 & 0.052 & 0.065 & 0.052 & 0.361 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset CRPS ($\downarrow$) on the online benchmark. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_crps}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & 0.112 & 0.445 & 0.345 & 0.139 & 0.166 & 0.445 & 0.059 & 0.438 & 0.092 & 0.122 \\
-TiRex & 0.118 & 0.436 & 0.347 & 0.139 & 0.174 & 0.428 & 0.056 & 0.408 & 0.100 & 0.118 \\
-TimesFM-2.5 & 0.136 & 0.518 & 0.481 & 0.172 & \textcolor{red}{\textbf{0.147}} & 0.505 & 0.071 & 0.499 & 0.111 & 0.161 \\
-Toto-1.0 & \textcolor{blue}{\underline{0.010}} & \textcolor{red}{\textbf{0.245}} & \textcolor{blue}{\underline{0.273}} & 0.010 & 0.186 & \textcolor{blue}{\underline{0.128}} & 0.027 & \textcolor{blue}{\underline{0.027}} & \textcolor{red}{\textbf{0.036}} & 0.132 \\
-Moirai-2.0 & \textcolor{red}{\textbf{0.008}} & 0.260 & \textcolor{red}{\textbf{0.262}} & \textcolor{blue}{\underline{0.008}} & 0.207 & \textcolor{red}{\textbf{0.124}} & \textcolor{red}{\textbf{0.027}} & 0.028 & 0.040 & \textcolor{red}{\textbf{0.050}} \\
-Chronos-Bolt & 0.010 & 0.272 & 0.278 & 0.010 & 0.365 & 0.129 & \textcolor{blue}{\underline{0.027}} & 0.028 & 0.041 & 0.111 \\
-TabPFN-TS & 0.010 & 0.334 & 0.371 & 0.009 & 0.339 & 0.171 & 0.036 & \textcolor{red}{\textbf{0.026}} & 0.045 & 0.063 \\
-Sundial & 0.018 & \textcolor{blue}{\underline{0.257}} & 0.296 & \textcolor{red}{\textbf{0.007}} & \textcolor{blue}{\underline{0.151}} & 0.164 & 0.033 & 0.039 & \textcolor{blue}{\underline{0.040}} & \textcolor{blue}{\underline{0.054}} \\
-\midrule
-Moving-Average & 0.107 & 0.490 & 0.348 & 0.132 & 0.597 & 0.451 & 0.106 & 0.435 & 0.178 & 0.321 \\
-ETS & 0.099 & 0.829 & 0.348 & 0.111 & 0.575 & 0.516 & 0.279 & 0.301 & 0.903 & 0.323 \\
-ARIMA & 0.117 & 0.457 & 0.338 & 0.117 & 0.514 & 0.458 & 0.174 & 0.345 & 0.356 & 0.284 \\
-Seasonal-Naive & 0.100 & 0.583 & 0.556 & 0.114 & 0.621 & 0.569 & 0.073 & 0.416 & 0.136 & 0.731 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset Temporal Stability ($\downarrow$) on the online benchmark, computed from release-level MSE histories. Cells with fewer than two releases are shown as --. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_stability}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & 7.329e+05 & 494.984 & 8.908 & 2.860e+03 & 0.271 & 3.756 & 1.756 & 27.049 & 1.953 & 129.300 \\
-TiRex & 6.805e+05 & 463.452 & 8.575 & \textcolor{blue}{\underline{2.414e+03}} & 0.310 & 3.479 & 1.653 & 27.449 & 1.788 & 167.781 \\
-TimesFM-2.5 & 6.407e+05 & 499.814 & 8.574 & 2.685e+03 & \textcolor{blue}{\underline{0.137}} & 3.345 & 1.964 & 27.191 & 1.673 & 133.699 \\
-Toto-1.0 & 3.767e+06 & 8.411e+03 & 26.727 & 9.212e+03 & 0.653 & 7.889 & 7.376 & 3.933 & 6.619 & 8.228e+03 \\
-Moirai-2.0 & \textcolor{blue}{\underline{4.540e+05}} & \textcolor{blue}{\underline{185.713}} & \textcolor{blue}{\underline{5.250}} & 2.734e+03 & 0.192 & 0.088 & \textcolor{red}{\textbf{0.375}} & \textcolor{blue}{\underline{0.737}} & 1.538 & \textcolor{blue}{\underline{64.521}} \\
-Chronos-Bolt & 6.818e+05 & \textcolor{red}{\textbf{169.701}} & 5.282 & 3.085e+03 & 0.358 & \textcolor{red}{\textbf{0.052}} & 1.235 & 0.981 & 2.238 & 238.712 \\
-TabPFN-TS & \textcolor{red}{\textbf{4.069e+05}} & 307.897 & 5.972 & 2.749e+03 & 0.288 & \textcolor{blue}{\underline{0.081}} & 0.928 & \textcolor{red}{\textbf{0.701}} & \textcolor{red}{\textbf{1.273}} & 68.714 \\
-Sundial & 1.307e+06 & 645.449 & \textcolor{red}{\textbf{5.049}} & \textcolor{red}{\textbf{2.020e+03}} & \textcolor{red}{\textbf{0.117}} & 0.102 & \textcolor{blue}{\underline{0.666}} & 2.253 & \textcolor{blue}{\underline{1.509}} & \textcolor{red}{\textbf{26.124}} \\
-\midrule
-Moving-Average & 9.664e+05 & 571.085 & 9.040 & 3.870e+03 & 1.352 & 3.555 & 5.080 & 26.020 & 2.855 & 1.196e+03 \\
-ETS & 9.012e+05 & 7.217e+03 & 8.041 & 2.763e+03 & 1.431 & 4.353 & 29.082 & 26.072 & 209.632 & 1.770e+03 \\
-ARIMA & 7.312e+05 & 943.393 & 8.244 & 3.046e+03 & 1.027 & 3.510 & 11.488 & 25.728 & 10.261 & 1.427e+03 \\
-Seasonal-Naive & 1.002e+06 & 644.216 & 12.657 & 4.223e+03 & 1.389 & 3.750 & 2.021 & 25.672 & 1.829 & 4.084e+03 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset Improvement ($\downarrow$; more negative is better) on the online benchmark, computed as Kendall $\tau$ on release-level MSE histories. Cells with fewer than two releases are shown as --. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_improvement}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & 0.560 & 0.588 & 0.398 & 0.224 & -0.033 & -0.500 & -0.138 & -0.025 & 0.527 & 0.704 \\
-TiRex & 0.565 & 0.545 & 0.429 & 0.242 & -0.010 & \textcolor{blue}{\underline{-0.504}} & 0.144 & -0.016 & 0.547 & 0.873 \\
-TimesFM-2.5 & 0.531 & 0.548 & 0.431 & 0.247 & -0.051 & -0.428 & -0.002 & -0.034 & 0.585 & 0.479 \\
-Toto-1.0 & -0.309 & \textcolor{blue}{\underline{0.059}} & -0.273 & \textcolor{red}{\textbf{0.072}} & 0.022 & -0.085 & 0.344 & 0.123 & 0.022 & 1.000 \\
-Moirai-2.0 & \textcolor{blue}{\underline{-0.355}} & \textcolor{red}{\textbf{-0.013}} & -0.351 & 0.132 & -0.028 & \textcolor{red}{\textbf{-0.639}} & -0.048 & \textcolor{red}{\textbf{-0.195}} & \textcolor{blue}{\underline{-0.385}} & \textcolor{red}{\textbf{-1.000}} \\
-Chronos-Bolt & 0.090 & 0.307 & \textcolor{blue}{\underline{-0.371}} & 0.151 & 0.014 & -0.098 & -0.048 & \textcolor{blue}{\underline{-0.143}} & \textcolor{red}{\textbf{-0.429}} & 1.000 \\
-TabPFN-TS & \textcolor{red}{\textbf{-0.505}} & 0.200 & \textcolor{red}{\textbf{-0.415}} & 0.121 & 0.000 & -0.237 & 0.023 & -0.086 & -0.114 & 0.333 \\
-Sundial & 0.503 & 0.066 & -0.271 & \textcolor{blue}{\underline{0.084}} & -0.080 & -0.221 & \textcolor{red}{\textbf{-0.505}} & -0.134 & -0.096 & \textcolor{blue}{\underline{0.000}} \\
-\midrule
-Moving-Average & 0.458 & 0.520 & 0.351 & 0.176 & \textcolor{blue}{\underline{-0.321}} & -0.395 & -0.391 & -0.081 & 0.525 & 0.423 \\
-ETS & 0.345 & 0.533 & 0.374 & 0.221 & -0.267 & -0.476 & -0.379 & 0.054 & 0.296 & 0.366 \\
-ARIMA & 0.393 & 0.555 & 0.414 & 0.191 & -0.313 & -0.464 & \textcolor{blue}{\underline{-0.456}} & -0.079 & 0.364 & 0.592 \\
-Seasonal-Naive & 0.484 & 0.459 & 0.381 & 0.134 & \textcolor{red}{\textbf{-0.329}} & -0.419 & -0.036 & -0.074 & 0.491 & 0.477 \\
-\bottomrule
-\end{tabular}}
-\end{table*}

requirements.txt

@@ -1,64 +0,0 @@
-# Self-contained: HF mounts only this file during dependency installation.
-# Validated Python 3.11 runtime; refresh these pins after deployment tests.
-aiofiles==23.2.1
-annotated-doc==0.0.5
-annotated-types==0.8.0
-anyio==4.15.0
-certifi==2026.7.22
-charset-normalizer==3.5.1
-click==8.5.0
-contourpy==1.3.3; python_version >= "3.11"
-contourpy==1.3.2; python_version < "3.11"
-cycler==0.12.1
-fastapi==0.112.4
-ffmpy==1.0.0
-filelock==3.32.5
-fonttools==4.64.0
-fsspec==2026.7.0
-gradio==4.44.0
-gradio-client==1.3.0
-h11==0.16.0
-hf-xet==1.6.0
-httpcore==1.0.9
-httpx==0.28.1
-huggingface-hub==0.35.2
-idna==3.19
-importlib-resources==6.5.2
-jinja2==3.1.6
-kiwisolver==1.5.1
-markdown-it-py==4.2.0
-markupsafe==2.1.5
-matplotlib==3.9.4
-mdurl==0.1.2
-numpy==1.26.4
-orjson==3.12.0
-packaging==26.3
-pandas==2.2.3
-pillow==10.4.0
-plotly==5.24.1
-pydantic==2.10.6
-pydantic-core==2.27.2
-pydub==0.25.1
-pygments==2.21.0
-pyparsing==3.3.2
-python-dateutil==2.9.0.post0
-python-multipart==0.0.32
-pytz==2026.3.post1
-pyyaml==6.0.3
-requests==2.34.2
-rich==15.0.0
-ruff==0.16.6
-scipy==1.11.4
-semantic-version==2.10.0
-shellingham==1.5.4
-six==1.17.0
-starlette==0.37.2
-tenacity==9.1.4
-tomlkit==0.12.0
-tqdm==4.70.0
-typer==0.27.2
-typing-extensions==4.16.0
-tzdata==2026.3
-urllib3==2.7.0
-uvicorn==0.30.6
-websockets==12.0

results/aggregates/canonical_20260601_20260701/coverage_by_dataset.csv

@@ -1,10 +0,0 @@
-dataset,rows,models,releases,first_target_end,last_target_end
-binance_btcusdt_1h_close/1h/short,246,9,38,2026-06-29T09:00:00+00:00,2026-07-01T23:00:00+00:00
-nasa_power_shanghai_hourly_T2M/1h/short,55,12,6,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-noaa_coops_sf_water_level_water_level/6min/short,557,9,83,2026-06-29T09:30:00+00:00,2026-07-01T14:24:00+00:00
-noaa_ndbc_46013_realtime_wave_height/10min/short,622,9,88,2026-06-28T11:00:00+00:00,2026-07-01T16:00:00+00:00
-open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,163,9,25,2026-06-29T09:00:00+00:00,2026-07-01T16:00:00+00:00
-open_meteo_shanghai_hourly_temperature_2m/1h/short,163,9,25,2026-06-29T09:00:00+00:00,2026-07-01T16:00:00+00:00
-usgs_earthquake_all_week_hourly_earthquake_count/1h/short,156,9,24,2026-06-29T09:00:00+00:00,2026-07-01T16:00:00+00:00
-usgs_potomac_iv_usgs_00060/15min/short,139,7,23,2026-06-30T04:40:00+00:00,2026-07-01T23:40:00+00:00
-wikimedia_time_series_hourly_pageviews/1D/short,28,12,3,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00

results/aggregates/canonical_20260601_20260701/coverage_by_model.csv

@@ -1,13 +0,0 @@
-model,rows,datasets,releases,first_target_end,last_target_end
-ARIMA,296,9,296,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-Chronos-2,281,9,281,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-Chronos-Bolt,3,2,3,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-ETS,296,9,296,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-Moirai-2.0,3,2,3,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Moving-Average,296,9,296,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-Seasonal-Naive,302,9,302,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-Sundial,81,8,81,2026-06-28T23:00:00+00:00,2026-07-01T23:00:00+00:00
-TabPFN-TS,11,8,11,2026-06-28T23:00:00+00:00,2026-07-01T23:00:00+00:00
-TiRex,276,9,276,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-TimesFM-2.5,281,9,281,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-Toto-1.0,3,2,3,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00

results/aggregates/canonical_20260601_20260701/live_overall.csv

@@ -1,13 +0,0 @@
-Rank,model,MSE,RMSE,MAPE,CRPS,RTG,AverageRank,WinRate,Elo,Stability,Improvement,SignificantImprovementRate,n_datasets,n_releases,MAPE_dataset_coverage,first_release,last_release
-1,TimesFM-2.5,1.0946207960049776,0.7646961657025039,0.14955128358112937,0.6119527235117949,,3.4282704702374147,0.6139804278420982,1171.3869526055241,1.4920371416158302,0.2529366945678866,0.0,9,281,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-2,Chronos-2,1.1326388861044336,0.8040364818602377,0.20483778133369082,0.5393027117854747,,3.1909156918934567,0.6580171612906629,1168.8750973854894,1.5180308374609321,0.2804225877171744,0.0,9,281,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-3,Moirai-2.0,0.10018644041932785,0.30975754854164506,0.03920899275826199,0.24000847989006013,,4.25,0.7272727272727273,1135.047754069867,0.07586405508768616,-1.0,0.0,2,3,1.0,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-4,TiRex,1.12712914496804,0.7948460378292348,0.21843260095592407,0.5416192451226494,,3.4156296722812027,0.6384861611886147,1095.2243439994159,1.3638102419455786,0.38381824150617944,0.0,9,276,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-5,Chronos-Bolt,0.19395769821221112,0.4208417594737871,0.0730003428796601,0.31352176156068234,,4.625,0.6704545454545454,1051.5414636174376,0.00049653416664056,-1.0,0.0,2,3,1.0,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-6,Sundial,1.6150782505219166,1.0392895013548342,0.4435806332725354,0.7406157226082475,,4.453430662805663,0.5405867047171394,1046.1068097348239,0.5840532449560404,-0.19732947232947234,0.25,8,81,1.0,2026-06-28T23:00:00+00:00,2026-07-01T23:00:00+00:00
-7,TabPFN-TS,0.98963697165799,0.889824049808239,0.3825136462105129,0.6929009114155815,,5.119047619047619,0.5255376344086021,1003.650854383221,0.07211106608491707,-0.6666666666666667,0.0,8,11,1.0,2026-06-28T23:00:00+00:00,2026-07-01T23:00:00+00:00
-8,Moving-Average,1.8024538802665302,1.049680521985132,0.5493668428959441,0.8221147961275904,,4.111307216685123,0.49103550366538834,951.3076969688816,2.1827485800587865,0.006944405817979387,0.1111111111111111,9,296,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-9,ARIMA,1.9768444915236445,1.1636171313935233,0.3940077958689297,0.8847950863227899,,4.866565223105921,0.4200544753358482,901.4286524981119,2.174248449960733,-0.011613378428388202,0.2222222222222222,9,296,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-10,ETS,5.177408741238722,1.64736124595868,0.42605531372761135,1.3034924877066876,,5.359710127297337,0.3418851424874899,896.4032882514504,6.409952346023613,-0.02379881667834706,0.1111111111111111,9,296,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00
-11,Toto-1.0,1.1435502355886433,0.9696895416381635,0.12676687709347578,0.4220173288549822,,9.25,0.25,840.9967482537461,0.036864244778132556,-1.0,0.0,2,3,1.0,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-12,Seasonal-Naive,2.107866440706461,1.1750989892144703,0.5777647068618941,0.9237466030248728,,5.735473016432319,0.23475691540568477,738.0303382320308,2.1086834208588616,0.07827682078813894,0.2222222222222222,9,302,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:40:00+00:00

results/aggregates/canonical_20260601_20260701/live_rank.csv

@@ -1,13 +0,0 @@
-Rank,model,AverageRank,WinRate,Elo,dataset_pair_matches,shared_releases,pairwise_matches
-1,TimesFM-2.5,3.4282704702374147,0.6139804278420982,1171.3869526055241,75,281,1736
-2,Chronos-2,3.1909156918934567,0.6580171612906629,1168.8750973854894,75,281,1736
-3,Moirai-2.0,4.25,0.7272727272727273,1135.047754069867,22,3,33
-4,TiRex,3.4156296722812027,0.6384861611886147,1095.2243439994159,75,276,1727
-5,Chronos-Bolt,4.625,0.6704545454545454,1051.5414636174376,22,3,33
-6,Sundial,4.453430662805663,0.5405867047171394,1046.1068097348239,69,80,579
-7,TabPFN-TS,5.119047619047619,0.5255376344086021,1003.650854383221,62,10,89
-8,Moving-Average,4.111307216685123,0.49103550366538834,951.3076969688816,75,296,1796
-9,ARIMA,4.866565223105921,0.4200544753358482,901.4286524981119,75,296,1796
-10,ETS,5.359710127297337,0.3418851424874899,896.4032882514504,75,296,1796
-11,Toto-1.0,9.25,0.25,840.9967482537461,22,3,33
-12,Seasonal-Naive,5.735473016432319,0.23475691540568477,738.0303382320308,75,296,1796

results/aggregates/canonical_20260601_20260701/live_results_by_dataset.csv

@@ -1,86 +0,0 @@
-model,dataset,domain,frequency,prediction_lengths,MSE,RMSE,MAPE,CRPS,RTG,Stability,Improvement,Improvement_pvalue,n_releases,MAPE_coverage,first_release,last_release
-ARIMA,binance_btcusdt_1h_close/1h/short,Finance,1h,24,2.822456113542257,1.5248600162517323,0.009262959194545664,0.9795404204409717,,2.8154144175575015,0.4756302521008403,5.8444363787764376e-05,35,1.0,2026-06-29T09:00:00+00:00,2026-07-01T14:00:00+00:00
-ARIMA,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,2.3752999375887875,1.334302029162008,0.09724154338156525,1.039649997352398,,2.1803231694263236,-0.8666666666666666,0.016666666666666666,6,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-ARIMA,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.1815522072544618,0.9538348910186538,2.0630263784410454,0.7469930239099749,,1.153552521089696,-0.053164556962025315,0.4851876467987325,80,1.0,2026-06-29T10:00:00+00:00,2026-07-01T14:24:00+00:00
-ARIMA,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,3.342599636582264,1.681884772885898,0.16754790113146817,1.260294369767515,,2.247567843826165,0.3526675786593707,1.5262181770775351e-06,86,1.0,2026-06-28T11:10:00+00:00,2026-07-01T16:00:00+00:00
-ARIMA,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.6040022637456495,0.732114776137741,0.30795105412375834,0.5474265365122765,,0.4288390879771497,0.3852813852813853,0.01182947469159795,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-ARIMA,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,1.9561336455723293,1.2020668987202836,0.101578963122163,0.9877950838164281,,2.042487342296525,-0.35064935064935066,0.022775270000007175,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-ARIMA,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.5670469341191795,0.7457315141658964,0.5824313431202027,0.4672421704909234,,0.1591782896502134,0.7428571428571429,1.6183725535608672e-07,21,1.0,2026-06-29T10:00:00+00:00,2026-07-01T13:00:00+00:00
-ARIMA,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,4.082408320581292,1.3706493914979119,0.01605557968426735,1.3553010765151436,,8.486229457810229,0.20952380952380956,0.19665272284077664,21,1.0,2026-06-30T05:40:00+00:00,2026-07-01T23:40:00+00:00
-ARIMA,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.8601013647265772,0.9271098927015848,0.20097444062135136,0.5789130980994779,,0.0546439200127943,-1.0,0.3333333333333333,3,1.0,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00
-Chronos-2,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.4075251021967354,1.0412872793785815,0.006952481782665041,0.7078413509977313,,1.526323140102154,0.42045454545454547,0.0004389055813102024,33,1.0,2026-06-29T09:00:00+00:00,2026-07-01T23:00:00+00:00
-Chronos-2,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.36970716562883027,0.5495369413389487,0.04086255894024071,0.3566864252365216,,0.332048510017911,-0.3333333333333333,0.46944444444444444,6,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Chronos-2,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.43633712751417497,0.5609104494027228,0.6532244911198224,0.3482332065695383,,0.5107696783321778,0.0022831050228310505,0.9772043323096734,73,1.0,2026-06-29T10:00:00+00:00,2026-07-01T14:24:00+00:00
-Chronos-2,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.8679948344162147,1.5822486956523245,0.1763029105518717,1.035417906492088,,2.156049135079124,0.49303797468354427,9.609882702934092e-11,80,1.0,2026-06-28T11:10:00+00:00,2026-07-01T16:00:00+00:00
-Chronos-2,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.5990581977504216,0.7218176226812874,0.2636707644834786,0.47427900085093616,,0.5044806088297599,0.5019762845849802,0.0005571976489409922,23,1.0,2026-06-29T11:00:00+00:00,2026-07-01T16:00:00+00:00
-Chronos-2,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.427514290990169,0.6263782472059969,0.043229874154323326,0.33036405565879795,,0.22222447929039651,0.6600790513833992,1.9661343985336093e-06,23,1.0,2026-06-29T11:00:00+00:00,2026-07-01T16:00:00+00:00
-Chronos-2,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.6129169213903741,0.7701448704007136,0.5980517113229076,0.5034326307381657,,0.2421639295578099,0.7662337662337663,1.7950735147639608e-08,22,1.0,2026-06-29T10:00:00+00:00,2026-07-01T16:00:00+00:00
-Chronos-2,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,3.4022970909600385,1.1222657302531316,0.010887987320840741,0.8696144392236914,,8.139666953453888,0.34640522875817,0.047735620701410846,18,1.0,2026-06-30T05:40:00+00:00,2026-07-01T23:40:00+00:00
-Chronos-2,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.07039924409294511,0.26173850042843344,0.050357252327067246,0.22785539030180177,,0.0285511024851686,-0.33333333333333337,1.0,3,1.0,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00
-Chronos-Bolt,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.08470188087812543,0.29103525049819745,0.02384245916541704,0.20932327367458128,,0.00049653416664056,-1.0,1.0,2,1.0,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Chronos-Bolt,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.30321351554629683,0.5506482684493768,0.12215822659390317,0.4177202494467834,,,,,1,1.0,2026-07-01T00:00:00+00:00,2026-07-01T00:00:00+00:00
-ETS,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.8997966065819916,1.2294521966674499,0.0078075746425991755,0.8972701719887477,,1.98066308200576,0.5327731092436975,6.736326393795382e-06,35,1.0,2026-06-29T09:00:00+00:00,2026-07-01T14:00:00+00:00
-ETS,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,6.204682625344804,2.211165426156247,0.17607712807864803,1.7793985333475615,,5.458160768871847,-0.7333333333333333,0.05555555555555555,6,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-ETS,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.5536710780194931,1.1036555532439918,1.9208417419108865,0.8415600303454586,,1.4244893944325039,-0.0481012658227848,0.5277079708402523,80,1.0,2026-06-29T10:00:00+00:00,2026-07-01T14:24:00+00:00
-ETS,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,8.880582977999717,2.4940493173124962,0.25764438345834967,2.0390713909503098,,15.726576130391107,0.16607387140902874,0.023573088960012416,86,1.0,2026-06-28T11:10:00+00:00,2026-07-01T16:00:00+00:00
-ETS,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.146274565865603,0.9280507102029663,0.38801585816373785,0.712214990266385,,1.491148544659128,0.5411255411255411,0.00025589009347005374,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-ETS,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,22.150708073001265,3.9851093045324775,0.3297484841796306,3.328749377356012,,24.142000288760652,-0.4632034632034632,0.002121217969693062,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-ETS,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.5470947455833002,0.7339247232652677,0.5372399407709951,0.4652446874620373,,0.1399769428561504,0.6285714285714286,2.2923472177128296e-05,21,1.0,2026-06-29T10:00:00+00:00,2026-07-01T13:00:00+00:00
-ETS,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,3.2294989095526696,1.172910073955425,0.01236702344197833,1.0130562634077642,,6.771924594100602,0.1619047619047619,0.3232088737909401,21,1.0,2026-06-30T05:40:00+00:00,2026-07-01T23:40:00+00:00
-ETS,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.9843690891996523,0.9679339082917983,0.20475568890167664,0.6548669442359124,,0.5546313681347649,-1.0,0.3333333333333333,3,1.0,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00
-Moirai-2.0,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.12472631142979262,0.34447588277219765,0.029969575598686668,0.25838774262396236,,0.07586405508768616,-1.0,1.0,2,1.0,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Moirai-2.0,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.07564656940886308,0.2750392143110925,0.04844840991783731,0.22162921715615794,,,,,1,1.0,2026-07-01T00:00:00+00:00,2026-07-01T00:00:00+00:00
-Moving-Average,binance_btcusdt_1h_close/1h/short,Finance,1h,24,3.879548758945736,1.6198975095904786,0.010560849387773324,1.3265774000846942,,4.381587816726595,0.5159663865546218,1.3015779113614505e-05,35,1.0,2026-06-29T09:00:00+00:00,2026-07-01T14:00:00+00:00
-Moving-Average,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,1.0960499130731682,0.9311246881488904,0.07622412041636702,0.7206844721385721,,0.9431248403034129,-0.7333333333333333,0.05555555555555555,6,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Moving-Average,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.3032702774101241,0.9560563389769594,3.4404514940816924,0.8146244983340136,,1.6482769308142224,0.04746835443037974,0.5331535206392048,80,1.0,2026-06-29T10:00:00+00:00,2026-07-01T14:24:00+00:00
-Moving-Average,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.878498544762162,1.5515188516837932,0.1632188705878369,1.2462033210899126,,2.077273109894067,0.39863201094391243,5.4985437286793216e-08,86,1.0,2026-06-28T11:10:00+00:00,2026-07-01T16:00:00+00:00
-Moving-Average,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.6984809488069949,0.8053614064456579,0.374457805629871,0.5949954767309134,,0.4044981369948708,0.03896103896103896,0.8236433617484156,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-Moving-Average,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.40014190725311,0.6012266690373912,0.04944943140204369,0.4405782725308695,,0.2786809082070551,-0.8528138528138528,3.5640063923451547e-11,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-Moving-Average,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.5748987086333028,0.7520605313546361,0.6153927218644084,0.47878477143924403,,0.1466860080301499,0.7238095238095239,4.211272699796076e-07,21,1.0,2026-06-29T10:00:00+00:00,2026-07-01T13:00:00+00:00
-Moving-Average,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,4.673657671982387,1.3828249294958572,0.014917885803696703,1.229155643877203,,9.751835316417484,0.2571428571428572,0.11012772228728104,21,1.0,2026-06-30T05:40:00+00:00,2026-07-01T23:40:00+00:00
-Moving-Average,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.7175381915317857,0.8470537731325227,0.1996284068898068,0.547429308922891,,0.012774153141219132,-0.33333333333333337,1.0,3,1.0,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00
-Seasonal-Naive,binance_btcusdt_1h_close/1h/short,Finance,1h,24,4.813570966404525,1.9181878903499499,0.012414171249733607,1.272747464237933,,4.655361308901476,0.6638655462184874,2.0283503167073148e-08,35,1.0,2026-06-29T09:00:00+00:00,2026-07-01T14:00:00+00:00
-Seasonal-Naive,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.4488837921853231,0.6243168605708784,0.0506661425413765,0.46271591951350244,,0.3528933760023636,-0.3333333333333333,0.46944444444444444,6,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Seasonal-Naive,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.3152621882598627,0.9702840530794777,3.4285931803046585,0.8356150837286066,,1.646655675887971,0.06481481481481481,0.39174041854069697,81,1.0,2026-06-29T09:30:00+00:00,2026-07-01T14:24:00+00:00
-Seasonal-Naive,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,3.290914584872926,1.6746026879422429,0.1729298473386337,1.4075220331935165,,2.149066455406273,0.39962576851109327,4.234635923598651e-08,87,1.0,2026-06-28T11:00:00+00:00,2026-07-01T16:00:00+00:00
-Seasonal-Naive,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.8968933325751801,0.933619900739506,0.47213065729508347,0.7935124849293679,,0.3181952783024134,-0.6284584980237155,7.515682058143897e-06,23,1.0,2026-06-29T09:00:00+00:00,2026-07-01T13:00:00+00:00
-Seasonal-Naive,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.345992535211921,0.5623152447125067,0.0399465197859672,0.35936109751177947,,0.2180508192835515,-0.30434782608695654,0.04378445860333526,23,1.0,2026-06-29T09:00:00+00:00,2026-07-01T13:00:00+00:00
-Seasonal-Naive,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.8441908849329445,0.9049882790915159,0.6433211765890576,0.7322836321655182,,0.2884784323372938,0.7922077922077922,3.4958554955895468e-09,22,1.0,2026-06-29T09:00:00+00:00,2026-07-01T13:00:00+00:00
-Seasonal-Naive,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,4.588338338104021,1.4297782409841469,0.014768733189610021,1.0775066290488255,,9.333488699187535,0.38345045611840156,0.012953579532081717,22,1.0,2026-06-30T04:40:00+00:00,2026-07-01T23:40:00+00:00
-Seasonal-Naive,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,2.42675134381145,1.557797745460009,0.365111933462926,1.3724550828948043,,0.015960742420877506,-0.33333333333333337,1.0,3,1.0,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00
-Sundial,binance_btcusdt_1h_close/1h/short,Finance,1h,24,7.070805529763384,2.6245021098597348,0.016690735171805644,2.1724042582510625,,2.2603974911611027,-0.9047619047619049,0.002777777777777778,7,1.0,2026-07-01T08:00:00+00:00,2026-07-01T14:00:00+00:00
-Sundial,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.2941034621401205,0.5313979835324893,0.04000309274444671,0.33260921756720746,,0.12609654017727526,-0.6666666666666669,0.3333333333333333,4,1.0,2026-06-28T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Sundial,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.5179763878564358,0.6856753526189802,2.436725783706289,0.4345523536263045,,0.3221545692059991,0.13333333333333333,0.505644437997331,16,1.0,2026-07-01T07:24:00+00:00,2026-07-01T14:24:00+00:00
-Sundial,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.733418279794468,1.6156065011780023,0.17534006507145453,1.2403994334192399,,1.2627812424578424,0.4594594594594595,6.277276081670365e-05,37,1.0,2026-06-30T09:40:00+00:00,2026-07-01T16:00:00+00:00
-Sundial,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.7660479867577139,0.8271793606199079,0.20036817366579332,0.47063682025001513,,0.5573109835867528,0.9999999999999999,0.016666666666666666,5,1.0,2026-07-01T08:00:00+00:00,2026-07-01T13:00:00+00:00
-Sundial,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.555133570142723,0.7433589653055102,0.052391731833241084,0.40345205339739226,,0.08241498879655114,0.39999999999999997,0.48333333333333334,5,1.0,2026-07-01T08:00:00+00:00,2026-07-01T13:00:00+00:00
-Sundial,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.8497608036820777,0.92147102664975,0.5544287019403262,0.647928901516449,,0.053012873256378296,-0.9999999999999999,0.016666666666666666,5,1.0,2026-07-01T08:00:00+00:00,2026-07-01T13:00:00+00:00
-Sundial,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.13337998403840923,0.36512471107429856,0.07269678204692653,0.22294274283830953,,0.008257271006420864,-1.0,1.0,2,1.0,2026-06-30T00:00:00+00:00,2026-07-01T00:00:00+00:00
-TabPFN-TS,binance_btcusdt_1h_close/1h/short,Finance,1h,24,0.9205243999682691,0.959439628099793,0.00590996758135923,0.8263193121197909,,,,,1,1.0,2026-07-01T13:00:00+00:00,2026-07-01T13:00:00+00:00
-TabPFN-TS,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.18788848606685102,0.41682308197976514,0.03252227639762996,0.3377727897823893,,0.11697040915812769,-0.33333333333333337,1.0,3,1.0,2026-06-28T23:00:00+00:00,2026-07-01T23:00:00+00:00
-TabPFN-TS,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,2.5353655218093705,1.5922831160975646,1.6566085287555021,1.2475896875132062,,,,,1,1.0,2026-07-01T12:54:00+00:00,2026-07-01T12:54:00+00:00
-TabPFN-TS,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,1.2381187510809586,1.1127078462386066,0.0910998740681948,0.9408105512215729,,,,,1,1.0,2026-06-30T13:20:00+00:00,2026-06-30T13:20:00+00:00
-TabPFN-TS,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.9025337271669518,1.3793236484476556,0.2502573283084637,0.8853464787653367,,,,,1,1.0,2026-07-01T13:00:00+00:00,2026-07-01T13:00:00+00:00
-TabPFN-TS,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.13683330665456825,0.3699098628781994,0.025493872543315862,0.2529552033890656,,,,,1,1.0,2026-07-01T13:00:00+00:00,2026-07-01T13:00:00+00:00
-TabPFN-TS,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.8680829549375272,0.9317096945602354,0.9345384759733598,0.7889182503540219,,,,,1,1.0,2026-07-01T13:00:00+00:00,2026-07-01T13:00:00+00:00
-TabPFN-TS,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.12774862557942399,0.35639552016409215,0.06367884605627792,0.26349501817926874,,0.027251723011706454,-1.0,1.0,2,1.0,2026-06-30T00:00:00+00:00,2026-07-01T00:00:00+00:00
-TiRex,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.9113973685052807,1.1800325918776207,0.0080777158182099,0.8163132934877906,,2.2175759385274763,0.3064516129032258,0.01348197375684625,32,1.0,2026-06-29T09:00:00+00:00,2026-07-01T23:00:00+00:00
-TiRex,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.3782069523002641,0.5692331619384968,0.04154718718621655,0.35638413800581586,,0.28726057163730884,0.06666666666666665,1.0,6,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-TiRex,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.4445580942602454,0.5815006146069573,0.7788734809101548,0.36780372784518955,,0.47181991479147856,-0.0121765601217656,0.8788755773695802,73,1.0,2026-06-29T10:00:00+00:00,2026-07-01T14:24:00+00:00
-TiRex,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,3.446267175496363,1.732123686060142,0.18848949368723053,1.111571554362769,,2.2069971572459828,0.33073677377474847,1.605025642096831e-05,79,1.0,2026-06-28T11:10:00+00:00,2026-07-01T16:00:00+00:00
-TiRex,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.5070522715670166,0.66686927641953,0.25594846761031137,0.45385019362958656,,0.37452858504208203,0.3593073593073593,0.01944737175151256,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-TiRex,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.26814542578814593,0.5013796726176349,0.038087057611822246,0.3106830929083624,,0.11855491860945622,0.3593073593073593,0.01944737175151256,22,1.0,2026-06-29T11:00:00+00:00,2026-07-01T13:00:00+00:00
-TiRex,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.5742493424688667,0.7503773871557267,0.5924129714171015,0.4928299257587462,,0.1605591639756147,0.7238095238095239,4.211272699796076e-07,21,1.0,2026-06-29T10:00:00+00:00,2026-07-01T13:00:00+00:00
-TiRex,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,2.521046409820184,0.8683022576534278,0.00801946678471168,0.6946355579571789,,6.414346853202799,0.32026143790849676,0.06849691078121536,18,1.0,2026-06-30T05:40:00+00:00,2026-07-01T23:40:00+00:00
-TiRex,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.0932392645059923,0.303795692133576,0.05443756757755811,0.27050172214840545,,0.022649074478009755,1.0,0.3333333333333333,3,1.0,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00
-TimesFM-2.5,binance_btcusdt_1h_close/1h/short,Finance,1h,24,2.1616544885978333,1.2273148230788373,0.007402062142021325,1.0449221341511221,,2.6306557382819937,0.3106060606060606,0.010756611928087191,33,1.0,2026-06-29T09:00:00+00:00,2026-07-01T23:00:00+00:00
-TimesFM-2.5,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.38678801142300223,0.574958990031141,0.04463643247330778,0.41313545386057265,,0.36986192844341603,-0.3333333333333333,0.46944444444444444,6,1.0,2026-06-26T23:00:00+00:00,2026-07-01T23:00:00+00:00
-TimesFM-2.5,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.19198547909293745,0.3725190047027978,0.2409037606054311,0.2850268917701464,,0.25001983900093905,0.0441400304414003,0.5806530540745722,73,1.0,2026-06-29T10:00:00+00:00,2026-07-01T14:24:00+00:00
-TimesFM-2.5,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.654397990245673,1.5154066695032502,0.14692658015852672,1.256035752712393,,1.7430189583124127,0.5278481012658227,4.2090931439819565e-12,80,1.0,2026-06-28T11:10:00+00:00,2026-07-01T16:00:00+00:00
-TimesFM-2.5,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.6032534821708869,0.713313403994813,0.2724188283970942,0.5091004583769575,,0.5841907030215134,0.525691699604743,0.00027728990904784715,23,1.0,2026-06-29T11:00:00+00:00,2026-07-01T16:00:00+00:00
-TimesFM-2.5,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.2690560448513563,0.5098024642553789,0.04607461425410657,0.38406887347164437,,0.10356560152941825,0.4308300395256917,0.003530488597524882,23,1.0,2026-06-29T11:00:00+00:00,2026-07-01T16:00:00+00:00
-TimesFM-2.5,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,0.5772058470532713,0.7529088365914174,0.5180634479296776,0.5971134923700899,,0.15527718661461343,0.7575757575757576,2.990978565750333e-08,22,1.0,2026-06-29T10:00:00+00:00,2026-07-01T16:00:00+00:00
-TimesFM-2.5,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,2.9286222902116736,0.9373935905156119,0.009281635793637682,0.7788576537027222,,7.571197452283863,0.34640522875817,0.047735620701410846,18,1.0,2026-06-30T05:40:00+00:00,2026-07-01T23:40:00+00:00
-TimesFM-2.5,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.07862353039816625,0.27864770864928706,0.060254190476361456,0.23931380119050613,,0.020546867054301223,-0.33333333333333337,1.0,3,1.0,2026-06-28T00:00:00+00:00,2026-07-01T00:00:00+00:00
-Toto-1.0,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.27020279569399985,0.5192038562415476,0.03279376337497453,0.24702621788878787,,0.036864244778132556,-1.0,1.0,2,1.0,2026-06-30T23:00:00+00:00,2026-07-01T23:00:00+00:00
-Toto-1.0,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,2.016897675483287,1.4201752270347792,0.22073999081197707,0.5970084398211766,,,,,1,1.0,2026-07-01T00:00:00+00:00,2026-07-01T00:00:00+00:00

results/aggregates/canonical_20260601_20260701/livehouse_tables.tex

@@ -1,129 +0,0 @@
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset RMSE ($\downarrow$) on the online benchmark. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_rmse}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & \textcolor{blue}{\underline{1.041}} & 0.722 & 0.770 & 1.122 & \textcolor{blue}{\underline{0.561}} & 1.582 & 0.550 & -- & 0.626 & \textcolor{red}{\textbf{0.262}} \\
-TiRex & 1.180 & \textcolor{red}{\textbf{0.667}} & 0.750 & \textcolor{red}{\textbf{0.868}} & 0.582 & 1.732 & 0.569 & -- & \textcolor{blue}{\underline{0.501}} & 0.304 \\
-TimesFM-2.5 & 1.227 & \textcolor{blue}{\underline{0.713}} & 0.753 & \textcolor{blue}{\underline{0.937}} & \textcolor{red}{\textbf{0.373}} & \textcolor{blue}{\underline{1.515}} & 0.575 & -- & 0.510 & 0.279 \\
-Toto-1.0 & -- & -- & -- & -- & -- & -- & 0.519 & -- & -- & 1.420 \\
-Moirai-2.0 & -- & -- & -- & -- & -- & -- & \textcolor{blue}{\underline{0.344}} & -- & -- & \textcolor{blue}{\underline{0.275}} \\
-Chronos-Bolt & -- & -- & -- & -- & -- & -- & \textcolor{red}{\textbf{0.291}} & -- & -- & 0.551 \\
-TabPFN-TS & \textcolor{red}{\textbf{0.959}} & 1.379 & 0.932 & -- & 1.592 & \textcolor{red}{\textbf{1.113}} & 0.417 & -- & \textcolor{red}{\textbf{0.370}} & 0.356 \\
-Sundial & 2.625 & 0.827 & 0.921 & -- & 0.686 & 1.616 & 0.531 & -- & 0.743 & 0.365 \\
-\midrule
-Moving-Average & 1.620 & 0.805 & 0.752 & 1.383 & 0.956 & 1.552 & 0.931 & -- & 0.601 & 0.847 \\
-ETS & 1.229 & 0.928 & \textcolor{red}{\textbf{0.734}} & 1.173 & 1.104 & 2.494 & 2.211 & -- & 3.985 & 0.968 \\
-ARIMA & 1.525 & 0.732 & \textcolor{blue}{\underline{0.746}} & 1.371 & 0.954 & 1.682 & 1.334 & -- & 1.202 & 0.927 \\
-Seasonal-Naive & 1.918 & 0.934 & 0.905 & 1.430 & 0.970 & 1.675 & 0.624 & -- & 0.562 & 1.558 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset MAPE ($\downarrow$) on the online benchmark. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_mape}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & \textcolor{blue}{\underline{0.007}} & 0.264 & 0.598 & 0.011 & \textcolor{blue}{\underline{0.653}} & 0.176 & 0.041 & -- & 0.043 & \textcolor{blue}{\underline{0.050}} \\
-TiRex & 0.008 & 0.256 & 0.592 & \textcolor{red}{\textbf{0.008}} & 0.779 & 0.188 & 0.042 & -- & \textcolor{blue}{\underline{0.038}} & 0.054 \\
-TimesFM-2.5 & 0.007 & 0.272 & \textcolor{red}{\textbf{0.518}} & \textcolor{blue}{\underline{0.009}} & \textcolor{red}{\textbf{0.241}} & \textcolor{blue}{\underline{0.147}} & 0.045 & -- & 0.046 & 0.060 \\
-Toto-1.0 & -- & -- & -- & -- & -- & -- & 0.033 & -- & -- & 0.221 \\
-Moirai-2.0 & -- & -- & -- & -- & -- & -- & \textcolor{blue}{\underline{0.030}} & -- & -- & \textcolor{red}{\textbf{0.048}} \\
-Chronos-Bolt & -- & -- & -- & -- & -- & -- & \textcolor{red}{\textbf{0.024}} & -- & -- & 0.122 \\
-TabPFN-TS & \textcolor{red}{\textbf{0.006}} & \textcolor{blue}{\underline{0.250}} & 0.935 & -- & 1.657 & \textcolor{red}{\textbf{0.091}} & 0.033 & -- & \textcolor{red}{\textbf{0.025}} & 0.064 \\
-Sundial & 0.017 & \textcolor{red}{\textbf{0.200}} & 0.554 & -- & 2.437 & 0.175 & 0.040 & -- & 0.052 & 0.073 \\
-\midrule
-Moving-Average & 0.011 & 0.374 & 0.615 & 0.015 & 3.440 & 0.163 & 0.076 & -- & 0.049 & 0.200 \\
-ETS & 0.008 & 0.388 & \textcolor{blue}{\underline{0.537}} & 0.012 & 1.921 & 0.258 & 0.176 & -- & 0.330 & 0.205 \\
-ARIMA & 0.009 & 0.308 & 0.582 & 0.016 & 2.063 & 0.168 & 0.097 & -- & 0.102 & 0.201 \\
-Seasonal-Naive & 0.012 & 0.472 & 0.643 & 0.015 & 3.429 & 0.173 & 0.051 & -- & 0.040 & 0.365 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset CRPS ($\downarrow$) on the online benchmark. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_crps}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & \textcolor{red}{\textbf{0.708}} & 0.474 & 0.503 & 0.870 & \textcolor{blue}{\underline{0.348}} & \textcolor{blue}{\underline{1.035}} & 0.357 & -- & 0.330 & 0.228 \\
-TiRex & \textcolor{blue}{\underline{0.816}} & \textcolor{red}{\textbf{0.454}} & 0.493 & \textcolor{red}{\textbf{0.695}} & 0.368 & 1.112 & 0.356 & -- & \textcolor{blue}{\underline{0.311}} & 0.271 \\
-TimesFM-2.5 & 1.045 & 0.509 & 0.597 & \textcolor{blue}{\underline{0.779}} & \textcolor{red}{\textbf{0.285}} & 1.256 & 0.413 & -- & 0.384 & 0.239 \\
-Toto-1.0 & -- & -- & -- & -- & -- & -- & \textcolor{blue}{\underline{0.247}} & -- & -- & 0.597 \\
-Moirai-2.0 & -- & -- & -- & -- & -- & -- & 0.258 & -- & -- & \textcolor{red}{\textbf{0.222}} \\
-Chronos-Bolt & -- & -- & -- & -- & -- & -- & \textcolor{red}{\textbf{0.209}} & -- & -- & 0.418 \\
-TabPFN-TS & 0.826 & 0.885 & 0.789 & -- & 1.248 & \textcolor{red}{\textbf{0.941}} & 0.338 & -- & \textcolor{red}{\textbf{0.253}} & 0.263 \\
-Sundial & 2.172 & \textcolor{blue}{\underline{0.471}} & 0.648 & -- & 0.435 & 1.240 & 0.333 & -- & 0.403 & \textcolor{blue}{\underline{0.223}} \\
-\midrule
-Moving-Average & 1.327 & 0.595 & 0.479 & 1.229 & 0.815 & 1.246 & 0.721 & -- & 0.441 & 0.547 \\
-ETS & 0.897 & 0.712 & \textcolor{red}{\textbf{0.465}} & 1.013 & 0.842 & 2.039 & 1.779 & -- & 3.329 & 0.655 \\
-ARIMA & 0.980 & 0.547 & \textcolor{blue}{\underline{0.467}} & 1.355 & 0.747 & 1.260 & 1.040 & -- & 0.988 & 0.579 \\
-Seasonal-Naive & 1.273 & 0.794 & 0.732 & 1.078 & 0.836 & 1.408 & 0.463 & -- & 0.359 & 1.372 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset Temporal Stability ($\downarrow$) on the online benchmark, computed from release-level MSE histories. Cells with fewer than two releases are shown as --. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_stability}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & \textcolor{red}{\textbf{1.526}} & 0.504 & 0.242 & 8.140 & 0.511 & 2.156 & 0.332 & -- & 0.222 & 0.029 \\
-TiRex & 2.218 & \textcolor{blue}{\underline{0.375}} & 0.161 & \textcolor{red}{\textbf{6.414}} & 0.472 & 2.207 & 0.287 & -- & 0.119 & 0.023 \\
-TimesFM-2.5 & 2.631 & 0.584 & 0.155 & 7.571 & \textcolor{red}{\textbf{0.250}} & \textcolor{blue}{\underline{1.743}} & 0.370 & -- & \textcolor{blue}{\underline{0.104}} & 0.021 \\
-Toto-1.0 & -- & -- & -- & -- & -- & -- & \textcolor{blue}{\underline{0.037}} & -- & -- & -- \\
-Moirai-2.0 & -- & -- & -- & -- & -- & -- & 0.076 & -- & -- & -- \\
-Chronos-Bolt & -- & -- & -- & -- & -- & -- & \textcolor{red}{\textbf{4.965e-04}} & -- & -- & -- \\
-TabPFN-TS & -- & -- & -- & -- & -- & -- & 0.117 & -- & -- & 0.027 \\
-Sundial & 2.260 & 0.557 & \textcolor{red}{\textbf{0.053}} & -- & \textcolor{blue}{\underline{0.322}} & \textcolor{red}{\textbf{1.263}} & 0.126 & -- & \textcolor{red}{\textbf{0.082}} & \textcolor{red}{\textbf{0.008}} \\
-\midrule
-Moving-Average & 4.382 & 0.404 & 0.147 & 9.752 & 1.648 & 2.077 & 0.943 & -- & 0.279 & \textcolor{blue}{\underline{0.013}} \\
-ETS & \textcolor{blue}{\underline{1.981}} & 1.491 & \textcolor{blue}{\underline{0.140}} & \textcolor{blue}{\underline{6.772}} & 1.424 & 15.727 & 5.458 & -- & 24.142 & 0.555 \\
-ARIMA & 2.815 & 0.429 & 0.159 & 8.486 & 1.154 & 2.248 & 2.180 & -- & 2.042 & 0.055 \\
-Seasonal-Naive & 4.655 & \textcolor{red}{\textbf{0.318}} & 0.288 & 9.333 & 1.647 & 2.149 & 0.353 & -- & 0.218 & 0.016 \\
-\bottomrule
-\end{tabular}}
-\end{table*}
-
-\begin{table*}[!t]
-\centering
-\caption{Per-dataset Improvement ($\downarrow$; more negative is better) on the online benchmark, computed as Kendall $\tau$ on release-level MSE histories. Cells with fewer than two releases are shown as --. In each column the best available model is in \textcolor{red}{\textbf{red bold}} and the second best is in \textcolor{blue}{\underline{blue underline}}.}
-\label{tab_perdataset_improvement}
-\resizebox{0.8 \linewidth}{!}{%
-\begin{tabular}{l rrrrrrrrrr}
-\toprule
-Model & BTC & PM2.5 & Quake & Potomac & Water & Wave & T2M & KSFO & Temp2m & Wiki \\
-\midrule
-Chronos-2 & 0.420 & 0.502 & 0.766 & 0.346 & 0.002 & 0.493 & -0.333 & -- & 0.660 & -0.333 \\
-TiRex & \textcolor{blue}{\underline{0.306}} & 0.359 & 0.724 & 0.320 & -0.012 & \textcolor{blue}{\underline{0.331}} & 0.067 & -- & 0.359 & 1.000 \\
-TimesFM-2.5 & 0.311 & 0.526 & 0.758 & 0.346 & 0.044 & 0.528 & -0.333 & -- & 0.431 & -0.333 \\
-Toto-1.0 & -- & -- & -- & -- & -- & -- & \textcolor{red}{\textbf{-1.000}} & -- & -- & -- \\
-Moirai-2.0 & -- & -- & -- & -- & -- & -- & \textcolor{blue}{\underline{-1.000}} & -- & -- & -- \\
-Chronos-Bolt & -- & -- & -- & -- & -- & -- & -1.000 & -- & -- & -- \\
-TabPFN-TS & -- & -- & -- & -- & -- & -- & -0.333 & -- & -- & \textcolor{red}{\textbf{-1.000}} \\
-Sundial & \textcolor{red}{\textbf{-0.905}} & 1.000 & \textcolor{red}{\textbf{-1.000}} & -- & 0.133 & 0.459 & -0.667 & -- & 0.400 & \textcolor{blue}{\underline{-1.000}} \\
-\midrule
-Moving-Average & 0.516 & \textcolor{blue}{\underline{0.039}} & 0.724 & 0.257 & 0.047 & 0.399 & -0.733 & -- & \textcolor{red}{\textbf{-0.853}} & -0.333 \\
-ETS & 0.533 & 0.541 & \textcolor{blue}{\underline{0.629}} & \textcolor{red}{\textbf{0.162}} & \textcolor{blue}{\underline{-0.048}} & \textcolor{red}{\textbf{0.166}} & -0.733 & -- & \textcolor{blue}{\underline{-0.463}} & -1.000 \\
-ARIMA & 0.476 & 0.385 & 0.743 & \textcolor{blue}{\underline{0.210}} & \textcolor{red}{\textbf{-0.053}} & 0.353 & -0.867 & -- & -0.351 & -1.000 \\
-Seasonal-Naive & 0.664 & \textcolor{red}{\textbf{-0.628}} & 0.792 & 0.383 & 0.065 & 0.400 & -0.333 & -- & -0.304 & -0.333 \\
-\bottomrule
-\end{tabular}}
-\end{table*}

results/aggregates/canonical_20260601_20260701/metadata.json

@@ -1,26 +0,0 @@
-{
-  "generated_at": "2026-07-15T10:49:00.285422+00:00",
-  "metric_version": "livehouse-canonical-v1",
-  "protocol": "historical-snapshot-recompute",
-  "causal_protocol_warning": "Metric values were recomputed from stored forecasts and targets. Historical snapshots do not prove that forecasts were frozen before targets became available.",
-  "interval": {
-    "field": "target_window_end",
-    "start_inclusive_utc": "2026-06-01T00:00:00+00:00",
-    "end_inclusive_date_utc": "2026-07-01",
-    "end_exclusive_utc": "2026-07-02T00:00:00+00:00"
-  },
-  "dataset_scope": "paper",
-  "num_rows": 2129,
-  "num_releases": 315,
-  "num_models": 12,
-  "num_datasets": 9,
-  "model_dataset_cells": 85,
-  "all_model_shared_releases": 3,
-  "normalization": "context-only z-normalization for MSE, RMSE, and quantile CRPS; original-scale MAPE",
-  "scan": {
-    "files": 33834,
-    "outside_interval": 26306,
-    "outside_cohort": 3722,
-    "invalid": 0
-  }
-}

results/aggregates/canonical_20260601_20260701/rank_metrics_by_domain.csv

@@ -1,202 +0,0 @@
-domain,metric,model,AverageRank,WinRate,Elo,n_datasets
-Air Quality,RMSE,ARIMA,4.0,0.625,1023.6828000198614,1
-Air Quality,RMSE,Chronos-2,3.0,0.75,1045.5676705184226,1
-Air Quality,RMSE,ETS,7.0,0.25,945.3399355089641,1
-Air Quality,RMSE,Moving-Average,5.0,0.5,999.9418550316178,1
-Air Quality,RMSE,Seasonal-Naive,8.0,0.125,921.636663020127,1
-Air Quality,RMSE,Sundial,6.0,0.375,976.1152893943774,1
-Air Quality,RMSE,TabPFN-TS,9.0,0.0,896.7124464237802,1
-Air Quality,RMSE,TiRex,1.0,1.0,1113.1617980430515,1
-Air Quality,RMSE,TimesFM-2.5,2.0,0.875,1077.8415420397982,1
-Air Quality,MAPE,ARIMA,6.0,0.375,966.7353786912705,1
-Air Quality,MAPE,Chronos-2,4.0,0.625,1022.8321527792635,1
-Air Quality,MAPE,ETS,8.0,0.125,919.1685378287692,1
-Air Quality,MAPE,Moving-Average,7.0,0.25,947.0852423632209,1
-Air Quality,MAPE,Seasonal-Naive,9.0,0.0,898.392087697704,1
-Air Quality,MAPE,Sundial,1.0,1.0,1116.546820585218,1
-Air Quality,MAPE,TabPFN-TS,2.0,0.875,1083.719746215393,1
-Air Quality,MAPE,TiRex,3.0,0.75,1050.8569509722372,1
-Air Quality,MAPE,TimesFM-2.5,5.0,0.5,994.663082866923,1
-Air Quality,CRPS,ARIMA,5.0,0.5,995.860133896551,1
-Air Quality,CRPS,Chronos-2,3.0,0.75,1050.7652539746666,1
-Air Quality,CRPS,ETS,7.0,0.25,946.0470750072143,1
-Air Quality,CRPS,Moving-Average,6.0,0.375,972.7836217105554,1
-Air Quality,CRPS,Seasonal-Naive,8.0,0.125,923.390939708848,1
-Air Quality,CRPS,Sundial,2.0,0.875,1080.7344667176856,1
-Air Quality,CRPS,TabPFN-TS,9.0,0.0,894.8304542825516,1
-Air Quality,CRPS,TiRex,1.0,1.0,1111.1398166169297,1
-Air Quality,CRPS,TimesFM-2.5,4.0,0.625,1024.4482380849977,1
-Finance,RMSE,ARIMA,6.0,0.375,970.3926115036254,1
-Finance,RMSE,Chronos-2,2.0,0.875,1080.914068106025,1
-Finance,RMSE,ETS,5.0,0.5,991.6893467284596,1
-Finance,RMSE,Moving-Average,7.0,0.25,945.5584610079,1
-Finance,RMSE,Seasonal-Naive,8.0,0.125,921.4305712779583,1
-Finance,RMSE,Sundial,9.0,0.0,896.6216555378825,1
-Finance,RMSE,TabPFN-TS,1.0,1.0,1113.7781382952273,1
-Finance,RMSE,TiRex,3.0,0.75,1056.4689436023614,1
-Finance,RMSE,TimesFM-2.5,4.0,0.625,1023.1462039405608,1
-Finance,MAPE,ARIMA,6.0,0.375,970.3926115036254,1
-Finance,MAPE,Chronos-2,2.0,0.875,1080.914068106025,1
-Finance,MAPE,ETS,4.0,0.625,1022.2227486244466,1
-Finance,MAPE,Moving-Average,7.0,0.25,944.2276472308473,1
-Finance,MAPE,Seasonal-Naive,8.0,0.125,920.1982143902625,1
-Finance,MAPE,Sundial,9.0,0.0,895.5070955830221,1
-Finance,MAPE,TabPFN-TS,1.0,1.0,1112.6191016300386,1
-Finance,MAPE,TiRex,5.0,0.5,999.02968322171,1
-Finance,MAPE,TimesFM-2.5,3.0,0.75,1054.888829710023,1
-Finance,CRPS,ARIMA,5.0,0.5,1002.3926115036254,1
-Finance,CRPS,Chronos-2,1.0,1.0,1108.7592747335182,1
-Finance,CRPS,ETS,4.0,0.625,1021.0737419044661,1
-Finance,CRPS,Moving-Average,8.0,0.125,915.0504529561427,1
-Finance,CRPS,Seasonal-Naive,7.0,0.25,944.1923480160216,1
-Finance,CRPS,Sundial,9.0,0.0,893.4187520279228,1
-Finance,CRPS,TabPFN-TS,3.0,0.75,1056.520123209462,1
-Finance,CRPS,TiRex,2.0,0.875,1084.4072239136246,1
-Finance,CRPS,TimesFM-2.5,6.0,0.375,974.1854717352162,1
-Hazards,RMSE,ARIMA,2.0,0.875,1085.1347260005614,1
-Hazards,RMSE,Chronos-2,6.0,0.375,971.3074302704049,1
-Hazards,RMSE,ETS,1.0,1.0,1106.0667484933438,1
-Hazards,RMSE,Moving-Average,4.0,0.625,1024.4670803276392,1
-Hazards,RMSE,Seasonal-Naive,7.0,0.25,942.3803042620115,1
-Hazards,RMSE,Sundial,8.0,0.125,917.1823264286814,1
-Hazards,RMSE,TabPFN-TS,9.0,0.0,891.4720393692653,1
-Hazards,RMSE,TiRex,3.0,0.75,1060.597972929989,1
-Hazards,RMSE,TimesFM-2.5,5.0,0.5,1001.3913719181038,1
-Hazards,MAPE,ARIMA,4.0,0.625,1025.285683479839,1
-Hazards,MAPE,Chronos-2,6.0,0.375,971.3772398744344,1
-Hazards,MAPE,ETS,2.0,0.875,1076.6353795438395,1
-Hazards,MAPE,Moving-Average,7.0,0.25,945.5399944387398,1
-Hazards,MAPE,Seasonal-Naive,8.0,0.125,921.3553628411842,1
-Hazards,MAPE,Sundial,3.0,0.75,1052.8170389834709,1
-Hazards,MAPE,TabPFN-TS,9.0,0.0,893.8729485497969,1
-Hazards,MAPE,TiRex,5.0,0.5,1003.5257281647746,1
-Hazards,MAPE,TimesFM-2.5,1.0,1.0,1109.5906241239204,1
-Hazards,CRPS,ARIMA,2.0,0.875,1085.1347260005614,1
-Hazards,CRPS,Chronos-2,5.0,0.5,1003.3074302704049,1
-Hazards,CRPS,ETS,1.0,1.0,1104.7248746281196,1
-Hazards,CRPS,Moving-Average,3.0,0.75,1053.6459453937093,1
-Hazards,CRPS,Seasonal-Naive,8.0,0.125,911.9121367530553,1
-Hazards,CRPS,Sundial,7.0,0.25,942.3018183567689,1
-Hazards,CRPS,TabPFN-TS,9.0,0.0,889.2678408148331,1
-Hazards,CRPS,TiRex,4.0,0.625,1032.8590196847072,1
-Hazards,CRPS,TimesFM-2.5,6.0,0.375,976.8462080978405,1
-Hydrology,RMSE,ARIMA,5.0,0.3333333333333333,971.2924391266943,1
-Hydrology,RMSE,Chronos-2,3.0,0.6666666666666666,1023.734315662739,1
-Hydrology,RMSE,ETS,4.0,0.5,997.1186900767719,1
-Hydrology,RMSE,Moving-Average,6.0,0.16666666666666666,945.9548412090151,1
-Hydrology,RMSE,Seasonal-Naive,7.0,0.0,919.2411028733098,1
-Hydrology,RMSE,TiRex,1.0,1.0,1088.6668852843436,1
-Hydrology,RMSE,TimesFM-2.5,2.0,0.8333333333333334,1053.991725767126,1
-Hydrology,MAPE,ARIMA,7.0,0.0,914.3077501543988,1
-Hydrology,MAPE,Chronos-2,3.0,0.6666666666666666,1026.0134168718869,1
-Hydrology,MAPE,ETS,4.0,0.5,999.325271080336,1
-Hydrology,MAPE,Moving-Average,6.0,0.16666666666666666,943.0910538364296,1
-Hydrology,MAPE,Seasonal-Naive,5.0,0.3333333333333333,974.0466990518419,1
-Hydrology,MAPE,TiRex,1.0,1.0,1088.9640327334548,1
-Hydrology,MAPE,TimesFM-2.5,2.0,0.8333333333333334,1054.2517762716514,1
-Hydrology,CRPS,ARIMA,7.0,0.0,914.3077501543988,1
-Hydrology,CRPS,Chronos-2,3.0,0.6666666666666666,1026.0134168718869,1
-Hydrology,CRPS,ETS,4.0,0.5,999.325271080336,1
-Hydrology,CRPS,Moving-Average,6.0,0.16666666666666666,943.0910538364296,1
-Hydrology,CRPS,Seasonal-Naive,5.0,0.3333333333333333,974.0466990518419,1
-Hydrology,CRPS,TiRex,1.0,1.0,1088.9640327334548,1
-Hydrology,CRPS,TimesFM-2.5,2.0,0.8333333333333334,1054.2517762716514,1
-Ocean,RMSE,ARIMA,6.0,0.375,942.86770070589,2
-Ocean,RMSE,Chronos-2,3.0,0.75,1077.1337490551311,2
-Ocean,RMSE,ETS,8.5,0.0625,837.457157427826,2
-Ocean,RMSE,Moving-Average,4.5,0.5625,1034.769826745529,2
-Ocean,RMSE,Seasonal-Naive,6.5,0.3125,938.463722059489,2
-Ocean,RMSE,Sundial,4.5,0.5625,1017.558686471443,2
-Ocean,RMSE,TabPFN-TS,5.0,0.5,1041.502478417735,2
-Ocean,RMSE,TiRex,5.5,0.4375,955.93394472455,2
-Ocean,RMSE,TimesFM-2.5,1.5,0.9375,1154.3127343924075,2
-Ocean,MAPE,ARIMA,5.0,0.5,1004.5889893648683,2
-Ocean,MAPE,Chronos-2,4.5,0.5625,997.8500466546354,2
-Ocean,MAPE,ETS,7.0,0.25,887.7333395047749,2
-Ocean,MAPE,Moving-Average,6.0,0.375,981.1140804975242,2
-Ocean,MAPE,Seasonal-Naive,6.5,0.3125,949.5396560414706,2
-Ocean,MAPE,Sundial,6.5,0.3125,941.0492823074759,2
-Ocean,MAPE,TabPFN-TS,2.5,0.8125,1128.4533082077514,2
-Ocean,MAPE,TiRex,5.5,0.4375,955.5961693289275,2
-Ocean,MAPE,TimesFM-2.5,1.5,0.9375,1154.0751280925724,2
-Ocean,CRPS,ARIMA,6.0,0.375,939.0046692101438,2
-Ocean,CRPS,Chronos-2,2.0,0.875,1135.4800201875382,2
-Ocean,CRPS,ETS,8.5,0.0625,835.6889179898117,2
-Ocean,CRPS,Moving-Average,5.5,0.4375,982.8902292697879,2
-Ocean,CRPS,Seasonal-Naive,7.5,0.1875,884.8602391754226,2
-Ocean,CRPS,Sundial,4.0,0.625,1046.4990808995994,2
-Ocean,CRPS,TabPFN-TS,5.0,0.5,1042.2607526137933,2
-Ocean,CRPS,TiRex,3.0,0.75,1091.5870285331866,2
-Ocean,CRPS,TimesFM-2.5,3.5,0.6875,1041.7290621207171,2
-Weather,RMSE,ARIMA,9.5,0.10526315789473684,822.9174773460753,2
-Weather,RMSE,Chronos-2,6.0,0.47368421052631576,966.4550397936893,2
-Weather,RMSE,Chronos-Bolt,1.0,1.0,1144.4047577907875,1
-Weather,RMSE,ETS,10.5,0.0,786.5492065203255,2
-Weather,RMSE,Moirai-2.0,2.0,0.9090909090909091,1121.9043145270387,1
-Weather,RMSE,Moving-Average,7.5,0.3157894736842105,920.5364586608346,2
-Weather,RMSE,Seasonal-Naive,6.5,0.42105263157894735,965.5967935898254,2
-Weather,RMSE,Sundial,6.0,0.47368421052631576,961.4038459245339,2
-Weather,RMSE,TabPFN-TS,2.0,0.8947368421052632,1171.742440160101,2
-Weather,RMSE,TiRex,4.5,0.631578947368421,1062.9376864151006,2
-Weather,RMSE,TimesFM-2.5,5.5,0.5263157894736842,1009.1811134155448,2
-Weather,RMSE,Toto-1.0,4.0,0.7272727272727273,1066.370865856143,1
-Weather,MAPE,ARIMA,9.5,0.10526315789473684,822.9174773460753,2
-Weather,MAPE,Chronos-2,5.0,0.5789473684210527,1023.8929555966173,2
-Weather,MAPE,Chronos-Bolt,1.0,1.0,1144.4047577907875,1
-Weather,MAPE,ETS,10.5,0.0,784.4212914539054,2
-Weather,MAPE,Moirai-2.0,2.0,0.9090909090909091,1121.9043145270387,1
-Weather,MAPE,Moving-Average,8.0,0.2631578947368421,894.6972686614198,2
-Weather,MAPE,Seasonal-Naive,6.0,0.47368421052631576,996.1075566071723,2
-Weather,MAPE,Sundial,6.0,0.47368421052631576,958.6849090926773,2
-Weather,MAPE,TabPFN-TS,2.0,0.8947368421052632,1169.7189674999677,2
-Weather,MAPE,TiRex,4.5,0.631578947368421,1060.4489438866049,2
-Weather,MAPE,TimesFM-2.5,6.5,0.42105263157894735,956.4306916815908,2
-Weather,MAPE,Toto-1.0,4.0,0.7272727272727273,1066.370865856143,1
-Weather,CRPS,ARIMA,9.5,0.10526315789473684,822.4437264113734,2
-Weather,CRPS,Chronos-2,5.0,0.5789473684210527,1030.1346049952824,2
-Weather,CRPS,Chronos-Bolt,1.0,1.0,1145.5363153506528,1
-Weather,CRPS,ETS,10.5,0.0,783.5786103798472,2
-Weather,CRPS,Moirai-2.0,3.0,0.8181818181818182,1090.984125649348,1
-Weather,CRPS,Moving-Average,8.5,0.21052631578947367,866.1958716802466,2
-Weather,CRPS,Seasonal-Naive,6.5,0.42105263157894735,973.5915699662188,2
-Weather,CRPS,Sundial,5.0,0.5789473684210527,1004.8909016572619,2
-Weather,CRPS,TabPFN-TS,3.0,0.7894736842105263,1129.109465319333,2
-Weather,CRPS,TiRex,4.0,0.6842105263157895,1075.5451718761924,2
-Weather,CRPS,TimesFM-2.5,6.5,0.42105263157894735,957.6029943116268,2
-Weather,CRPS,Toto-1.0,2.0,0.9090909090909091,1120.3866424026157,1
-Web,RMSE,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-Web,RMSE,Chronos-2,1.0,1.0,1143.1029179978057,1
-Web,RMSE,Chronos-Bolt,7.0,0.45454545454545453,979.7128328073431,1
-Web,RMSE,ETS,10.0,0.18181818181818182,915.5860102141032,1
-Web,RMSE,Moirai-2.0,2.0,0.9090909090909091,1120.044261467588,1
-Web,RMSE,Moving-Average,8.0,0.36363636363636365,956.2796661057683,1
-Web,RMSE,Seasonal-Naive,12.0,0.0,859.0568087699597,1
-Web,RMSE,Sundial,6.0,0.5454545454545454,1009.3637393654459,1
-Web,RMSE,TabPFN-TS,5.0,0.6363636363636364,1036.6479005321619,1
-Web,RMSE,TiRex,4.0,0.7272727272727273,1064.301675917895,1
-Web,RMSE,TimesFM-2.5,3.0,0.8181818181818182,1092.3279875198925,1
-Web,RMSE,Toto-1.0,11.0,0.09090909090909091,885.086806911113,1
-Web,MAPE,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-Web,MAPE,Chronos-2,2.0,0.9090909090909091,1119.6463781856794,1
-Web,MAPE,Chronos-Bolt,7.0,0.45454545454545453,980.4351380440276,1
-Web,MAPE,ETS,10.0,0.18181818181818182,916.2630631515607,1
-Web,MAPE,Moirai-2.0,1.0,1.0,1141.2762057104214,1
-Web,MAPE,Moving-Average,8.0,0.36363636363636365,956.4325982911496,1
-Web,MAPE,Seasonal-Naive,12.0,0.0,859.1435060528005,1
-Web,MAPE,Sundial,6.0,0.5454545454545454,1009.5182229563097,1
-Web,MAPE,TabPFN-TS,5.0,0.6363636363636364,1036.7929073162422,1
-Web,MAPE,TiRex,3.0,0.8181818181818182,1095.2620928451086,1
-Web,MAPE,TimesFM-2.5,4.0,0.7272727272727273,1061.650166636733,1
-Web,MAPE,Toto-1.0,11.0,0.09090909090909091,885.0903284190435,1
-Web,CRPS,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-Web,CRPS,Chronos-2,3.0,0.8181818181818182,1092.9124955291252,1
-Web,CRPS,Chronos-Bolt,7.0,0.45454545454545453,981.4284989983828,1
-Web,CRPS,ETS,11.0,0.09090909090909091,885.1747664954612,1
-Web,CRPS,Moirai-2.0,1.0,1.0,1143.3554721552562,1
-Web,CRPS,Moving-Average,8.0,0.36363636363636365,958.7402490777979,1
-Web,CRPS,Seasonal-Naive,12.0,0.0,861.2309927421578,1
-Web,CRPS,Sundial,2.0,0.9090909090909091,1119.7022639519219,1
-Web,CRPS,TabPFN-TS,5.0,0.6363636363636364,1037.19012386289,1
-Web,CRPS,TiRex,6.0,0.5454545454545454,1007.4977105945987,1
-Web,CRPS,TimesFM-2.5,4.0,0.7272727272727273,1065.3716991326883,1
-Web,CRPS,Toto-1.0,10.0,0.18181818181818182,908.9063350687956,1

results/aggregates/canonical_20260601_20260701/rank_metrics_by_frequency.csv

@@ -1,148 +0,0 @@
-frequency,metric,model,AverageRank,WinRate,Elo,n_datasets
-10min,RMSE,ARIMA,7.0,0.25,945.43074574341,1
-10min,RMSE,Chronos-2,4.0,0.625,1024.3687150753785,1
-10min,RMSE,ETS,9.0,0.0,892.8739924482007,1
-10min,RMSE,Moving-Average,3.0,0.75,1051.9848183212303,1
-10min,RMSE,Seasonal-Naive,6.0,0.375,973.4718307741487,1
-10min,RMSE,Sundial,5.0,0.5,1001.8252822075692,1
-10min,RMSE,TabPFN-TS,1.0,1.0,1111.1627309146215,1
-10min,RMSE,TiRex,8.0,0.125,919.3928185026132,1
-10min,RMSE,TimesFM-2.5,2.0,0.875,1079.4890660128278,1
-10min,MAPE,ARIMA,4.0,0.625,1022.7899565020151,1
-10min,MAPE,Chronos-2,7.0,0.25,945.2692025021275,1
-10min,MAPE,ETS,9.0,0.0,892.8928094429525,1
-10min,MAPE,Moving-Average,3.0,0.75,1051.9992623863081,1
-10min,MAPE,Seasonal-Naive,5.0,0.5,1002.4161113026107,1
-10min,MAPE,Sundial,6.0,0.375,975.0948037101224,1
-10min,MAPE,TabPFN-TS,1.0,1.0,1110.989065000902,1
-10min,MAPE,TiRex,8.0,0.125,919.2096422496605,1
-10min,MAPE,TimesFM-2.5,2.0,0.875,1079.339146903301,1
-10min,CRPS,ARIMA,7.0,0.25,941.4366648493956,1
-10min,CRPS,Chronos-2,2.0,0.875,1082.06591708269,1
-10min,CRPS,ETS,9.0,0.0,890.9282524829308,1
-10min,CRPS,Moving-Average,5.0,0.5,1000.6158176629559,1
-10min,CRPS,Seasonal-Naive,8.0,0.125,920.611795696644,1
-10min,CRPS,Sundial,4.0,0.625,1030.3982045518148,1
-10min,CRPS,TabPFN-TS,1.0,1.0,1111.684974569111,1
-10min,CRPS,TiRex,3.0,0.75,1054.41968819344,1
-10min,CRPS,TimesFM-2.5,6.0,0.375,967.8386849110178,1
-15min,RMSE,ARIMA,5.0,0.3333333333333333,971.2924391266943,1
-15min,RMSE,Chronos-2,3.0,0.6666666666666666,1023.734315662739,1
-15min,RMSE,ETS,4.0,0.5,997.1186900767719,1
-15min,RMSE,Moving-Average,6.0,0.16666666666666666,945.9548412090151,1
-15min,RMSE,Seasonal-Naive,7.0,0.0,919.2411028733098,1
-15min,RMSE,TiRex,1.0,1.0,1088.6668852843436,1
-15min,RMSE,TimesFM-2.5,2.0,0.8333333333333334,1053.991725767126,1
-15min,MAPE,ARIMA,7.0,0.0,914.3077501543988,1
-15min,MAPE,Chronos-2,3.0,0.6666666666666666,1026.0134168718869,1
-15min,MAPE,ETS,4.0,0.5,999.325271080336,1
-15min,MAPE,Moving-Average,6.0,0.16666666666666666,943.0910538364296,1
-15min,MAPE,Seasonal-Naive,5.0,0.3333333333333333,974.0466990518419,1
-15min,MAPE,TiRex,1.0,1.0,1088.9640327334548,1
-15min,MAPE,TimesFM-2.5,2.0,0.8333333333333334,1054.2517762716514,1
-15min,CRPS,ARIMA,7.0,0.0,914.3077501543988,1
-15min,CRPS,Chronos-2,3.0,0.6666666666666666,1026.0134168718869,1
-15min,CRPS,ETS,4.0,0.5,999.325271080336,1
-15min,CRPS,Moving-Average,6.0,0.16666666666666666,943.0910538364296,1
-15min,CRPS,Seasonal-Naive,5.0,0.3333333333333333,974.0466990518419,1
-15min,CRPS,TiRex,1.0,1.0,1088.9640327334548,1
-15min,CRPS,TimesFM-2.5,2.0,0.8333333333333334,1054.2517762716514,1
-1D,RMSE,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-1D,RMSE,Chronos-2,1.0,1.0,1143.1029179978057,1
-1D,RMSE,Chronos-Bolt,7.0,0.45454545454545453,979.7128328073431,1
-1D,RMSE,ETS,10.0,0.18181818181818182,915.5860102141032,1
-1D,RMSE,Moirai-2.0,2.0,0.9090909090909091,1120.044261467588,1
-1D,RMSE,Moving-Average,8.0,0.36363636363636365,956.2796661057683,1
-1D,RMSE,Seasonal-Naive,12.0,0.0,859.0568087699597,1
-1D,RMSE,Sundial,6.0,0.5454545454545454,1009.3637393654459,1
-1D,RMSE,TabPFN-TS,5.0,0.6363636363636364,1036.6479005321619,1
-1D,RMSE,TiRex,4.0,0.7272727272727273,1064.301675917895,1
-1D,RMSE,TimesFM-2.5,3.0,0.8181818181818182,1092.3279875198925,1
-1D,RMSE,Toto-1.0,11.0,0.09090909090909091,885.086806911113,1
-1D,MAPE,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-1D,MAPE,Chronos-2,2.0,0.9090909090909091,1119.6463781856794,1
-1D,MAPE,Chronos-Bolt,7.0,0.45454545454545453,980.4351380440276,1
-1D,MAPE,ETS,10.0,0.18181818181818182,916.2630631515607,1
-1D,MAPE,Moirai-2.0,1.0,1.0,1141.2762057104214,1
-1D,MAPE,Moving-Average,8.0,0.36363636363636365,956.4325982911496,1
-1D,MAPE,Seasonal-Naive,12.0,0.0,859.1435060528005,1
-1D,MAPE,Sundial,6.0,0.5454545454545454,1009.5182229563097,1
-1D,MAPE,TabPFN-TS,5.0,0.6363636363636364,1036.7929073162422,1
-1D,MAPE,TiRex,3.0,0.8181818181818182,1095.2620928451086,1
-1D,MAPE,TimesFM-2.5,4.0,0.7272727272727273,1061.650166636733,1
-1D,MAPE,Toto-1.0,11.0,0.09090909090909091,885.0903284190435,1
-1D,CRPS,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-1D,CRPS,Chronos-2,3.0,0.8181818181818182,1092.9124955291252,1
-1D,CRPS,Chronos-Bolt,7.0,0.45454545454545453,981.4284989983828,1
-1D,CRPS,ETS,11.0,0.09090909090909091,885.1747664954612,1
-1D,CRPS,Moirai-2.0,1.0,1.0,1143.3554721552562,1
-1D,CRPS,Moving-Average,8.0,0.36363636363636365,958.7402490777979,1
-1D,CRPS,Seasonal-Naive,12.0,0.0,861.2309927421578,1
-1D,CRPS,Sundial,2.0,0.9090909090909091,1119.7022639519219,1
-1D,CRPS,TabPFN-TS,5.0,0.6363636363636364,1037.19012386289,1
-1D,CRPS,TiRex,6.0,0.5454545454545454,1007.4977105945987,1
-1D,CRPS,TimesFM-2.5,4.0,0.7272727272727273,1065.3716991326883,1
-1D,CRPS,Toto-1.0,10.0,0.18181818181818182,908.9063350687956,1
-1h,RMSE,ARIMA,6.2,0.3953488372093023,974.77563535783,5
-1h,RMSE,Chronos-2,4.6,0.5813953488372093,967.990090080745,5
-1h,RMSE,Chronos-Bolt,1.0,1.0,1145.9502782698903,1
-1h,RMSE,ETS,6.8,0.32558139534883723,939.8039049084209,5
-1h,RMSE,Moirai-2.0,2.0,0.9090909090909091,1123.0359225291484,1
-1h,RMSE,Moving-Average,6.2,0.3953488372093023,958.1547192245819,5
-1h,RMSE,Seasonal-Naive,7.2,0.27906976744186046,858.5075387798472,5
-1h,RMSE,Sundial,7.0,0.3023255813953488,832.2384367954261,5
-1h,RMSE,TabPFN-TS,4.6,0.5813953488372093,943.867894048241,5
-1h,RMSE,TiRex,3.2,0.7441860465116279,1151.4888874523688,5
-1h,RMSE,TimesFM-2.5,4.4,0.6046511627906976,1037.2963199744443,5
-1h,RMSE,Toto-1.0,4.0,0.7272727272727273,1066.8903725790549,1
-1h,MAPE,ARIMA,7.0,0.3023255813953488,882.5621108827361,5
-1h,MAPE,Chronos-2,4.4,0.6046511627906976,996.8271323402748,5
-1h,MAPE,Chronos-Bolt,1.0,1.0,1145.818818617784,1
-1h,MAPE,ETS,7.0,0.3023255813953488,897.7511038314186,5
-1h,MAPE,Moirai-2.0,2.0,0.9090909090909091,1123.3112585181564,1
-1h,MAPE,Moving-Average,7.4,0.2558139534883721,830.9555210546473,5
-1h,MAPE,Seasonal-Naive,7.4,0.2558139534883721,841.9975526530181,5
-1h,MAPE,Sundial,5.0,0.5348837209302325,1033.7405334104405,5
-1h,MAPE,TabPFN-TS,3.2,0.7441860465116279,1046.915265409844,5
-1h,MAPE,TiRex,4.4,0.6046511627906976,1054.4768294769776,5
-1h,MAPE,TimesFM-2.5,4.4,0.6046511627906976,1078.9996198016274,5
-1h,MAPE,Toto-1.0,4.0,0.7272727272727273,1066.6442540030744,1
-1h,CRPS,ARIMA,6.2,0.3953488372093023,963.7059354920405,5
-1h,CRPS,Chronos-2,3.8,0.6744186046511628,1053.4629313693526,5
-1h,CRPS,Chronos-Bolt,1.0,1.0,1147.3554637856332,1
-1h,CRPS,ETS,6.6,0.3488372093023256,940.761180570531,5
-1h,CRPS,Moirai-2.0,3.0,0.8181818181818182,1092.7286537771895,1
-1h,CRPS,Moving-Average,6.8,0.32558139534883723,929.7905285214598,5
-1h,CRPS,Seasonal-Naive,7.2,0.27906976744186046,835.4080845508378,5
-1h,CRPS,Sundial,5.6,0.46511627906976744,930.3863589507461,5
-1h,CRPS,TabPFN-TS,5.4,0.4883720930232558,908.6483664977442,5
-1h,CRPS,TiRex,3.0,0.7674418604651163,1133.9893667536883,5
-1h,CRPS,TimesFM-2.5,5.8,0.4418604651162791,943.1688279136874,5
-1h,CRPS,Toto-1.0,2.0,0.9090909090909091,1120.5943018170888,1
-6min,RMSE,ARIMA,5.0,0.5,995.860133896551,1
-6min,RMSE,Chronos-2,2.0,0.875,1077.2197107237466,1
-6min,RMSE,ETS,8.0,0.125,918.4306798066657,1
-6min,RMSE,Moving-Average,6.0,0.375,972.8374986073543,1
-6min,RMSE,Seasonal-Naive,7.0,0.25,947.8678435395773,1
-6min,RMSE,Sundial,4.0,0.625,1024.6395800917048,1
-6min,RMSE,TabPFN-TS,9.0,0.0,896.1655562397349,1
-6min,RMSE,TiRex,3.0,0.75,1057.1276740020323,1
-6min,RMSE,TimesFM-2.5,1.0,1.0,1109.8513230926333,1
-6min,MAPE,ARIMA,6.0,0.375,970.3926115036254,1
-6min,MAPE,Chronos-2,2.0,0.875,1078.1197980295537,1
-6min,MAPE,ETS,5.0,0.5,991.9504104373757,1
-6min,MAPE,Moving-Average,9.0,0.0,890.9399088382542,1
-6min,MAPE,Seasonal-Naive,8.0,0.125,921.2161779930651,1
-6min,MAPE,Sundial,7.0,0.25,951.5446881100709,1
-6min,MAPE,TabPFN-TS,4.0,0.625,1028.3211428004793,1
-6min,MAPE,TiRex,3.0,0.75,1057.4352346979795,1
-6min,MAPE,TimesFM-2.5,1.0,1.0,1110.0800275895967,1
-6min,CRPS,ARIMA,5.0,0.5,995.860133896551,1
-6min,CRPS,Chronos-2,2.0,0.875,1077.2197107237466,1
-6min,CRPS,ETS,8.0,0.125,918.4306798066657,1
-6min,CRPS,Moving-Average,6.0,0.375,972.8374986073543,1
-6min,CRPS,Seasonal-Naive,7.0,0.25,947.8678435395773,1
-6min,CRPS,Sundial,4.0,0.625,1024.6395800917048,1
-6min,CRPS,TabPFN-TS,9.0,0.0,896.1655562397349,1
-6min,CRPS,TiRex,3.0,0.75,1057.1276740020323,1
-6min,CRPS,TimesFM-2.5,1.0,1.0,1109.8513230926333,1

results/aggregates/canonical_20260601_20260701/rank_metrics_by_horizon.csv

@@ -1,127 +0,0 @@
-prediction_length,metric,model,AverageRank,WinRate,Elo,n_datasets
-24,RMSE,ARIMA,6.0,0.3877551020408163,948.9997925759217,6
-24,RMSE,Chronos-2,4.333333333333333,0.5918367346938775,997.1378892469181,6
-24,RMSE,Chronos-Bolt,1.0,1.0,1145.9502782698903,1
-24,RMSE,ETS,6.333333333333333,0.3469387755102041,949.017777322647,6
-24,RMSE,Moirai-2.0,2.0,0.9090909090909091,1123.0359225291484,1
-24,RMSE,Moving-Average,6.166666666666667,0.3673469387755102,909.5154530300852,6
-24,RMSE,Seasonal-Naive,7.166666666666667,0.24489795918367346,806.27295194375,6
-24,RMSE,Sundial,7.0,0.3023255813953488,832.2384367954261,5
-24,RMSE,TabPFN-TS,4.6,0.5813953488372093,943.867894048241,5
-24,RMSE,TiRex,2.8333333333333335,0.7755102040816326,1198.5322815293116,6
-24,RMSE,TimesFM-2.5,4.0,0.6326530612244898,1078.5409501296044,6
-24,RMSE,Toto-1.0,4.0,0.7272727272727273,1066.8903725790549,1
-24,MAPE,ARIMA,7.0,0.2653061224489796,811.2571989698006,6
-24,MAPE,Chronos-2,4.166666666666667,0.6122448979591837,1008.8710865463117,6
-24,MAPE,Chronos-Bolt,1.0,1.0,1145.818818617784,1
-24,MAPE,ETS,6.5,0.32653061224489793,909.180474224301,6
-24,MAPE,Moirai-2.0,2.0,0.9090909090909091,1123.3112585181564,1
-24,MAPE,Moving-Average,7.166666666666667,0.24489795918367346,800.4427577635173,6
-24,MAPE,Seasonal-Naive,7.0,0.2653061224489796,839.5221616705801,6
-24,MAPE,Sundial,5.0,0.5348837209302325,1033.7405334104405,5
-24,MAPE,TabPFN-TS,3.2,0.7441860465116279,1046.915265409844,5
-24,MAPE,TiRex,3.8333333333333335,0.6530612244897959,1114.3795343025106,6
-24,MAPE,TimesFM-2.5,4.0,0.6326530612244898,1099.9166565636788,6
-24,MAPE,Toto-1.0,4.0,0.7272727272727273,1066.6442540030744,1
-24,CRPS,ARIMA,6.333333333333333,0.3469387755102041,878.9468459466577,6
-24,CRPS,Chronos-2,3.6666666666666665,0.673469387755102,1058.2450700040588,6
-24,CRPS,Chronos-Bolt,1.0,1.0,1147.3554637856332,1
-24,CRPS,ETS,6.166666666666667,0.3673469387755102,948.9157378751636,6
-24,CRPS,Moirai-2.0,3.0,0.8181818181818182,1092.7286537771895,1
-24,CRPS,Moving-Average,6.666666666666667,0.30612244897959184,883.1646787243906,6
-24,CRPS,Seasonal-Naive,6.833333333333333,0.2857142857142857,843.3139017278647,6
-24,CRPS,Sundial,5.6,0.46511627906976744,930.3863589507461,5
-24,CRPS,TabPFN-TS,5.4,0.4883720930232558,908.6483664977442,5
-24,CRPS,TiRex,2.6666666666666665,0.7959183673469388,1182.264947599076,6
-24,CRPS,TimesFM-2.5,5.166666666666667,0.4897959183673469,1005.4356732943858,6
-24,CRPS,Toto-1.0,2.0,0.9090909090909091,1120.5943018170888,1
-60,RMSE,ARIMA,5.0,0.5,995.860133896551,1
-60,RMSE,Chronos-2,2.0,0.875,1077.2197107237466,1
-60,RMSE,ETS,8.0,0.125,918.4306798066657,1
-60,RMSE,Moving-Average,6.0,0.375,972.8374986073543,1
-60,RMSE,Seasonal-Naive,7.0,0.25,947.8678435395773,1
-60,RMSE,Sundial,4.0,0.625,1024.6395800917048,1
-60,RMSE,TabPFN-TS,9.0,0.0,896.1655562397349,1
-60,RMSE,TiRex,3.0,0.75,1057.1276740020323,1
-60,RMSE,TimesFM-2.5,1.0,1.0,1109.8513230926333,1
-60,MAPE,ARIMA,6.0,0.375,970.3926115036254,1
-60,MAPE,Chronos-2,2.0,0.875,1078.1197980295537,1
-60,MAPE,ETS,5.0,0.5,991.9504104373757,1
-60,MAPE,Moving-Average,9.0,0.0,890.9399088382542,1
-60,MAPE,Seasonal-Naive,8.0,0.125,921.2161779930651,1
-60,MAPE,Sundial,7.0,0.25,951.5446881100709,1
-60,MAPE,TabPFN-TS,4.0,0.625,1028.3211428004793,1
-60,MAPE,TiRex,3.0,0.75,1057.4352346979795,1
-60,MAPE,TimesFM-2.5,1.0,1.0,1110.0800275895967,1
-60,CRPS,ARIMA,5.0,0.5,995.860133896551,1
-60,CRPS,Chronos-2,2.0,0.875,1077.2197107237466,1
-60,CRPS,ETS,8.0,0.125,918.4306798066657,1
-60,CRPS,Moving-Average,6.0,0.375,972.8374986073543,1
-60,CRPS,Seasonal-Naive,7.0,0.25,947.8678435395773,1
-60,CRPS,Sundial,4.0,0.625,1024.6395800917048,1
-60,CRPS,TabPFN-TS,9.0,0.0,896.1655562397349,1
-60,CRPS,TiRex,3.0,0.75,1057.1276740020323,1
-60,CRPS,TimesFM-2.5,1.0,1.0,1109.8513230926333,1
-7,RMSE,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-7,RMSE,Chronos-2,1.0,1.0,1143.1029179978057,1
-7,RMSE,Chronos-Bolt,7.0,0.45454545454545453,979.7128328073431,1
-7,RMSE,ETS,10.0,0.18181818181818182,915.5860102141032,1
-7,RMSE,Moirai-2.0,2.0,0.9090909090909091,1120.044261467588,1
-7,RMSE,Moving-Average,8.0,0.36363636363636365,956.2796661057683,1
-7,RMSE,Seasonal-Naive,12.0,0.0,859.0568087699597,1
-7,RMSE,Sundial,6.0,0.5454545454545454,1009.3637393654459,1
-7,RMSE,TabPFN-TS,5.0,0.6363636363636364,1036.6479005321619,1
-7,RMSE,TiRex,4.0,0.7272727272727273,1064.301675917895,1
-7,RMSE,TimesFM-2.5,3.0,0.8181818181818182,1092.3279875198925,1
-7,RMSE,Toto-1.0,11.0,0.09090909090909091,885.086806911113,1
-7,MAPE,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-7,MAPE,Chronos-2,2.0,0.9090909090909091,1119.6463781856794,1
-7,MAPE,Chronos-Bolt,7.0,0.45454545454545453,980.4351380440276,1
-7,MAPE,ETS,10.0,0.18181818181818182,916.2630631515607,1
-7,MAPE,Moirai-2.0,1.0,1.0,1141.2762057104214,1
-7,MAPE,Moving-Average,8.0,0.36363636363636365,956.4325982911496,1
-7,MAPE,Seasonal-Naive,12.0,0.0,859.1435060528005,1
-7,MAPE,Sundial,6.0,0.5454545454545454,1009.5182229563097,1
-7,MAPE,TabPFN-TS,5.0,0.6363636363636364,1036.7929073162422,1
-7,MAPE,TiRex,3.0,0.8181818181818182,1095.2620928451086,1
-7,MAPE,TimesFM-2.5,4.0,0.7272727272727273,1061.650166636733,1
-7,MAPE,Toto-1.0,11.0,0.09090909090909091,885.0903284190435,1
-7,CRPS,ARIMA,9.0,0.2727272727272727,938.4893923909236,1
-7,CRPS,Chronos-2,3.0,0.8181818181818182,1092.9124955291252,1
-7,CRPS,Chronos-Bolt,7.0,0.45454545454545453,981.4284989983828,1
-7,CRPS,ETS,11.0,0.09090909090909091,885.1747664954612,1
-7,CRPS,Moirai-2.0,1.0,1.0,1143.3554721552562,1
-7,CRPS,Moving-Average,8.0,0.36363636363636365,958.7402490777979,1
-7,CRPS,Seasonal-Naive,12.0,0.0,861.2309927421578,1
-7,CRPS,Sundial,2.0,0.9090909090909091,1119.7022639519219,1
-7,CRPS,TabPFN-TS,5.0,0.6363636363636364,1037.19012386289,1
-7,CRPS,TiRex,6.0,0.5454545454545454,1007.4977105945987,1
-7,CRPS,TimesFM-2.5,4.0,0.7272727272727273,1065.3716991326883,1
-7,CRPS,Toto-1.0,10.0,0.18181818181818182,908.9063350687956,1
-72,RMSE,ARIMA,7.0,0.25,945.43074574341,1
-72,RMSE,Chronos-2,4.0,0.625,1024.3687150753785,1
-72,RMSE,ETS,9.0,0.0,892.8739924482007,1
-72,RMSE,Moving-Average,3.0,0.75,1051.9848183212303,1
-72,RMSE,Seasonal-Naive,6.0,0.375,973.4718307741487,1
-72,RMSE,Sundial,5.0,0.5,1001.8252822075692,1
-72,RMSE,TabPFN-TS,1.0,1.0,1111.1627309146215,1
-72,RMSE,TiRex,8.0,0.125,919.3928185026132,1
-72,RMSE,TimesFM-2.5,2.0,0.875,1079.4890660128278,1
-72,MAPE,ARIMA,4.0,0.625,1022.7899565020151,1
-72,MAPE,Chronos-2,7.0,0.25,945.2692025021275,1
-72,MAPE,ETS,9.0,0.0,892.8928094429525,1
-72,MAPE,Moving-Average,3.0,0.75,1051.9992623863081,1
-72,MAPE,Seasonal-Naive,5.0,0.5,1002.4161113026107,1
-72,MAPE,Sundial,6.0,0.375,975.0948037101224,1
-72,MAPE,TabPFN-TS,1.0,1.0,1110.989065000902,1
-72,MAPE,TiRex,8.0,0.125,919.2096422496605,1
-72,MAPE,TimesFM-2.5,2.0,0.875,1079.339146903301,1
-72,CRPS,ARIMA,7.0,0.25,941.4366648493956,1
-72,CRPS,Chronos-2,2.0,0.875,1082.06591708269,1
-72,CRPS,ETS,9.0,0.0,890.9282524829308,1
-72,CRPS,Moving-Average,5.0,0.5,1000.6158176629559,1
-72,CRPS,Seasonal-Naive,8.0,0.125,920.611795696644,1
-72,CRPS,Sundial,4.0,0.625,1030.3982045518148,1
-72,CRPS,TabPFN-TS,1.0,1.0,1111.684974569111,1
-72,CRPS,TiRex,3.0,0.75,1054.41968819344,1
-72,CRPS,TimesFM-2.5,6.0,0.375,967.8386849110178,1

results/aggregates/canonical_20260601_20260701/rank_metrics_overall.csv

@@ -1,37 +0,0 @@
-scope,metric,model,AverageRank,WinRate,Elo,n_datasets
-overall,RMSE,ARIMA,6.333333333333333,0.3684210526315789,906.6982362875241,9
-overall,RMSE,Chronos-2,3.6666666666666665,0.6842105263157895,1150.9854331374736,9
-overall,RMSE,Chronos-Bolt,4.0,0.7272727272727273,1071.0461508709514,2
-overall,RMSE,ETS,7.222222222222222,0.2631578947368421,863.8862025349209,9
-overall,RMSE,Moirai-2.0,2.0,0.9090909090909091,1199.30096463289,2
-overall,RMSE,Moving-Average,6.0,0.40789473684210525,915.6819426682551,9
-overall,RMSE,Seasonal-Naive,7.555555555555555,0.2236842105263158,727.5466847822751,9
-overall,RMSE,Sundial,6.25,0.4,908.0281812502944,8
-overall,RMSE,TabPFN-TS,4.75,0.5714285714285714,988.6627427416125,8
-overall,RMSE,TiRex,3.5555555555555554,0.6973684210526315,1176.3618566505604,9
-overall,RMSE,TimesFM-2.5,3.3333333333333335,0.7236842105263158,1167.940922066819,9
-overall,RMSE,Toto-1.0,7.5,0.4090909090909091,923.8606823764223,2
-overall,MAPE,ARIMA,6.777777777777778,0.3157894736842105,830.2586177483358,9
-overall,MAPE,Chronos-2,4.0,0.6447368421052632,1121.3467455422456,9
-overall,MAPE,Chronos-Bolt,4.0,0.7272727272727273,1072.1394130016756,2
-overall,MAPE,ETS,7.0,0.2894736842105263,847.1965429113052,9
-overall,MAPE,Moirai-2.0,1.5,0.9545454545454546,1222.1912530154518,2
-overall,MAPE,Moving-Average,7.0,0.2894736842105263,837.1584688990293,9
-overall,MAPE,Seasonal-Naive,7.444444444444445,0.23684210526315788,748.3137403699099,9
-overall,MAPE,Sundial,5.5,0.4857142857142857,1015.3025184469101,8
-overall,MAPE,TabPFN-TS,3.25,0.7428571428571429,1072.4878625582858,8
-overall,MAPE,TiRex,4.111111111111111,0.631578947368421,1158.0699660096284,9
-overall,MAPE,TimesFM-2.5,3.4444444444444446,0.7105263157894737,1149.3589284691482,9
-overall,MAPE,Toto-1.0,7.5,0.4090909090909091,926.1759430280745,2
-overall,CRPS,ARIMA,6.555555555555555,0.34210526315789475,858.7157731112528,9
-overall,CRPS,Chronos-2,3.2222222222222223,0.7368421052631579,1148.1110696903756,9
-overall,CRPS,Chronos-Bolt,4.0,0.7272727272727273,1073.461023738584,2
-overall,CRPS,ETS,7.222222222222222,0.2631578947368421,830.7041309304514,9
-overall,CRPS,Moirai-2.0,2.0,0.9090909090909091,1204.7838933531712,2
-overall,CRPS,Moving-Average,6.555555555555555,0.34210526315789475,893.5320251559683,9
-overall,CRPS,Seasonal-Naive,7.555555555555555,0.2236842105263158,740.0420618137904,9
-overall,CRPS,Sundial,4.75,0.5714285714285714,1083.2903317736366,8
-overall,CRPS,TabPFN-TS,5.25,0.5142857142857142,977.5244279282712,8
-overall,CRPS,TiRex,3.111111111111111,0.75,1130.3347903897736,9
-overall,CRPS,TimesFM-2.5,4.666666666666667,0.5657894736842105,1077.0558861204443,9
-overall,CRPS,Toto-1.0,6.0,0.5454545454545454,982.4445859942808,2

results/aggregates/live_metadata.json

@@ -1,45 +0,0 @@
-{
-  "generated_at": "2026-07-30T04:35:52.403587+00:00",
-  "scope": "Canonical metrics-only release history when available; otherwise legacy release history plus latest allowlisted snapshots",
-  "release_deduplication": "One row per model, dataset, data source timestamp, and prediction length",
-  "dataset_aggregation": "Arithmetic mean over releases, then equal-weight mean over datasets",
-  "persistence": "Public aggregates contain metric rows only. Forecast/target snapshots may be retained privately for audit and are excluded from Space uploads.",
-  "metric_version": "livehouse-canonical-v1",
-  "normalization": "Context-only z-normalization for MSE/RMSE and quantile-CRPS; original-scale MAPE",
-  "mape": "Original-scale p50 MAPE; omitted when any target is too close to zero",
-  "crps": "Twice the mean pinball loss over q=0.1,...,0.9 after context-only z-normalization",
-  "rtg": "100 * (MSE_seasonal_naive - MSE_model) / (MSE_seasonal_naive + MSE_model) on metrics-only matched releases",
-  "ranking": "Dataset-balanced pairwise MSE/CRPS win rate on shared releases; eligible pairs require >=30 releases, >=5 datasets, and >=7 days of coverage; official models require >=3 opponents in the main comparison component",
-  "temporal_metrics": "Per-dataset MSE stability and Kendall tau, then equal-weight mean over datasets",
-  "num_models": 12,
-  "num_datasets": 13,
-  "num_model_releases": 27830,
-  "num_unique_releases": 2741,
-  "fixed_windows": {
-    "1d": {
-      "days": 1,
-      "num_model_releases": 180,
-      "num_unique_releases": 15,
-      "ranking_scope": "Cumulative release history through reference_time",
-      "metrics_scope": "Trailing 24 hours through reference_time"
-    },
-    "7d": {
-      "days": 7,
-      "num_model_releases": 2478,
-      "num_unique_releases": 207,
-      "ranking_scope": "Cumulative release history through reference_time",
-      "metrics_scope": "Trailing 168 hours through reference_time"
-    },
-    "30d": {
-      "days": 30,
-      "num_model_releases": 26603,
-      "num_unique_releases": 2553,
-      "ranking_scope": "Cumulative release history through reference_time",
-      "metrics_scope": "Trailing 720 hours through reference_time"
-    }
-  },
-  "protocol_counts": {
-    "historical-snapshot-recompute": 22388,
-    "prequential-v1": 5442
-  }
-}

results/aggregates/live_overall_1d.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,MSE,RMSE,MAPE,CRPS,RTG,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days,Stability,Improvement,SignificantImprovementRate,n_datasets,n_releases,MAPE_dataset_coverage,first_release,last_release
-1,Official,Chronos-2,193.64446911942545,3.438028930407185,0.26718939459984553,3.1875944354633323,23.29093504132125,0.6690595882869556,11,2681,13,34.46875,781.2115679067806,-0.32763147756116817,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-2,Official,TiRex,193.80401038476273,3.522303943995241,0.34459823764561115,3.2559033603412564,20.059157179010704,0.6672506631965874,11,2672,13,34.46875,781.585389425669,-0.620126536676021,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-3,Official,TimesFM-2.5,193.86412420689712,3.4803583784522645,0.18945546081745926,3.2462041859023487,16.173459040435468,0.6084222193830509,11,2667,13,34.46875,781.8712292744625,-0.620126536676021,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-4,Official,Moirai-2.0,194.73776743040773,3.563040699148272,0.4832484719803291,3.264389584694608,4.9167401436396725,0.5788853136781448,11,1923,13,29.125,785.0608279292065,-0.24595492912420727,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-5,Official,TabPFN-TS,193.9935563431534,3.664733345225218,0.35284269070748464,3.414174087094596,-10.616745074348447,0.558456153060992,11,1812,13,31.125,781.190156397884,-0.4681771513464296,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-6,Official,Chronos-Bolt,195.6153930378029,3.662133091914785,0.5027002678033098,3.336756987648861,1.4295223513475743,0.5235332252610707,11,1910,13,29.125,787.8639629390365,-0.912621595790874,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-7,Official,Sundial,195.61907059427773,3.5759252361850598,0.32622081962472776,3.2626104178227875,-0.50544522653394,0.5128812538914634,11,2161,13,31.125,788.2283010450695,-0.4222222222222222,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-8,Official,Seasonal-Naive,196.5325100366261,3.744084559932112,0.608353446758644,3.3989703870045345,0.0,0.38680236507990295,11,2512,13,34.46875,791.0377164040988,0.0,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-9,Official,Moving-Average,197.03689281510916,3.7361223640286787,0.599322288789598,3.417406058535502,-17.672406057178254,0.38017698152671175,11,2512,13,34.46875,793.5823143695399,-0.3162277660168379,0.14285714285714285,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-10,Official,ARIMA,193.88876403961075,3.88343766425971,0.5955451634943991,3.8147299549163565,-27.922723315462864,0.3742819212234938,11,2512,13,34.46875,779.4303448431646,-0.46817715134642945,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-11,Official,Toto-1.0,196.248471274055,3.9932778808169798,0.42681688523206013,3.2793610290421396,-15.965265429543447,0.3741511178964434,11,1937,13,29.125,787.3235403312923,-0.15555555555555559,0.0,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00
-12,Official,ETS,196.1893924690447,4.166455453740183,0.7394114310988326,3.8004888510083057,-32.291563407364464,0.3660991975151834,11,2512,13,34.46875,784.0553610248666,-0.5384499882390601,0.14285714285714285,7,15,0.8571428571428571,2026-07-29T04:00:00+00:00,2026-07-30T02:00:00+00:00

results/aggregates/live_overall_30d.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,MSE,RMSE,MAPE,CRPS,RTG,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days,Stability,Improvement,SignificantImprovementRate,n_datasets,n_releases,MAPE_dataset_coverage,first_release,last_release
-1,Official,Chronos-2,15.239897859904232,0.901048483104018,0.1548565306026782,0.6622461194917094,22.838300605926754,0.6690595882869556,11,2681,13,34.46875,136.4562248202112,0.019190627922101824,0.23076923076923078,13,2518,0.8461538461538461,2026-06-30T02:20:00+00:00,2026-07-30T02:00:00+00:00
-2,Official,TiRex,15.39739734180183,0.9005562656767363,0.1895023703088925,0.6928342270788045,24.53903461278223,0.6672506631965874,11,2672,13,34.46875,139.11264513318267,0.020447371797183016,0.3076923076923077,13,2505,0.8461538461538461,2026-06-30T02:20:00+00:00,2026-07-30T02:00:00+00:00
-3,Official,TimesFM-2.5,15.291133001124964,0.9005596272483474,0.13700323477956117,0.7406992325742251,23.341632180734337,0.6084222193830509,11,2667,13,34.46875,136.70613360141996,0.02101967941113391,0.23076923076923078,13,2499,0.8461538461538461,2026-06-30T02:20:00+00:00,2026-07-30T02:00:00+00:00
-4,Official,Moirai-2.0,18.964699125331904,0.9471157619161314,0.24052342246408792,0.6930558742857736,22.199859606845248,0.5788853136781448,11,1923,13,29.125,155.31691524744969,0.06332808667780647,0.23076923076923078,13,1923,0.8461538461538461,2026-06-30T23:00:00+00:00,2026-07-30T02:00:00+00:00
-5,Official,TabPFN-TS,20.716132556473227,0.9981454424556762,0.20298864124009625,0.8428840553795296,18.27860198272448,0.558456153060992,11,1812,13,31.125,162.3845507874026,0.04985123682012013,0.23076923076923078,13,1813,0.8461538461538461,2026-06-30T03:30:00+00:00,2026-07-30T02:00:00+00:00
-6,Official,Chronos-Bolt,19.243386009848898,0.993584447317904,0.27586325396117223,0.7412796604919597,11.5411935730001,0.5235332252610707,11,1910,13,29.125,156.24388833860218,0.022997693694017777,0.15384615384615385,13,1910,0.8461538461538461,2026-06-30T23:00:00+00:00,2026-07-30T02:00:00+00:00
-7,Official,Sundial,18.564900214543123,1.032774700614687,0.22411709154183493,0.7858926738426515,16.044363997604048,0.5128812538914634,11,2161,13,31.125,150.44897504584685,0.0063299929730214095,0.3076923076923077,13,2148,0.8461538461538461,2026-06-30T09:40:00+00:00,2026-07-30T02:00:00+00:00
-8,Official,Seasonal-Naive,17.15595927072993,1.2560789559232828,0.34098065730172983,0.9805046204472379,0.0,0.38680236507990295,11,2512,13,34.46875,141.62377015477801,0.027201234219787096,0.23076923076923078,13,2339,0.8461538461538461,2026-06-30T02:20:00+00:00,2026-07-30T02:00:00+00:00
-9,Official,Moving-Average,16.892138782232788,1.1615436554645537,0.3164168930654245,0.9356360041893635,2.6850309083573025,0.38017698152671175,11,2512,13,34.46875,141.85276157541333,0.07976284316644308,0.07692307692307693,13,2337,0.8461538461538461,2026-06-30T02:20:00+00:00,2026-07-30T02:00:00+00:00
-10,Official,ARIMA,16.78545965829615,1.1633283246064934,0.3351722615580132,0.9219099971249531,1.5967004531805107,0.3742819212234938,11,2512,13,34.46875,141.79419447592238,0.0627638992178676,0.15384615384615385,13,2337,0.8461538461538461,2026-06-30T02:20:00+00:00,2026-07-30T02:00:00+00:00
-11,Official,Toto-1.0,29.603104139697532,1.677365790548887,0.2817679303767769,0.7234731989609118,-19.01389910274924,0.3741511178964434,11,1937,13,29.125,211.36132625316623,-0.011351184970238643,0.23076923076923078,13,1937,0.8461538461538461,2026-06-30T23:00:00+00:00,2026-07-30T02:00:00+00:00
-12,Official,ETS,18.431513752532883,1.4053510594848482,0.3033654302510692,1.1167122642915905,-3.5900164079107237,0.3660991975151834,11,2512,13,34.46875,146.47919370602278,0.08448100378881603,0.15384615384615385,13,2337,0.8461538461538461,2026-06-30T02:20:00+00:00,2026-07-30T02:00:00+00:00

results/aggregates/live_overall_7d.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,MSE,RMSE,MAPE,CRPS,RTG,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days,Stability,Improvement,SignificantImprovementRate,n_datasets,n_releases,MAPE_dataset_coverage,first_release,last_release
-1,Official,Chronos-2,140.61238667145676,1.9343044138710643,0.164446920361167,1.7288297147294374,15.807633203654483,0.6690595882869556,11,2681,13,34.46875,451.4946233781509,-0.17615755240541348,0.09090909090909091,11,207,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-2,Official,TiRex,141.45727570100632,1.9039586311067225,0.17051072367801082,2.0283690172965128,19.844267223590453,0.6672506631965874,11,2672,13,34.46875,460.2034749826222,-0.11594576824052648,0.09090909090909091,11,207,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-3,Official,TimesFM-2.5,140.54427674478487,1.9244555138681192,0.14343516168544027,1.7884667267589165,13.391796693711592,0.6084222193830509,11,2667,13,34.46875,451.5034140569111,-0.20140324458806472,0.09090909090909091,11,207,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-4,Official,Moirai-2.0,140.72683930119527,1.9631859680052548,0.2630927248225825,1.7341127026158951,12.75025227594678,0.5788853136781448,11,1923,13,29.125,451.6875812843316,-0.11018543068303743,0.0,11,207,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-5,Official,TabPFN-TS,140.78892054096073,2.0199345729056217,0.23533229169854022,1.8846251198600148,7.354546089942443,0.558456153060992,11,1812,13,31.125,451.5996749358133,-0.09315029311223505,0.0,11,206,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-6,Official,Chronos-Bolt,140.70895376728242,1.9739597606035524,0.28946345234222365,1.7665494033955995,4.150582304787195,0.5235332252610707,11,1910,13,29.125,451.7544595272939,-0.12453041720113647,0.0,11,207,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-7,Official,Sundial,140.8817777156987,1.9753005997902717,0.26217171812652695,1.772561167884139,11.449439751983403,0.5128812538914634,11,2161,13,31.125,451.5635898136403,-0.24820886962924452,0.18181818181818182,11,206,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-8,Official,Seasonal-Naive,141.42130897420378,2.1747459027017366,0.40370611074166085,1.793069199174043,0.0,0.38680236507990295,11,2512,13,34.46875,452.00266902106125,-0.11480089900789477,0.09090909090909091,11,206,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-9,Official,Moving-Average,141.29804082848557,2.1747051296133297,0.4248256692782988,1.9700032823486773,-9.762972341078944,0.38017698152671175,11,2512,13,34.46875,451.77239836525496,-0.24660186029998074,0.09090909090909091,11,206,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-10,Official,ARIMA,141.12747507806617,2.266735075229248,0.34981331201040294,1.9928023240192465,-13.826959012721051,0.3742819212234938,11,2512,13,34.46875,451.5735101268976,-0.018034618076678735,0.09090909090909091,11,206,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-11,Official,Toto-1.0,185.37494285162327,2.555048323056507,0.24474230946552197,1.653487017163294,-25.86441523301397,0.3741511178964434,11,1937,13,29.125,576.8791372360803,-0.13007904054374775,0.09090909090909091,11,207,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00
-12,Official,ETS,142.61734628170217,2.5785629461854858,0.4697530826001883,2.2982323637753477,-20.373724513722344,0.3660991975151834,11,2512,13,34.46875,453.505495842816,-0.03616703152576467,0.0,11,206,0.8181818181818182,2026-07-23T04:30:00+00:00,2026-07-30T02:00:00+00:00

results/aggregates/live_overall_up_to_now.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,MSE,RMSE,MAPE,CRPS,RTG,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days,Stability,Improvement,SignificantImprovementRate,n_datasets,n_releases,MAPE_dataset_coverage,first_release,last_release
-1,Official,Chronos-2,15.20065110905645,0.8937239377360141,0.1595855540811949,0.6573975798558322,23.51782160705088,0.6690595882869556,11,2681,13,34.46875,136.30960528511025,0.03184941741642475,0.23076923076923078,13,2686,0.8461538461538461,2026-06-25T14:45:00+00:00,2026-07-30T02:00:00+00:00
-2,Official,TiRex,15.369354212968647,0.8969080505643137,0.19489237513970423,0.6900315782371714,24.80863619706493,0.6672506631965874,11,2672,13,34.46875,138.9674390379394,0.03157193923246989,0.23076923076923078,13,2672,0.8461538461538461,2026-06-25T14:45:00+00:00,2026-07-30T02:00:00+00:00
-3,Official,TimesFM-2.5,15.254282217764201,0.8936344799467592,0.13715137087264503,0.7355018526881735,23.890806166104504,0.6084222193830509,11,2667,13,34.46875,136.561606207296,0.03261972566597339,0.23076923076923078,13,2667,0.8461538461538461,2026-06-25T14:45:00+00:00,2026-07-30T02:00:00+00:00
-4,Official,Moirai-2.0,18.964699125331904,0.9471157619161314,0.24052342246408792,0.6930558742857736,22.199859606845248,0.5788853136781448,11,1923,13,29.125,155.31691524744969,0.06332808667780647,0.23076923076923078,13,1923,0.8461538461538461,2026-06-30T23:00:00+00:00,2026-07-30T02:00:00+00:00
-5,Official,TabPFN-TS,20.714494432451236,0.9970897979469994,0.20276735827743064,0.841865125037099,18.45123087787983,0.558456153060992,11,1812,13,31.125,162.3831518994619,0.04544584164549416,0.23076923076923078,13,1815,0.8461538461538461,2026-06-28T23:00:00+00:00,2026-07-30T02:00:00+00:00
-6,Official,Chronos-Bolt,19.243386009848898,0.993584447317904,0.27586325396117223,0.7412796604919597,11.5411935730001,0.5235332252610707,11,1910,13,29.125,156.24388833860218,0.022997693694017777,0.15384615384615385,13,1910,0.8461538461538461,2026-06-30T23:00:00+00:00,2026-07-30T02:00:00+00:00
-7,Official,Sundial,18.564239204143057,1.0326603756602528,0.22403188464021603,0.7855252616483439,16.177869036676984,0.5128812538914634,11,2161,13,31.125,150.44723331195462,3.3155906953579e-05,0.3076923076923077,13,2163,0.8461538461538461,2026-06-28T23:00:00+00:00,2026-07-30T02:00:00+00:00
-8,Official,Seasonal-Naive,17.11844033135731,1.2526930578349464,0.3684952179564504,0.9803087909289953,0.0,0.38680236507990295,11,2512,13,34.46875,141.46797704091742,0.03556609747964632,0.3076923076923077,13,2521,0.8461538461538461,2026-06-25T14:25:00+00:00,2026-07-30T02:00:00+00:00
-9,Official,Moving-Average,16.871535126086044,1.1621563925242528,0.34440384104469696,0.9376159102253953,2.7912100643977933,0.38017698152671175,11,2512,13,34.46875,141.7141717913958,0.06665894996018105,0.15384615384615385,13,2512,0.8461538461538461,2026-06-25T14:45:00+00:00,2026-07-30T02:00:00+00:00
-10,Official,ARIMA,16.780773904823985,1.1679930873184594,0.3469619237383255,0.9256104703923624,1.544820044428646,0.3742819212234938,11,2512,13,34.46875,141.66498910172018,0.04427607444898624,0.15384615384615385,13,2512,0.8461538461538461,2026-06-25T14:45:00+00:00,2026-07-30T02:00:00+00:00
-11,Official,Toto-1.0,29.603104139697532,1.677365790548887,0.2817679303767769,0.7234731989609118,-19.01389910274924,0.3741511178964434,11,1937,13,29.125,211.36132625316623,-0.011351184970238643,0.23076923076923078,13,1937,0.8461538461538461,2026-06-30T23:00:00+00:00,2026-07-30T02:00:00+00:00
-12,Official,ETS,18.576087402020974,1.4280864485043077,0.3173487402563386,1.1366416142439497,-3.93013373932143,0.3660991975151834,11,2512,13,34.46875,146.5549935171359,0.0500581925005512,0.15384615384615385,13,2512,0.8461538461538461,2026-06-25T14:45:00+00:00,2026-07-30T02:00:00+00:00

results/aggregates/live_rank_1d.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days
-1,Official,Chronos-2,0.6690595882869556,11,2681,13,34.46875
-2,Official,TiRex,0.6672506631965874,11,2672,13,34.46875
-3,Official,TimesFM-2.5,0.6084222193830509,11,2667,13,34.46875
-4,Official,Moirai-2.0,0.5788853136781448,11,1923,13,29.125
-5,Official,TabPFN-TS,0.558456153060992,11,1812,13,31.125
-6,Official,Chronos-Bolt,0.5235332252610707,11,1910,13,29.125
-7,Official,Sundial,0.5128812538914634,11,2161,13,31.125
-8,Official,Seasonal-Naive,0.38680236507990295,11,2512,13,34.46875
-9,Official,Moving-Average,0.38017698152671175,11,2512,13,34.46875
-10,Official,ARIMA,0.3742819212234938,11,2512,13,34.46875
-11,Official,Toto-1.0,0.3741511178964434,11,1937,13,29.125
-12,Official,ETS,0.3660991975151834,11,2512,13,34.46875

results/aggregates/live_rank_30d.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days
-1,Official,Chronos-2,0.6690595882869556,11,2681,13,34.46875
-2,Official,TiRex,0.6672506631965874,11,2672,13,34.46875
-3,Official,TimesFM-2.5,0.6084222193830509,11,2667,13,34.46875
-4,Official,Moirai-2.0,0.5788853136781448,11,1923,13,29.125
-5,Official,TabPFN-TS,0.558456153060992,11,1812,13,31.125
-6,Official,Chronos-Bolt,0.5235332252610707,11,1910,13,29.125
-7,Official,Sundial,0.5128812538914634,11,2161,13,31.125
-8,Official,Seasonal-Naive,0.38680236507990295,11,2512,13,34.46875
-9,Official,Moving-Average,0.38017698152671175,11,2512,13,34.46875
-10,Official,ARIMA,0.3742819212234938,11,2512,13,34.46875
-11,Official,Toto-1.0,0.3741511178964434,11,1937,13,29.125
-12,Official,ETS,0.3660991975151834,11,2512,13,34.46875

results/aggregates/live_rank_7d.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days
-1,Official,Chronos-2,0.6690595882869556,11,2681,13,34.46875
-2,Official,TiRex,0.6672506631965874,11,2672,13,34.46875
-3,Official,TimesFM-2.5,0.6084222193830509,11,2667,13,34.46875
-4,Official,Moirai-2.0,0.5788853136781448,11,1923,13,29.125
-5,Official,TabPFN-TS,0.558456153060992,11,1812,13,31.125
-6,Official,Chronos-Bolt,0.5235332252610707,11,1910,13,29.125
-7,Official,Sundial,0.5128812538914634,11,2161,13,31.125
-8,Official,Seasonal-Naive,0.38680236507990295,11,2512,13,34.46875
-9,Official,Moving-Average,0.38017698152671175,11,2512,13,34.46875
-10,Official,ARIMA,0.3742819212234938,11,2512,13,34.46875
-11,Official,Toto-1.0,0.3741511178964434,11,1937,13,29.125
-12,Official,ETS,0.3660991975151834,11,2512,13,34.46875

results/aggregates/live_rank_up_to_now.csv

@@ -1,13 +0,0 @@
-Rank,Status,model,WinRate,eligible_opponents,shared_releases,shared_datasets,covered_span_days
-1,Official,Chronos-2,0.6690595882869556,11,2681,13,34.46875
-2,Official,TiRex,0.6672506631965874,11,2672,13,34.46875
-3,Official,TimesFM-2.5,0.6084222193830509,11,2667,13,34.46875
-4,Official,Moirai-2.0,0.5788853136781448,11,1923,13,29.125
-5,Official,TabPFN-TS,0.558456153060992,11,1812,13,31.125
-6,Official,Chronos-Bolt,0.5235332252610707,11,1910,13,29.125
-7,Official,Sundial,0.5128812538914634,11,2161,13,31.125
-8,Official,Seasonal-Naive,0.38680236507990295,11,2512,13,34.46875
-9,Official,Moving-Average,0.38017698152671175,11,2512,13,34.46875
-10,Official,ARIMA,0.3742819212234938,11,2512,13,34.46875
-11,Official,Toto-1.0,0.3741511178964434,11,1937,13,29.125
-12,Official,ETS,0.3660991975151834,11,2512,13,34.46875

results/aggregates/live_results_by_dataset.csv

@@ -1,157 +0,0 @@
-model,dataset,domain,frequency,prediction_lengths,MSE,RMSE,MAPE,CRPS,RTG,Stability,Improvement,Improvement_pvalue,n_releases,MAPE_coverage,first_release,last_release
-ARIMA,binance_btcusdt_1h_close/1h/short,Finance,1h,24,2.02822259565676,1.2607522900906072,0.014571734778297322,1.1925931902558862,10.143224515706287,2.1229014708247815,0.03247200689061154,0.4776408470740481,216,1.0,2026-06-29T09:00:00+00:00,2026-07-30T02:00:00+00:00
-ARIMA,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.9083101123257313,1.261258169978178,0.011845155708664644,1.1042089583487873,17.948263157190265,1.7646338660449543,-0.19354838709677422,0.12407814866273859,32,1.0,2026-06-30T08:00:00+00:00,2026-07-26T08:00:00+00:00
-ARIMA,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,6.430981811646138,0.370766603909224,,0.15157022461471686,-31.79656459177291,72.46141093454932,0.06469677557379651,0.14045294103659456,274,0.0,2026-06-29T10:05:00+00:00,2026-07-29T18:15:00+00:00
-ARIMA,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,9.578202015526528e-15,9.78682891212804e-08,,2.5021713821890616e-07,0.0,1.5791580618185917e-30,0.0,1.0,550,0.0,2026-06-25T14:45:00+00:00,2026-07-28T15:40:00+00:00
-ARIMA,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,2.0379265364760504,1.341938783720677,0.0882364325192599,1.0492572016487152,-61.32015971705557,1.2999471724338816,-0.011494252873563218,0.9436180468092228,30,1.0,2026-06-26T23:00:00+00:00,2026-07-26T23:00:00+00:00
-ARIMA,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.2135106327932361,0.9712651511810751,1.3212275657763966,0.7610550085867495,5.3417241438102065,1.1904303507160816,0.07900550267100453,0.02029582628627477,387,0.9974160206718347,2026-06-29T10:00:00+00:00,2026-07-29T18:48:00+00:00
-ARIMA,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.6278568825194553,1.4251075897774492,0.13227878922346972,1.0387696251664715,11.737236632404167,3.378824238756953,-0.12978633877226614,0.000924387813090632,293,1.0,2026-06-28T11:10:00+00:00,2026-07-28T18:10:00+00:00
-ARIMA,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.224989505012516,0.8376872389949994,0.03753078258092905,0.6302451084156856,31.472996936085384,9.894620159763747,0.07644529383659818,0.2804556277713832,92,1.0,2026-07-04T00:00:00+00:00,2026-07-15T23:00:00+00:00
-ARIMA,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.665109551610478,0.9425843342865656,0.45340885250266716,0.7368541719040477,2.6129379148167384,3.801462211022909,-0.30151975683890575,1.129050878760189e-07,141,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-ARIMA,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,1.707595147467111,1.2137946283982373,0.09503290881139861,0.9472151818486351,-43.64651110848551,1.4390179917400023,-0.010472865756902571,0.8554026963994866,138,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-ARIMA,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.08938592017765,1.013669384906228,0.5450516177075309,0.6341238489945653,25.792373622139436,0.536199084992324,0.34012586155229246,1.9071800572108664e-09,142,1.0,2026-06-29T10:00:00+00:00,2026-07-29T04:00:00+00:00
-ARIMA,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,194.09040636812642,3.5149279793999155,0.9192745512816514,3.1479968855665605,5.99861897331838,1743.1378176050575,0.24504974403554527,1.9364816618247272e-07,204,1.0,2026-06-30T05:40:00+00:00,2026-07-29T19:55:00+00:00
-ARIMA,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,1.1257656989002478,1.030157882628527,0.19812277023131533,0.6390464595327553,45.798520099415526,0.6175932364599516,0.3846153846153845,0.07631653936341436,13,1.0,2026-06-28T00:00:00+00:00,2026-07-22T00:00:00+00:00
-Chronos-2,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.6055445263155645,1.0685216089542688,0.010035766414845054,0.7725357896096103,28.64677212786545,1.8942544003343063,0.0748271092669433,0.083652494132501,241,1.0,2026-06-29T09:00:00+00:00,2026-07-30T02:00:00+00:00
-Chronos-2,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.5811863431219901,1.070465590173461,0.008323636090464196,0.7421514556711728,36.369387975458395,2.0049073075588306,-0.056818181818181816,0.6556644947844955,33,1.0,2026-06-30T08:00:00+00:00,2026-07-26T08:00:00+00:00
-Chronos-2,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,18;36,6.199376212562263,0.3189154656903312,,0.1405568707576083,-31.07087368448362,71.13837868797852,0.03825623679811225,0.37245335864247076,285,0.0,2026-06-29T10:05:00+00:00,2026-07-29T18:15:00+00:00
-Chronos-2,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,1.729686274365332e-18,1.3151753777977035e-09,,2.3561627471096824e-09,0.0,1.927621582784852e-34,0.0,1.0,570,0.0,2026-06-25T14:45:00+00:00,2026-07-28T15:40:00+00:00
-Chronos-2,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.295371688844987,0.4728719138176587,0.03169250099185042,0.32183935593940316,8.73042977853834,0.361298836217281,-0.3517241379310345,0.005952597596458611,30,1.0,2026-06-26T23:00:00+00:00,2026-07-26T23:00:00+00:00
-Chronos-2,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.3267718045769036,0.47674721226781136,0.4838424912974793,0.31330482436095664,50.890842667274356,0.4210806576917784,-0.05406555981268625,0.10372205381864447,406,0.9975369458128078,2026-06-29T10:00:00+00:00,2026-07-29T18:48:00+00:00
-Chronos-2,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.78083175102839,1.4836897221770533,0.1467397909358067,1.0114377175893885,7.288724509866297,3.4550091462980164,-0.048859934853420196,0.20091018335726885,308,1.0,2026-06-28T11:10:00+00:00,2026-07-28T18:10:00+00:00
-Chronos-2,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.770662920708487,0.9383375365561323,0.04147426688621382,0.6664343471483456,32.51750738043405,9.969986449028195,0.026208503203261502,0.6962897689185866,102,1.0,2026-07-04T00:00:00+00:00,2026-07-15T23:00:00+00:00
-Chronos-2,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.0150596519024666,0.7557781682829121,0.34095294564200657,0.5123488205397073,22.098651176284342,2.3368501610540005,-0.355188679245283,2.624043129362762e-11,160,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-Chronos-2,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.3940478744472938,0.5771713731490018,0.04256327026164297,0.3974893070276744,14.686422228128519,0.31840009183520673,-0.12572373862696443,0.019844133998979652,156,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-Chronos-2,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.0391402843229742,0.9894170271114018,0.5349815376123469,0.6360602317632279,28.131910063451926,0.5265025443384733,0.36350931677018633,7.691995824424643e-12,161,1.0,2026-06-29T10:00:00+00:00,2026-07-29T04:00:00+00:00
-Chronos-2,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,179.32052435973506,3.018938520197161,0.034355732036435445,2.709422916632916,24.069034652396596,1679.218777344755,0.2332918223329182,2.612791626778769e-07,220,1.0,2026-06-30T05:40:00+00:00,2026-07-29T19:55:00+00:00
-Chronos-2,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.27994700016746327,0.4475570508758146,0.08047915672405251,0.3225868987296447,83.37287201644678,0.3794230793437146,0.6703296703296704,0.00045112620881470087,14,1.0,2026-06-28T00:00:00+00:00,2026-07-22T00:00:00+00:00
-Chronos-Bolt,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.355122965615315,0.9893754829852162,0.00988390797377136,0.721848209508366,22.557693183794793,1.5826891667916059,0.21423639445107023,2.0647156106623688e-05,179,1.0,2026-07-03T07:00:00+00:00,2026-07-30T02:00:00+00:00
-Chronos-Bolt,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.4539380254510008,1.0171651602630492,0.00866256496836003,0.694295550748422,34.41538763559448,1.694495727681373,0.021645021645021644,0.9112884689584274,22,1.0,2026-07-10T05:00:00+00:00,2026-07-26T08:00:00+00:00
-Chronos-Bolt,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,8.826375411993522,0.4479282125373743,,0.1799181940014753,-24.557373638805046,84.83848421033936,0.04157062428158732,0.41770124491616134,200,0.0,2026-07-03T04:20:00+00:00,2026-07-29T18:15:00+00:00
-Chronos-Bolt,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,1.0941039077622845e-12,1.045994219755676e-06,,3.2148618499168906e-06,-100.0,2.021847269745433e-28,0.0,1.0,428,0.0,2026-07-01T21:10:00+00:00,2026-07-28T15:40:00+00:00
-Chronos-Bolt,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.33646790118188474,0.46932795303124963,0.03148247055252711,0.3285493541758667,10.269454068402935,0.5551840161623731,-0.2553846153846154,0.07039249318951525,26,1.0,2026-06-30T23:00:00+00:00,2026-07-26T23:00:00+00:00
-Chronos-Bolt,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.3337502092040887,1.0487941809007166,1.1407968302349951,0.7041582531046675,7.112516468924779,1.0731097727140144,0.006361007847996695,0.8762120172150925,270,0.9962962962962963,2026-07-03T07:42:00+00:00,2026-07-29T18:48:00+00:00
-Chronos-Bolt,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,3.011961547015877,1.562904984130352,0.14097602774054388,1.073538135241004,-1.0208813336356009,3.7398179683984893,-0.07342657342657344,0.1143260371287455,209,1.0,2026-07-02T10:10:00+00:00,2026-07-28T18:10:00+00:00
-Chronos-Bolt,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.768843963278756,0.8902673165851895,0.03498639781627768,0.6413761405723531,39.70093271789535,11.382484507106362,0.07441016333938293,0.40932488546762036,58,1.0,2026-07-07T21:00:00+00:00,2026-07-15T23:00:00+00:00
-Chronos-Bolt,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.5192212900807802,0.6136169988670386,0.3781507253907484,0.41067132524837424,12.693943394160948,0.5811873908132617,-0.47313527180783815,1.0937270052212145e-13,113,1.0,2026-07-03T07:00:00+00:00,2026-07-29T06:00:00+00:00
-Chronos-Bolt,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.39597589650585163,0.5508489228436029,0.04139058885573126,0.404325940830895,23.22709754885763,0.4314227954453064,-0.22779922779922776,0.00037014614571445777,112,1.0,2026-07-03T08:00:00+00:00,2026-07-29T06:00:00+00:00
-Chronos-Bolt,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.2197099579302122,1.0810013805728789,0.5702207587503711,0.6935165434104239,28.17282127268216,0.5161945522851598,0.15572116131035557,0.014040647693432893,114,1.0,2026-07-03T07:00:00+00:00,2026-07-29T04:00:00+00:00
-Chronos-Bolt,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,228.35382816531558,3.553257477348847,0.535576184284403,3.252814576747454,28.072472977870554,1924.153703100461,0.26931678811052595,2.3873558611663343e-07,167,1.0,2026-07-04T03:20:00+00:00,2026-07-29T19:55:00+00:00
-Chronos-Bolt,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.5888227944617089,0.6921086990730174,0.14236933700516546,0.5316201479443244,69.39145215325834,0.6217751936303204,0.5454545454545454,0.013770768197851531,12,1.0,2026-07-01T00:00:00+00:00,2026-07-22T00:00:00+00:00
-ETS,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.9691708971324284,1.1575471479868784,0.01032869270950729,0.9014951212668394,24.880194886412095,2.6280741403124965,0.10396210163652023,0.022998670359794266,216,1.0,2026-06-29T09:00:00+00:00,2026-07-30T02:00:00+00:00
-ETS,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.6772698673479125,1.1374607267848178,0.00888958251994685,0.8481888404956763,28.643717831168455,1.8085885112023488,-0.08064516129032259,0.5301288877477086,32,1.0,2026-06-30T08:00:00+00:00,2026-07-26T08:00:00+00:00
-ETS,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,6.448610013695132,0.3655620746407916,,0.14735320466255647,-31.76389710666277,72.51570891716871,0.08663633723273328,0.04838218992159158,274,0.0,2026-06-29T10:05:00+00:00,2026-07-29T18:15:00+00:00
-ETS,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,9.578202015526528e-15,9.78682891212804e-08,,2.5021713821890616e-07,0.0,1.5791580618185917e-30,0.0,1.0,550,0.0,2026-06-25T14:45:00+00:00,2026-07-28T15:40:00+00:00
-ETS,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,5.632064283514427,2.2241017917224624,0.15885787001642346,1.7941800506233858,-79.9671220048645,3.8344178607315382,0.043678160919540236,0.7502215453736768,30,1.0,2026-06-26T23:00:00+00:00,2026-07-26T23:00:00+00:00
-ETS,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.9105349595384657,1.2282957327708113,1.4858643816039663,0.934047642181641,-11.664144025054568,1.7105004040905394,0.08824356348154394,0.009536233792891072,387,0.9974160206718347,2026-06-29T10:00:00+00:00,2026-07-29T18:48:00+00:00
-ETS,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,5.8314847093947915,1.9009997211706162,0.18412655871109107,1.5184719108617473,-4.838827377004714,11.985049737781578,-0.18490813034737483,2.3645322036176374e-06,293,1.0,2026-06-28T11:10:00+00:00,2026-07-28T18:10:00+00:00
-ETS,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,1.972878454121812,0.853143992192325,0.04758814209444523,0.6729960300640387,6.483095468375056,9.382395081066424,0.14811275680840896,0.03651580906292498,92,1.0,2026-07-04T00:00:00+00:00,2026-07-15T23:00:00+00:00
-ETS,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,3.820774171434048,1.072625636884402,0.5167834642087665,0.8466345131083669,-0.9221819391856056,27.11124123452995,-0.24782168186423503,1.3011201820176544e-05,141,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-ETS,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,17.288229673618275,3.460803312137743,0.2788475265243386,2.8620921815140727,-79.72997348219963,29.353901284692668,-0.06675129588490426,0.24544578545277684,138,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-ETS,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.062923434000745,0.995527250155036,0.5317832419617853,0.6366186442652785,27.8242535150799,0.5942335395698336,0.3864748776346019,8.860468670656982e-12,142,1.0,2026-06-29T10:00:00+00:00,2026-07-29T04:00:00+00:00
-ETS,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,192.79184669046458,3.173811924937021,0.05478162737479353,2.94408565307993,21.4569173815964,1743.5234829989377,0.16864676905244858,0.00034047042434064216,204,1.0,2026-06-30T05:40:00+00:00,2026-07-29T19:55:00+00:00
-ETS,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,1.0833490720100392,0.9952444213048076,0.2129850550946607,0.6701769428306765,48.5062282411613,0.7673220126829784,0.2051282051282051,0.3674042836022003,13,1.0,2026-06-28T00:00:00+00:00,2026-07-22T00:00:00+00:00
-Moirai-2.0,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.3214317074080382,0.9444742060603264,0.008945844717584457,0.6913555595328206,31.764157657944974,1.6383145538047237,0.30254500310366234,1.6402639183159967e-09,180,1.0,2026-07-03T07:00:00+00:00,2026-07-30T02:00:00+00:00
-Moirai-2.0,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.7617173231646346,1.1324285203842483,0.009484338375650726,0.7276927535003623,29.188919734540207,1.7734024748178494,-0.05627705627705628,0.7380940484479567,22,1.0,2026-07-10T05:00:00+00:00,2026-07-26T08:00:00+00:00
-Moirai-2.0,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,8.783192011683383,0.44571420460790684,,0.17734146672732806,-24.55020247971262,84.63450992331303,0.02501136575246573,0.6251649968625166,201,0.0,2026-07-03T04:20:00+00:00,2026-07-29T18:15:00+00:00
-Moirai-2.0,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,1.2167879962794955e-13,3.488248839001449e-07,,4.1005151803435396e-07,0.0,0.0,0.0,1.0,429,0.0,2026-07-01T21:10:00+00:00,2026-07-28T15:40:00+00:00
-Moirai-2.0,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.32783875148011027,0.4861314501111893,0.032171503433641925,0.3331142593364293,2.7413565787529137,0.5308169063111237,-0.28615384615384615,0.04171775347628058,26,1.0,2026-06-30T23:00:00+00:00,2026-07-26T23:00:00+00:00
-Moirai-2.0,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.7109392826076268,0.7091589360164084,0.8808127165131181,0.46979335294352825,38.72315606262861,0.8622416836804444,0.045018450184501846,0.26937195838536865,271,0.996309963099631,2026-07-03T07:42:00+00:00,2026-07-29T18:48:00+00:00
-Moirai-2.0,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.863091468404272,1.5096376464858068,0.13622918673225815,1.0172514731538336,3.358732957085348,3.6646981441787014,-0.02974497856014444,0.5203721458013295,211,1.0,2026-07-02T10:10:00+00:00,2026-07-28T18:10:00+00:00
-Moirai-2.0,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.670225338703816,0.8791254469903079,0.03496247950075732,0.6108317841224591,37.06055843587799,11.37096795671203,0.09175920514319111,0.30456198913461274,59,1.0,2026-07-07T21:00:00+00:00,2026-07-15T23:00:00+00:00
-Moirai-2.0,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.4715153320594922,0.5873144922469989,0.3456406578945194,0.39620317776089164,14.684842484870142,0.5573026837283488,-0.36127930445582984,1.2084311369054593e-08,114,1.0,2026-07-03T07:00:00+00:00,2026-07-29T06:00:00+00:00
-Moirai-2.0,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.45608751447480117,0.5987022784121335,0.045222709870817925,0.44293438780100797,13.674628356253022,0.46521605444133185,-0.177307206068268,0.005368703288571927,113,1.0,2026-07-03T08:00:00+00:00,2026-07-29T06:00:00+00:00
-Moirai-2.0,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.1278691727807912,1.0359833568497623,0.5092334645064265,0.6731034701375159,32.2323099862297,0.5247401631994546,0.20329835082458766,0.001214221215900907,116,1.0,2026-07-03T07:00:00+00:00,2026-07-29T04:00:00+00:00
-Moirai-2.0,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,225.72141377681507,3.5063918505867244,0.5586191315549695,3.1330714586245754,28.215138845040556,1912.6388485923521,0.3088193857424627,2.519101166027516e-09,169,1.0,2026-07-04T03:20:00+00:00,2026-07-29T19:55:00+00:00
-Moirai-2.0,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.32576694973257325,0.4774421673330105,0.08443561400522327,0.33703281202278523,81.50457626947743,0.4588390803064478,0.7575757575757575,0.00024002425044091711,12,1.0,2026-07-01T00:00:00+00:00,2026-07-22T00:00:00+00:00
-Moving-Average,binance_btcusdt_1h_close/1h/short,Finance,1h,24,2.588404821188794,1.354568434366223,0.012697141539093938,1.1313318417427036,13.4942823676864,2.90216611858017,-0.004565030146425495,0.9204803447870819,216,1.0,2026-06-29T09:00:00+00:00,2026-07-30T02:00:00+00:00
-Moving-Average,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,3.269265685407324,1.5349643437810503,0.012371122286664232,1.296030600804856,16.041236998369264,3.389151169692855,-0.07661290322580645,0.5514777322263826,32,1.0,2026-06-30T08:00:00+00:00,2026-07-26T08:00:00+00:00
-Moving-Average,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,6.486869850934467,0.38944453399639717,,0.17021273119641145,-32.576055885899514,72.52407598131104,0.08043613226078328,0.0668483138802308,274,0.0,2026-06-29T10:05:00+00:00,2026-07-29T18:15:00+00:00
-Moving-Average,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,9.578202015526528e-15,9.78682891212804e-08,,2.5021713821890616e-07,0.0,1.5791580618185917e-30,0.0,1.0,550,0.0,2026-06-25T14:45:00+00:00,2026-07-28T15:40:00+00:00
-Moving-Average,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.9224463856199253,0.9010670399481847,0.0645836248358115,0.6869453492193306,-43.08462326691053,0.6586811407632233,-0.04827586206896552,0.7235302654564064,30,1.0,2026-06-26T23:00:00+00:00,2026-07-26T23:00:00+00:00
-Moving-Average,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.4246661740983064,1.037002799245903,2.1205320381876667,0.9065763542590775,5.406634171579568,1.5863252968339965,0.16252292779585223,1.804161960363586e-06,387,0.9974160206718347,2026-06-29T10:00:00+00:00,2026-07-29T18:48:00+00:00
-Moving-Average,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.618646975514632,1.4302841198111884,0.141224289786264,1.133222556737405,11.492529596110773,3.484868083809825,-0.09663845902099212,0.013642638654681776,293,1.0,2026-06-28T11:10:00+00:00,2026-07-28T18:10:00+00:00
-Moving-Average,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.8914444303842557,1.068962110527693,0.06617696620566264,0.8956165091670224,16.219078657811732,9.585776068034434,0.03774486383182035,0.5941010151538975,92,1.0,2026-07-04T00:00:00+00:00,2026-07-15T23:00:00+00:00
-Moving-Average,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.480721728057981,0.9736093363199961,0.4600085522308967,0.7568512947290484,-2.1922693248171874,2.5147415660218684,-0.3588652482269503,2.7279170890889704e-10,141,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-Moving-Average,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.8935463205962211,0.9040529015828146,0.06581214312841947,0.6421640999964857,-28.261544365897937,0.5260873051902926,0.12281815296731197,0.03259360404575268,138,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-Moving-Average,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.0861317863828843,1.008911131051856,0.5705545612336516,0.6470871686372446,26.506225998753617,0.574805903709013,0.3467186095295175,9.244981045509393e-10,142,1.0,2026-06-29T10:00:00+00:00,2026-07-29T04:00:00+00:00
-Moving-Average,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,194.64433352287642,3.5239422867632606,0.07180641008700073,3.2885318023482197,3.861018332094877,1743.9428054201687,0.2910267555297982,6.330451314672276e-10,204,1.0,2026-06-30T05:40:00+00:00,2026-07-29T19:55:00+00:00
-Moving-Average,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,1.0234789580573493,0.981223967552433,0.20267540197053469,0.6344362738751932,49.37921755829025,0.594749234030022,0.4102564102564102,0.05725682817696707,13,1.0,2026-06-28T00:00:00+00:00,2026-07-22T00:00:00+00:00
-Seasonal-Naive,binance_btcusdt_1h_close/1h/short,Finance,1h,24,3.1003155095690036,1.5168685917459,0.013697042456024787,1.0289876490781864,0.0,3.1850467167144214,-0.006890611541774331,0.8802243736907243,216,1.0,2026-06-29T09:00:00+00:00,2026-07-30T02:00:00+00:00
-Seasonal-Naive,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,3.8803486777886427,1.7234750348172114,0.013600798681791645,1.164368059063642,0.0,3.667874600129973,-0.14919354838709678,0.23861491183733988,32,1.0,2026-06-30T08:00:00+00:00,2026-07-26T08:00:00+00:00
-Seasonal-Naive,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,6.811335081565297,0.43849587908926135,,0.1712725693119828,0.0,72.42921511885002,0.1446980539063893,0.002566009667765918,275,0.0,2026-06-29T09:30:00+00:00,2026-07-29T18:15:00+00:00
-Seasonal-Naive,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,0.0,0.0,,0.0,0.0,0.0,0.0,1.0,551,0.0,2026-06-25T14:25:00+00:00,2026-07-28T15:40:00+00:00
-Seasonal-Naive,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.3838835766683514,0.5349065407917174,0.037747810105515,0.3810075120009519,0.0,0.46585943829990095,-0.3701149425287356,0.00369749418816167,30,1.0,2026-06-26T23:00:00+00:00,2026-07-26T23:00:00+00:00
-Seasonal-Naive,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.495276068607949,1.07432376499679,2.1502358843152636,0.9444179065849289,0.0,1.610377470138945,0.18039905165294756,1.1191374486892663e-07,388,0.9974226804123711,2026-06-29T09:30:00+00:00,2026-07-29T18:48:00+00:00
-Seasonal-Naive,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,3.0594168823220187,1.5771760883130423,0.1492407580046367,1.2784702577477862,0.0,3.5772402034239623,-0.09224304056093426,0.018353224893709753,294,1.0,2026-06-28T11:00:00+00:00,2026-07-28T18:10:00+00:00
-Seasonal-Naive,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.907553326809399,1.1113168709918815,0.06395200154691993,0.8936284979553439,0.0,9.58160211148785,0.053763440860215055,0.4452669441695035,93,1.0,2026-07-03T23:00:00+00:00,2026-07-15T23:00:00+00:00
-Seasonal-Naive,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.740886219130264,1.0380822429396779,0.4625913459515543,0.857304676129714,0.0,2.6500469287478814,-0.3862750973928678,9.080792355065225e-12,142,1.0,2026-06-29T09:00:00+00:00,2026-07-29T06:00:00+00:00
-Seasonal-Naive,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.5194390531654802,0.6727912793635036,0.04929150109572573,0.4808134290372592,0.0,0.3809392189483209,-0.13293712855802314,0.0202490445900226,139,1.0,2026-06-29T09:00:00+00:00,2026-07-29T06:00:00+00:00
-Seasonal-Naive,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.913112285942165,1.3314768939317172,0.6514734798572527,1.0461980938090638,0.0,1.0922521561758867,0.5207327883384221,2.768667622410759e-20,143,1.0,2026-06-29T09:00:00+00:00,2026-07-29T04:00:00+00:00
-Seasonal-Naive,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,193.8627444420358,3.592883222146693,0.0856287155254285,3.0456136785391354,0.0,1739.5470216588271,0.29016389119044994,6.902136472110782e-10,205,1.0,2026-06-30T04:40:00+00:00,2026-07-29T19:55:00+00:00
-Seasonal-Naive,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,2.8654131840406496,1.6732133427269074,0.3759880599808413,1.451931952818942,0.0,0.8962259101819249,0.4102564102564102,0.05725682817696707,13,1.0,2026-06-28T00:00:00+00:00,2026-07-22T00:00:00+00:00
-Sundial,binance_btcusdt_1h_close/1h/short,Finance,1h,24,2.313904975839161,1.3621776427279877,0.013947536011837357,1.071876260690525,3.9064310868544183,2.0744315059367833,-0.16782341563317782,0.0006267563530803425,188,1.0,2026-07-01T08:00:00+00:00,2026-07-30T02:00:00+00:00
-Sundial,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,2.195593023269829,1.2510649627495094,0.010353811211048837,0.9577149267740791,30.624585259542382,2.167796226333411,-0.18153846153846157,0.20324965345831253,26,1.0,2026-07-01T13:00:00+00:00,2026-07-26T08:00:00+00:00
-Sundial,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,7.44563563661902,0.4023153498699733,,0.15607592136044882,-31.008922991964166,77.93776874428441,0.036615890724451115,0.4012781553845268,237,0.0,2026-07-01T00:15:00+00:00,2026-07-29T18:15:00+00:00
-Sundial,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,6.616451259440971e-16,2.326008475147592e-08,,2.0230052672786597e-08,0.0,1.386375509942261e-15,0.0,1.0,481,0.0,2026-06-29T22:35:00+00:00,2026-07-28T15:40:00+00:00
-Sundial,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.2989915504083323,0.4810597675775045,0.031935842024323965,0.32229608362516915,5.478488539646862,0.35359595910756725,-0.41798941798941797,0.001494389653163529,28,1.0,2026-06-28T23:00:00+00:00,2026-07-26T23:00:00+00:00
-Sundial,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.39056853891979787,0.5410626441743579,0.819400674653941,0.3572785188468581,53.36337450840049,0.3881711741054812,0.03886314251100898,0.2973948199712074,323,0.9969040247678018,2026-07-01T07:24:00+00:00,2026-07-29T18:48:00+00:00
-Sundial,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,3.19548685710466,1.6500781195800127,0.1649509866713147,1.2268800008203813,-4.85419317378813,3.52800630664717,-0.10166632935303244,0.018022954716784046,244,1.0,2026-06-30T09:40:00+00:00,2026-07-28T18:10:00+00:00
-Sundial,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.881456278598701,1.0224167870279186,0.04675885085597254,0.7204555593446484,14.578590822390296,10.258215961261458,0.11796042617960426,0.13985682980676,73,1.0,2026-07-05T21:00:00+00:00,2026-07-15T23:00:00+00:00
-Sundial,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.0468842107574035,0.7537646795855256,0.3724221072967029,0.5243551612492412,16.411187705870706,2.4426725327631766,-0.3957513768686074,7.1126563668391e-11,124,1.0,2026-07-01T08:00:00+00:00,2026-07-29T06:00:00+00:00
-Sundial,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.4864872368777169,0.638614491621658,0.047742198073724575,0.46862980163770085,7.673307428063925,0.4022284122976959,-0.10330578512396693,0.09291483454565659,121,1.0,2026-07-01T08:00:00+00:00,2026-07-29T06:00:00+00:00
-Sundial,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.2463094799442371,1.0935756315570324,0.5862729199938929,0.7372365873448081,22.64814312332872,0.5150182641385935,0.17815873015873018,0.0030903428510241303,126,1.0,2026-07-01T08:00:00+00:00,2026-07-29T04:00:00+00:00
-Sundial,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,219.52212833343663,3.717284646191996,0.2773850959696539,3.329242382391105,9.600444696638123,1855.4397261230854,0.2999379267535692,2.259306201411122e-09,180,1.0,2026-07-02T03:40:00+00:00,2026-07-29T19:55:00+00:00
-Sundial,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.31166353208424874,0.5111701376597275,0.09318070827996433,0.3397871771134533,81.89086047181716,0.306401845448795,0.6969696969696969,0.0009744810873283095,12,1.0,2026-06-30T00:00:00+00:00,2026-07-22T00:00:00+00:00
-TabPFN-TS,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.288056428948168,0.9650539502864618,0.009405708052795354,0.8277417774560242,24.250171582126555,1.5132279052561872,0.2981197262640356,5.222422594836484e-09,174,1.0,2026-07-01T13:00:00+00:00,2026-07-30T02:00:00+00:00
-TabPFN-TS,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.6897087292640207,1.09329092186638,0.009593598242124572,0.9474734246730254,30.125180199747636,1.9526605060946605,-0.03896103896103896,0.8236433617484156,22,1.0,2026-07-10T05:00:00+00:00,2026-07-26T08:00:00+00:00
-TabPFN-TS,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,9.054946600619552,0.4613115864804278,,0.182834724017508,-24.84934326033105,85.92649130173157,0.04225375766985575,0.41823512484673353,195,0.0,2026-07-01T12:55:00+00:00,2026-07-29T18:15:00+00:00
-TabPFN-TS,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,0.0,0.0,,0.0,0.0,0.0,0.0,1.0,414,0.0,2026-06-30T03:30:00+00:00,2026-07-28T15:40:00+00:00
-TabPFN-TS,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.3499836747388939,0.4967729072984653,0.03265549655192607,0.39498106583018344,3.657192499155621,0.493990451889389,-0.2934472934472935,0.032513093519389046,27,1.0,2026-06-28T23:00:00+00:00,2026-07-26T23:00:00+00:00
-TabPFN-TS,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.9782348153880248,0.8761527007632791,0.9556428937490422,0.713837980502079,22.505255355891645,0.8942909883123211,0.0,1.0,252,0.996031746031746,2026-07-01T12:54:00+00:00,2026-07-29T18:48:00+00:00
-TabPFN-TS,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.89178649768332,1.5102029945429798,0.13527004554698432,1.2764680720002513,3.151821276070372,3.7559270189862373,-0.03707121981233657,0.4379864082099799,198,1.0,2026-06-30T13:20:00+00:00,2026-07-28T18:10:00+00:00
-TabPFN-TS,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,3.0669307026933486,0.9634836711907595,0.03523961683690969,0.736313878115392,32.539994057587926,11.885777737268304,0.1264849755415793,0.1769092815963943,54,1.0,2026-07-06T02:00:00+00:00,2026-07-15T23:00:00+00:00
-TabPFN-TS,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.510925237519673,0.5960871212166821,0.3355496042219181,0.4901428157258468,11.142701120007423,0.7053624588633668,-0.39133681852128455,3.9299760057831175e-09,104,1.0,2026-07-01T13:00:00+00:00,2026-07-29T06:00:00+00:00
-TabPFN-TS,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.436250711548795,0.6041637518295926,0.04554221433804426,0.49641438029013757,7.773809205063626,0.4198360351426503,-0.2510946126023225,0.0001708962196969261,103,1.0,2026-07-01T13:00:00+00:00,2026-07-29T06:00:00+00:00
-TabPFN-TS,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.154471754389707,1.0524631203257253,0.5478623028392814,0.8550100439288849,29.37774851701149,0.49241976404003895,0.10476190476190475,0.1132380824293668,105,1.0,2026-07-01T13:00:00+00:00,2026-07-29T04:00:00+00:00
-TabPFN-TS,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,247.53660545240493,3.8211200270294747,0.02894598485766242,3.613250485564524,21.52515557980803,2002.6180372079293,0.2874968169085816,1.213624345087292e-07,154,1.0,2026-07-02T08:40:00+00:00,2026-07-29T19:55:00+00:00
-TabPFN-TS,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.330527016667658,0.5220646204807641,0.09473347581504885,0.40977797737842825,78.66631528029852,0.3229533174905907,0.7435897435897434,0.00014526497165386054,13,1.0,2026-06-30T00:00:00+00:00,2026-07-22T00:00:00+00:00
-TiRex,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.595166827532652,1.070175914874257,0.009870884457193719,0.7742285993349264,30.234309710458177,1.7811512745358207,0.04804741980474199,0.2676742179484297,240,1.0,2026-06-29T09:00:00+00:00,2026-07-30T02:00:00+00:00
-TiRex,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.8183701071507006,1.1566950827938647,0.009098519179104744,0.7859114801504872,36.06338252137382,2.012663949949189,-0.12096774193548389,0.34153305448057775,32,1.0,2026-06-30T08:00:00+00:00,2026-07-26T08:00:00+00:00
-TiRex,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,18;36,6.21664918520148,0.3153884695136067,,0.14014587341598428,-31.070268224312148,71.26721218054698,-0.00023028225279445822,0.9957258141297903,284,0.0,2026-06-29T10:05:00+00:00,2026-07-29T18:15:00+00:00
-TiRex,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,2.0440368407041847e-18,1.4296981641955703e-09,,1.3977486927145102e-09,0.0,3.855249119424703e-34,0.0,1.0,569,0.0,2026-06-25T14:45:00+00:00,2026-07-28T15:40:00+00:00
-TiRex,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.29587531469370065,0.45830202303845324,0.030294215858784057,0.314433562506276,15.912214496004603,0.39335092685640916,-0.3241379310344828,0.011605514320066219,30,1.0,2026-06-26T23:00:00+00:00,2026-07-26T23:00:00+00:00
-TiRex,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.3906089733185281,0.5211622397971412,0.6221305581827286,0.34835712436166444,46.02616780692926,0.5018211721062746,-0.03479900261509457,0.29498186103749624,406,0.9975369458128078,2026-06-29T10:00:00+00:00,2026-07-29T18:48:00+00:00
-TiRex,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.8856717472206497,1.5061430132566989,0.14993260120512927,1.0285652740893811,5.934850537302864,3.5828698047326872,-0.14300312959059847,0.0001861443546264914,307,1.0,2026-06-28T11:10:00+00:00,2026-07-28T18:10:00+00:00
-TiRex,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.468994721394927,0.8596170375096616,0.037194240537534014,0.6036450284928152,41.50715153356337,9.60643761665164,0.0716831683168317,0.28815304090301486,101,1.0,2026-07-04T00:00:00+00:00,2026-07-15T23:00:00+00:00
-TiRex,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.9433189252558988,0.7261824015943259,0.324130900006619,0.5017579647927536,23.866528455203486,2.1650401778035553,-0.3058131097315166,1.1785461407902463e-08,158,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-TiRex,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.39607419787570164,0.5716568056568146,0.04236269351762131,0.4091659225475469,16.700482692230054,0.36068213839480007,-0.09270725834193327,0.08901434605385444,153,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-TiRex,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.0620022241311462,1.0020402920646108,0.5433951815682505,0.6456280240973072,27.14398877427217,0.5160462434204027,0.36852161452113685,5.41011394258528e-12,159,1.0,2026-06-29T10:00:00+00:00,2026-07-29T04:00:00+00:00
-TiRex,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,181.44437681834188,3.009487211384316,0.29131907572532856,3.082894341816755,27.433761640008488,1714.0266974428744,0.2735117925516317,1.7095106304973464e-09,219,1.0,2026-06-30T05:40:00+00:00,2026-07-29T19:55:00+00:00
-TiRex,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.28449572647514776,0.46295416442262743,0.0840872562984529,0.3356773200795831,82.75970061880996,0.36273456534043697,0.6703296703296704,0.00045112620881470087,14,1.0,2026-06-28T00:00:00+00:00,2026-07-22T00:00:00+00:00
-TimesFM-2.5,binance_btcusdt_1h_close/1h/short,Finance,1h,24,1.6349860582050633,1.0773573894119468,0.010536085071638973,0.8831090433364557,28.18851240945548,1.8924644328652338,0.06191765409092507,0.15404363753003578,239,1.0,2026-06-29T09:00:00+00:00,2026-07-30T02:00:00+00:00
-TimesFM-2.5,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,1.9235807995648218,1.1939238211789782,0.009107697376501547,0.9818204856365835,32.13359881394004,2.2268271082902564,-0.09469696969696971,0.45073160411871227,33,1.0,2026-06-30T08:00:00+00:00,2026-07-26T08:00:00+00:00
-TimesFM-2.5,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,6.216590414739115,0.31622621128322576,,0.12974211886898387,-28.848395066327843,71.26604187930977,0.11293549361919303,0.009377168452175217,284,0.0,2026-06-29T10:05:00+00:00,2026-07-29T18:15:00+00:00
-TimesFM-2.5,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,0.0,0.0,,0.0,0.0,0.0,0.0,1.0,569,0.0,2026-06-25T14:45:00+00:00,2026-07-28T15:40:00+00:00
-TimesFM-2.5,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.31259224147394643,0.4973346576596029,0.03799042775808872,0.35734743509649297,2.559933492785978,0.33467509116808847,-0.3977011494252874,0.0017234661675702629,30,1.0,2026-06-26T23:00:00+00:00,2026-07-26T23:00:00+00:00
-TimesFM-2.5,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,0.17385337041712254,0.35572580171296164,0.2655397483227165,0.2743964367464691,62.95219919643831,0.20386503496328487,-0.015404269955531536,0.6437735169594563,404,0.9975247524752475,2026-06-29T10:00:00+00:00,2026-07-29T18:48:00+00:00
-TimesFM-2.5,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,2.6897039073550544,1.4679509685853767,0.13240551730985642,1.2284802228783873,7.228439936710899,3.2519409070296725,-0.09880564603691641,0.009820190766037526,307,1.0,2026-06-28T11:10:00+00:00,2026-07-28T18:10:00+00:00
-TimesFM-2.5,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,2.473458750158442,0.883920069404717,0.039945153768864705,0.7179661355505145,37.40913646012532,9.426150906207923,0.060606060606060615,0.3716242470071768,100,1.0,2026-07-04T00:00:00+00:00,2026-07-15T23:00:00+00:00
-TimesFM-2.5,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,0.9928392903270465,0.743079876763076,0.31640421749784975,0.5711622674235939,19.455728804183,2.34432412328017,-0.32794381838967823,1.0897006086054243e-09,157,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-TimesFM-2.5,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.4510823735297692,0.608101584765456,0.05402256024731402,0.4650612794140051,11.539697239815482,0.42361056496648186,-0.06381148950808395,0.24177701191344003,153,1.0,2026-06-29T11:00:00+00:00,2026-07-29T06:00:00+00:00
-TimesFM-2.5,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,1.045240052034546,0.9913427141059734,0.47019361734244985,0.7830977233973082,28.487294661641272,0.536313537457822,0.354349754091752,3.897784373471317e-11,158,1.0,2026-06-29T10:00:00+00:00,2026-07-29T04:00:00+00:00
-TimesFM-2.5,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,180.12884814423555,3.0355175566244372,0.09369366371581486,2.8208094580865644,25.2058433477046,1683.0512293238269,0.27217125382262997,2.050856549870416e-09,219,1.0,2026-06-30T05:40:00+00:00,2026-07-29T19:55:00+00:00
-TimesFM-2.5,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,0.2628934288941335,0.4467675878121167,0.07882639118800008,0.348531478510896,84.26849086288598,0.34343778548255705,0.5604395604395604,0.004565983394728434,14,1.0,2026-06-28T00:00:00+00:00,2026-07-22T00:00:00+00:00
-Toto-1.0,binance_btcusdt_1h_close/1h/short,Finance,1h,24,2.2678574829266447,1.294191202553444,0.009766191877901266,0.7487831388748828,0.33819418892673314,2.8512982748886015,0.1885131443142493,0.00015782950697466668,182,1.0,2026-07-03T07:00:00+00:00,2026-07-30T02:00:00+00:00
-Toto-1.0,coingecko_bitcoin_7d_price_usd/1h/short,Finance,1h,24,3.175086269910645,1.521645487561495,0.010709564244259217,0.8709867168219557,0.5322464158750319,3.5235205419444062,-0.012987012987012986,0.9555771436337516,22,1.0,2026-07-10T05:00:00+00:00,2026-07-26T08:00:00+00:00
-Toto-1.0,data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Climate,5min,36,11.309586159013941,1.4735824726232214,,0.1808331860196804,-87.27438173846481,84.9485693492587,0.0029850746268656717,0.9498199909375991,201,0.0,2026-07-03T04:20:00+00:00,2026-07-29T18:15:00+00:00
-Toto-1.0,data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Transportation,5min,12,0.5315809953991664,0.3144713537895293,,0.00027575573133779553,-100.0,3.4031762637140384,0.0008956995629417797,0.977837633211838,431,0.0,2026-07-01T21:10:00+00:00,2026-07-28T15:40:00+00:00
-Toto-1.0,nasa_power_shanghai_hourly_T2M/1h/short,Weather,1h,24,0.6586340425895975,0.6335735514017304,0.03023697154965001,0.3095297258176916,-11.611604151595333,1.3086718510560469,-0.2676923076923077,0.057446554888585626,26,1.0,2026-06-30T23:00:00+00:00,2026-07-26T23:00:00+00:00
-Toto-1.0,noaa_coops_sf_water_level_water_level/6min/short,Ocean,6min,60,1.3112561965760832,0.96372921838034,0.8071101123462269,0.3953518650443914,16.736569923551336,2.461560822879547,0.018853695324283562,0.6424373930669409,273,0.9963369963369964,2026-07-03T07:42:00+00:00,2026-07-29T18:48:00+00:00
-Toto-1.0,noaa_ndbc_46013_realtime_wave_height/10min/short,Ocean,10min,72,55.16745988667621,5.073150153049318,0.12983393143649136,1.0246742254474148,-64.73943690309451,180.09259376606326,-0.09983169456993535,0.030183564220730433,213,1.0,2026-07-02T10:10:00+00:00,2026-07-28T18:10:00+00:00
-Toto-1.0,nws_ksfo_observations_temperature/1h/short,Weather,1h,24,8.45680483631431,1.7566451020306872,0.03543346962187676,0.6053896244254073,-21.810618327960736,31.64405952117616,0.15141242937853108,0.0873982232047124,60,1.0,2026-07-07T21:00:00+00:00,2026-07-15T23:00:00+00:00
-Toto-1.0,open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Air Quality,1h,24,1.8086755463047894,1.1244214289763996,0.38690031407444925,0.4160504766079341,-31.42725574876232,3.090909965391763,-0.4440884820747522,1.974384373799413e-12,115,1.0,2026-07-03T07:00:00+00:00,2026-07-29T06:00:00+00:00
-Toto-1.0,open_meteo_shanghai_hourly_temperature_2m/1h/short,Weather,1h,24,0.4583658746295953,0.5921699440160674,0.03933345122165723,0.37845409305226885,13.66322108581051,0.634815129779458,-0.18678887484197218,0.0033579559666237773,113,1.0,2026-07-03T08:00:00+00:00,2026-07-29T06:00:00+00:00
-Toto-1.0,usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Hazards,1h,24,2.430965679490457,1.4510909721515362,0.5363220023978719,0.719912647612576,3.3949732087353004,2.2694510560088026,0.16615964073591194,0.007634418387809793,118,1.0,2026-07-03T07:00:00+00:00,2026-07-29T04:00:00+00:00
-Toto-1.0,usgs_potomac_iv_usgs_00060/15min/short,Hydrology,15min,24,295.7706502073809,4.424803362209111,0.8969225208422494,3.0526529144466323,0.19768550952934166,2430.7186179803157,0.18348813209494325,0.00036714313495844964,171,1.0,2026-07-04T03:20:00+00:00,2026-07-29T19:55:00+00:00
-Toto-1.0,wikimedia_time_series_hourly_pageviews/1D/short,Web,1D,7,1.493430638855567,1.1822810283926517,0.2168787045319125,0.7022572165896811,34.8197182017094,0.749996768684687,0.1515151515151515,0.5452047007776174,12,1.0,2026-07-01T00:00:00+00:00,2026-07-22T00:00:00+00:00

results/aggregates/metadata.json

@@ -1,16 +0,0 @@
-{
-  "generated_at": "2026-07-30T04:35:50.405687+00:00",
-  "baseline_model": "Seasonal-Naive",
-  "normalization": "Per-config metric / Seasonal-Naive metric",
-  "metric_aggregation": "Geometric mean over dataset configurations",
-  "rank_aggregation": "Positive integer order by mean per-config CRPS rank; falls back to MSE when CRPS is unavailable",
-  "config_key": [
-    "dataset",
-    "term_length",
-    "frequency",
-    "prediction_length"
-  ],
-  "num_configs": 13,
-  "num_models": 12,
-  "num_rows_missing_prediction_length": 0
-}

results/aggregates/results_by_domain.csv

@@ -1,85 +0,0 @@
-domain,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
-Climate,TiRex,0.3650840775416369,4.494631549597824,1,5,5,1.0
-Climate,Chronos-2,0.6005303272522906,3.803669144633632,2,5,5,1.0
-Climate,Seasonal-Naive,1.0,1.0,3,5,5,1.0
-Climate,Toto-1.0,250.48123709396697,39.07319519277663,4,5,5,1.0
-Climate,Chronos-Bolt,0.5971525929874819,8.14664917827943,5,5,5,1.0
-Climate,Sundial,1.160278382303475,7.971052011756972,6,5,5,1.0
-Climate,TimesFM-2.5,0.6925659028674915,0.9761392705573495,7,5,5,1.0
-Climate,Moirai-2.0,0.5817912928502318,11.71860679832664,8,5,5,1.0
-Climate,TabPFN-TS,1.0068764519852622,1.060134200054248,9,5,5,1.0
-Climate,ARIMA,4.715503696525904,25.224389359520575,10,5,5,1.0
-Climate,Moving-Average,4.134367014342511,25.875934697489736,11,5,5,1.0
-Climate,ETS,21.543674640132167,62.452876356248865,12,5,5,1.0
-Finance,Toto-1.0,0.47359649850734575,0.6231359237095236,1,2,2,1.0
-Finance,Chronos-2,0.45868389998246445,0.6317217686870393,2,2,2,1.0
-Finance,Moirai-2.0,0.4798581249676576,0.6605332244056603,3,2,2,1.0
-Finance,TiRex,0.5372417757981601,0.6992691084422749,4,2,2,1.0
-Finance,Chronos-Bolt,0.5518350621361773,0.7027270573740718,5,2,2,1.0
-Finance,Sundial,0.5430797293951739,0.7173067854498968,6,2,2,1.0
-Finance,ETS,0.6210066130524007,0.7929852425870437,7,2,2,1.0
-Finance,TabPFN-TS,0.5508969893448746,0.8267874459652148,8,2,2,1.0
-Finance,TimesFM-2.5,0.6090940677587863,0.7963579678462861,9,2,2,1.0
-Finance,ARIMA,0.7413661652254578,1.2443902340535606,10,2,2,1.0
-Finance,Moving-Average,0.8011696454027099,0.9378527989335791,11,2,2,1.0
-Finance,Seasonal-Naive,1.0,1.0,12,2,2,1.0
-Hazards,Moving-Average,0.35737180512230066,0.48041852665503215,1,1,1,1.0
-Hazards,Sundial,0.38205541355912803,0.49965959709714997,2,1,1,1.0
-Hazards,ARIMA,0.513256217173379,0.5679535645164655,3,1,1,1.0
-Hazards,Chronos-Bolt,0.4210157601116908,0.5748702525097187,4,1,1,1.0
-Hazards,Chronos-2,0.45162715714217433,0.6022361419220289,5,1,1,1.0
-Hazards,TimesFM-2.5,0.45467963247593834,0.608374911851745,6,1,1,1.0
-Hazards,Moirai-2.0,0.5527598317900934,0.6675979279891759,7,1,1,1.0
-Hazards,ETS,0.7274503629390828,0.668790755636714,8,1,1,1.0
-Hazards,TiRex,0.5770288400823175,0.7115324291942324,9,1,1,1.0
-Hazards,TabPFN-TS,0.6991576609415653,0.8458251470212828,10,1,1,1.0
-Hazards,Toto-1.0,4.498480717774431,0.9849038836611602,11,1,1,1.0
-Hazards,Seasonal-Naive,1.0,1.0,12,1,1,1.0
-Hydrology,TiRex,0.2824453503385544,0.39112502049835196,1,1,1,1.0
-Hydrology,Chronos-2,0.20416919351787574,0.39478734274085064,2,1,1,1.0
-Hydrology,ETS,0.2560864091067253,0.4874835460344713,3,1,1,1.0
-Hydrology,Chronos-Bolt,0.4754032778577805,0.5176792502018304,4,1,1,1.0
-Hydrology,ARIMA,0.4667039434859784,0.5267019349418464,5,1,1,1.0
-Hydrology,TimesFM-2.5,0.3047366945562363,0.56656996875841,6,1,1,1.0
-Hydrology,Toto-1.0,0.8634944196033479,0.7413404266390278,7,1,1,1.0
-Hydrology,Moirai-2.0,1.1594996829328539,0.8069085279450355,8,1,1,1.0
-Hydrology,Seasonal-Naive,1.0,1.0,9,1,1,1.0
-Hydrology,Sundial,1.3977594282011032,1.074296938071852,10,1,1,1.0
-Hydrology,TabPFN-TS,1.1276707612981798,1.1435318896536943,11,1,1,1.0
-Hydrology,Moving-Average,1.0229049999998812,1.1718693936132067,12,1,1,1.0
-Ocean,Sundial,0.09810147309542504,0.3139673303974916,1,2,2,1.0
-Ocean,TimesFM-2.5,0.10629290937324604,0.3740637706641928,2,2,2,1.0
-Ocean,Moirai-2.0,0.2507027133379547,0.5155586476034103,3,2,2,1.0
-Ocean,Chronos-2,0.16531491040649635,0.43440109895756907,4,2,2,1.0
-Ocean,TiRex,0.25654550427146766,0.5579102101718059,5,2,2,1.0
-Ocean,Moving-Average,0.8045682066786157,0.8390273234049286,6,2,2,1.0
-Ocean,ARIMA,0.9245768420702,0.893865099153588,7,2,2,1.0
-Ocean,ETS,0.944975253695873,0.9027003780512771,8,2,2,1.0
-Ocean,Toto-1.0,1.1851575627052668,0.5959660750263593,9,2,2,1.0
-Ocean,TabPFN-TS,0.8814726674819053,0.937096534332281,10,2,2,1.0
-Ocean,Chronos-Bolt,0.7529704283424046,0.9320915038846262,11,2,2,1.0
-Ocean,Seasonal-Naive,1.0,1.0,12,2,2,1.0
-Transportation,Seasonal-Naive,1.0,1.0,1,1,1,1.0
-Transportation,TabPFN-TS,1.0,1.0,2,1,1,1.0
-Transportation,TimesFM-2.5,1.0,1.0,3,1,1,1.0
-Transportation,TiRex,1.0,1397.7486927145103,4,1,1,1.0
-Transportation,Chronos-2,1.0,2356.162747109683,5,1,1,1.0
-Transportation,Sundial,1.0,20383.004328005398,6,1,1,1.0
-Transportation,ARIMA,1.0,250217.138218906,7,1,1,1.0
-Transportation,ETS,1.0,250217.138218906,8,1,1,1.0
-Transportation,Moving-Average,1.0,250217.138218906,9,1,1,1.0
-Transportation,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
-Transportation,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
-Transportation,Toto-1.0,3400355409364.4365,280360071.88010037,12,1,1,1.0
-Web,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
-Web,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
-Web,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
-Web,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
-Web,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
-Web,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
-Web,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
-Web,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
-Web,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
-Web,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
-Web,Seasonal-Naive,1.0,1.0,11,1,1,1.0
-Web,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0

results/aggregates/results_by_frequency.csv

@@ -1,85 +0,0 @@
-frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
-10min,ETS,0.37084216483909954,0.5737953847117148,1,1,1,1.0
-10min,ARIMA,0.4099769901781535,0.5995237490382248,2,1,1,1.0
-10min,TimesFM-2.5,0.4291045227516081,0.704607954602834,3,1,1,1.0
-10min,Sundial,0.5847596806384108,0.7067971714254332,4,1,1,1.0
-10min,Moirai-2.0,0.42111651716916393,0.7353270529790262,5,1,1,1.0
-10min,Moving-Average,0.7142776235117748,0.787262305176215,6,1,1,1.0
-10min,TiRex,0.46102069657796657,0.7963848617823616,7,1,1,1.0
-10min,TabPFN-TS,0.5631332342335849,0.8244493268615699,8,1,1,1.0
-10min,Toto-1.0,4.270252629792189,0.9194856152874338,9,1,1,1.0
-10min,Chronos-2,0.50726807105889,0.9493473918865494,10,1,1,1.0
-10min,Chronos-Bolt,0.39987945951262094,0.949539431774318,11,1,1,1.0
-10min,Seasonal-Naive,1.0,1.0,12,1,1,1.0
-15min,TiRex,0.2824453503385544,0.39112502049835196,1,1,1,1.0
-15min,Chronos-2,0.20416919351787574,0.39478734274085064,2,1,1,1.0
-15min,ETS,0.2560864091067253,0.4874835460344713,3,1,1,1.0
-15min,Chronos-Bolt,0.4754032778577805,0.5176792502018304,4,1,1,1.0
-15min,ARIMA,0.4667039434859784,0.5267019349418464,5,1,1,1.0
-15min,TimesFM-2.5,0.3047366945562363,0.56656996875841,6,1,1,1.0
-15min,Toto-1.0,0.8634944196033479,0.7413404266390278,7,1,1,1.0
-15min,Moirai-2.0,1.1594996829328539,0.8069085279450355,8,1,1,1.0
-15min,Seasonal-Naive,1.0,1.0,9,1,1,1.0
-15min,Sundial,1.3977594282011032,1.074296938071852,10,1,1,1.0
-15min,TabPFN-TS,1.1276707612981798,1.1435318896536943,11,1,1,1.0
-15min,Moving-Average,1.0229049999998812,1.1718693936132067,12,1,1,1.0
-1D,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
-1D,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
-1D,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
-1D,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
-1D,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
-1D,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
-1D,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
-1D,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
-1D,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
-1D,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
-1D,Seasonal-Naive,1.0,1.0,11,1,1,1.0
-1D,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
-1h,Chronos-2,0.4700571173602689,0.738760910451211,1,6,6,1.0
-1h,Sundial,0.8266958160973342,0.7589339078501757,2,6,6,1.0
-1h,Toto-1.0,1.2070389322819421,0.7621521414652723,3,6,6,1.0
-1h,TiRex,0.3384428383706496,0.785142800751391,4,6,6,1.0
-1h,Moirai-2.0,0.495940832164787,0.8307452021157272,5,6,6,1.0
-1h,Chronos-Bolt,0.493706094794177,0.7899858262009699,6,6,6,1.0
-1h,TimesFM-2.5,0.5703969736111165,0.8681785098911137,7,6,6,1.0
-1h,Seasonal-Naive,1.0,1.0,8,6,6,1.0
-1h,TabPFN-TS,0.8003854893015097,0.9765717352616982,9,6,6,1.0
-1h,ARIMA,3.096279080186383,1.892166533015781,10,6,6,1.0
-1h,Moving-Average,2.586697565880482,1.6698897443180363,11,6,6,1.0
-1h,ETS,10.943401002277517,3.560998728982149,12,6,6,1.0
-1mo,Moirai-2.0,0.5701893078499076,0.5711658118752873,1,1,1,1.0
-1mo,Chronos-Bolt,0.6722527938921684,0.6335328970612374,2,1,1,1.0
-1mo,Toto-1.0,0.6317640740160342,0.6385745807295035,3,1,1,1.0
-1mo,Chronos-2,0.6879834115815433,0.6437671766189335,4,1,1,1.0
-1mo,TiRex,0.7187693708563099,0.6536268717700132,5,1,1,1.0
-1mo,ARIMA,0.7464480695996939,0.7692893066778397,6,1,1,1.0
-1mo,ETS,0.7580203095992263,0.7703148978390245,7,1,1,1.0
-1mo,Sundial,0.7423182015400501,0.7871685560956725,8,1,1,1.0
-1mo,TimesFM-2.5,0.7803986235065251,0.7985326751147283,9,1,1,1.0
-1mo,Moving-Average,0.9249973049108767,0.8887079460534169,10,1,1,1.0
-1mo,TabPFN-TS,0.8352213750339312,0.8925810519947165,11,1,1,1.0
-1mo,Seasonal-Naive,1.0,1.0,12,1,1,1.0
-5min,Seasonal-Naive,1.0,1.0,1,2,2,1.0
-5min,TabPFN-TS,1.0,1.0,2,2,2,1.0
-5min,TimesFM-2.5,1.0,1.0,3,2,2,1.0
-5min,Chronos-2,1.0,2075.594868502009,4,2,2,1.0
-5min,TiRex,1.0,2413.6848893618544,5,2,2,1.0
-5min,Sundial,1.0,33482.62681398571,6,2,2,1.0
-5min,ARIMA,1.0,252290.1359197037,7,2,2,1.0
-5min,ETS,1.0,252290.1359197037,8,2,2,1.0
-5min,Moving-Average,1.0,252290.1359197037,9,2,2,1.0
-5min,Chronos-Bolt,1.0459942197556757,461166.5554836744,10,2,2,1.0
-5min,Moirai-2.0,1.0,374952.8836038598,11,2,2,1.0
-5min,Toto-1.0,1315831479284.881,279321442.6516978,12,2,2,1.0
-6min,Sundial,0.016457870373322452,0.13946785378063345,1,1,1,1.0
-6min,TimesFM-2.5,0.026329674902003237,0.19858377074721575,2,1,1,1.0
-6min,Chronos-2,0.05387490591643252,0.1987726688757729,3,1,1,1.0
-6min,Moirai-2.0,0.14925049935708146,0.36147278689369644,4,1,1,1.0
-6min,Toto-1.0,0.328926311909055,0.38627636656533804,5,1,1,1.0
-6min,TiRex,0.1427606097739933,0.390845955958178,6,1,1,1.0
-6min,Moving-Average,0.9062722642988865,0.8941960573896243,7,1,1,1.0
-6min,Chronos-Bolt,1.4178384322344766,0.9149641842576952,8,1,1,1.0
-6min,Seasonal-Naive,1.0,1.0,9,1,1,1.0
-6min,TabPFN-TS,1.3797695044142473,1.065135098115034,10,1,1,1.0
-6min,ARIMA,2.0850983283745657,1.332715871167117,11,1,1,1.0
-6min,ETS,2.407973835674871,1.420136854086624,12,1,1,1.0

results/aggregates/results_by_prediction_length.csv

@@ -1,73 +0,0 @@
-prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
-7,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
-7,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
-7,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
-7,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
-7,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
-7,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
-7,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
-7,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
-7,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
-7,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
-7,Seasonal-Naive,1.0,1.0,11,1,1,1.0
-7,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
-12,Chronos-2,0.8294476545156683,38.946376459967496,1,2,2,1.0
-12,TiRex,0.847802672121473,30.22591777828443,2,2,2,1.0
-12,Moirai-2.0,0.7551088053055054,483.94979926515697,3,2,2,1.0
-12,TimesFM-2.5,0.883401733927733,0.8936065549864372,4,2,2,1.0
-12,Chronos-Bolt,0.8576213668056174,1427.1372538860771,5,2,2,1.0
-12,TabPFN-TS,0.9139044671265871,0.9447650776752475,6,2,2,1.0
-12,Sundial,0.8615789003568101,126.66830734547548,7,2,2,1.0
-12,ARIMA,0.8639722620545719,438.7361038019728,8,2,2,1.0
-12,Seasonal-Naive,1.0,1.0,9,2,2,1.0
-12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
-12,Toto-1.0,1465681.5433519448,13380.239734553657,11,2,2,1.0
-12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
-24,Chronos-2,0.41726641458067687,0.6755020428874297,1,7,7,1.0
-24,TiRex,0.32980996363298754,0.710747530536114,2,7,7,1.0
-24,Toto-1.0,1.1506441378565604,0.7591436458872278,3,7,7,1.0
-24,Chronos-Bolt,0.4910488847970414,0.7436980633116519,4,7,7,1.0
-24,Sundial,0.8911063790878467,0.7975611873368402,5,7,7,1.0
-24,Moirai-2.0,0.5599141005770759,0.8272973291632758,6,7,7,1.0
-24,TimesFM-2.5,0.5215356544051807,0.8168262332285622,7,7,7,1.0
-24,Seasonal-Naive,1.0,1.0,8,7,7,1.0
-24,ARIMA,2.362872536227482,1.5762216685237753,9,7,7,1.0
-24,TabPFN-TS,0.8405590388716491,0.9988405588615388,10,7,7,1.0
-24,Moving-Average,2.265619805663808,1.5875051482372313,11,7,7,1.0
-24,ETS,6.400085458836564,2.6803943648684987,12,7,7,1.0
-36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
-36,TabPFN-TS,1.0,1.0,2,1,1,1.0
-36,TimesFM-2.5,1.0,1.0,3,1,1,1.0
-36,Chronos-2,1.0,1828.4365387902994,4,1,1,1.0
-36,TiRex,1.0,4168.041634021886,5,1,1,1.0
-36,Sundial,1.0,55001.033229645705,6,1,1,1.0
-36,Chronos-Bolt,1.0,66153.5710786996,7,1,1,1.0
-36,ARIMA,1.0,254380.30798153122,8,1,1,1.0
-36,ETS,1.0,254380.30798153122,9,1,1,1.0
-36,Moving-Average,1.0,254380.30798153122,10,1,1,1.0
-36,Moirai-2.0,1.0,342858.54030437075,11,1,1,1.0
-36,Toto-1.0,509185738969.7562,278286661.15620023,12,1,1,1.0
-60,Sundial,0.016457870373322452,0.13946785378063345,1,1,1,1.0
-60,TimesFM-2.5,0.026329674902003237,0.19858377074721575,2,1,1,1.0
-60,Chronos-2,0.05387490591643252,0.1987726688757729,3,1,1,1.0
-60,Moirai-2.0,0.14925049935708146,0.36147278689369644,4,1,1,1.0
-60,Toto-1.0,0.328926311909055,0.38627636656533804,5,1,1,1.0
-60,TiRex,0.1427606097739933,0.390845955958178,6,1,1,1.0
-60,Moving-Average,0.9062722642988865,0.8941960573896243,7,1,1,1.0
-60,Chronos-Bolt,1.4178384322344766,0.9149641842576952,8,1,1,1.0
-60,Seasonal-Naive,1.0,1.0,9,1,1,1.0
-60,TabPFN-TS,1.3797695044142473,1.065135098115034,10,1,1,1.0
-60,ARIMA,2.0850983283745657,1.332715871167117,11,1,1,1.0
-60,ETS,2.407973835674871,1.420136854086624,12,1,1,1.0
-72,ETS,0.37084216483909954,0.5737953847117148,1,1,1,1.0
-72,ARIMA,0.4099769901781535,0.5995237490382248,2,1,1,1.0
-72,TimesFM-2.5,0.4291045227516081,0.704607954602834,3,1,1,1.0
-72,Sundial,0.5847596806384108,0.7067971714254332,4,1,1,1.0
-72,Moirai-2.0,0.42111651716916393,0.7353270529790262,5,1,1,1.0
-72,Moving-Average,0.7142776235117748,0.787262305176215,6,1,1,1.0
-72,TiRex,0.46102069657796657,0.7963848617823616,7,1,1,1.0
-72,TabPFN-TS,0.5631332342335849,0.8244493268615699,8,1,1,1.0
-72,Toto-1.0,4.270252629792189,0.9194856152874338,9,1,1,1.0
-72,Chronos-2,0.50726807105889,0.9493473918865494,10,1,1,1.0
-72,Chronos-Bolt,0.39987945951262094,0.949539431774318,11,1,1,1.0
-72,Seasonal-Naive,1.0,1.0,12,1,1,1.0

results/aggregates/results_overall.csv

@@ -1,13 +0,0 @@
-overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
-Overall,Chronos-2,0.43268228989411894,2.1361019300883823,1,13,13,1.0
-Overall,TiRex,0.40995577193139365,2.344352317307399,2,13,13,1.0
-Overall,Sundial,0.5863450480593485,3.439655607773914,3,13,13,1.0
-Overall,Moirai-2.0,0.5286975323240499,5.343807856551616,4,13,13,1.0
-Overall,TimesFM-2.5,0.4487953726978033,0.7310069040248663,5,13,13,1.0
-Overall,Chronos-Bolt,0.5934827454627915,5.853165573506846,6,13,13,1.0
-Overall,Toto-1.0,79.23641351751978,14.911385919485305,7,13,13,1.0
-Overall,ARIMA,1.4160569065190673,7.882303531315528,8,13,13,1.0
-Overall,Seasonal-Naive,1.0,1.0,9,13,13,1.0
-Overall,TabPFN-TS,0.8709943017830731,0.9811288865190397,10,13,13,1.0
-Overall,Moving-Average,1.401098006741648,8.005311788166683,11,13,13,1.0
-Overall,ETS,2.4684777060273344,10.6118711698599,12,13,13,1.0

results/arima/all_results.csv

@@ -1,15 +0,0 @@
-dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates,prediction_length
-binance_btcusdt_1h_close/1h/short,ARIMA,1.0645216857991302,3.043999571436649,nan,nan,0.015691951079973187,nan,nan,1.0317566020138327,nan,nan,1.5735206753310387,Finance,1,24
-coingecko_bitcoin_7d_price_usd/1h/short,ARIMA,0.459657391080611,1.4186819575230558,nan,nan,0.015254467601366208,nan,nan,0.6779803766191254,nan,nan,1.0911009757378656,Finance,1,24
-data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd/1mo/short,ARIMA,27197.688534080287,28885.073828115153,130.26006235500384,1.3733941545973163,0.6111556523811462,1.024494621436719,15.484310582150973,164.91721721542686,1.0152918018145418,0.8019294507021014,0.723321704945088,Finance,1,12
-data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,ARIMA,4.407835548068247e-15,1.12132504091072e-14,nan,nan,nan,nan,nan,6.639153220154094e-08,nan,nan,2.543803079815313e-07,Climate,1,36
-data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,ARIMA,9.578202015526527e-15,9.143141084502762e-15,nan,nan,nan,nan,nan,9.786828912128038e-08,nan,nan,2.502171382189061e-07,Transportation,1,12
-nasa_power_shanghai_hourly_T2M/1h/short,ARIMA,2.056925758158167,2.1513339170576207,nan,nan,0.08313762419760717,nan,nan,1.4341986466867715,nan,nan,1.1091462251330082,Weather,1,24
-noaa_coops_sf_water_level_water_level/6min/short,ARIMA,1.8083467863892388,1.8079982355384892,nan,nan,1.8344389159135426,nan,nan,1.3447478523460221,nan,nan,1.030819601529486,Ocean,1,60
-noaa_ndbc_46013_realtime_wave_height/10min/short,ARIMA,0.31931708197508357,0.32202101361068647,nan,nan,0.06517417837115333,nan,nan,0.5650814825979379,nan,nan,0.3942476088227878,Ocean,1,72
-nws_ksfo_observations_temperature/1h/short,ARIMA,0.33228586127163234,0.22104454915678584,0.36362891565490346,0.26312846157942765,0.022250183536134175,0.02191393413024315,2.960766211760618,0.5764424180016876,0.03447450399419848,0.021747057665548703,0.019463503681897795,Weather,1,24
-open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,ARIMA,0.02045968038051262,0.019237349597677596,nan,nan,0.20808709764662048,nan,nan,0.14303733911294847,nan,nan,0.08921582967146684,Air Quality,1,24
-open_meteo_shanghai_hourly_temperature_2m/1h/short,ARIMA,2.3057718816852564,2.2153411608014966,nan,nan,0.1529423193725712,nan,nan,1.5184768294858029,nan,nan,1.2404385332212717,Weather,1,24
-usgs_earthquake_all_week_hourly_earthquake_count/1h/short,ARIMA,0.7701051557926232,0.8365086925921487,nan,nan,0.340511126277645,nan,nan,0.8775563547673866,nan,nan,0.5710876673827213,Hazards,1,24
-usgs_potomac_iv_usgs_00060/15min/short,ARIMA,1.078693309189009,0.5441305878211891,nan,nan,0.018699027453382828,nan,nan,1.0386016123562534,nan,nan,0.6036229445417213,Hydrology,1,24
-wikimedia_time_series_hourly_pageviews/1D/short,ARIMA,0.41946174479404164,0.3887520067886783,nan,nan,0.12900699451842257,nan,nan,0.6476586637991046,nan,nan,0.4079750467727446,Web,1,7

results/arima/config.json

@@ -1,14 +0,0 @@
-{
-    "model": "ARIMA",
-    "model_type": "statistical",
-    "model_dtype": "float32",
-    "model_link": "https://tsfm.ai/models/baseline/arima",
-    "code_link": "https://github.com/zhouziyu02/TS-Live/blob/main/scripts/run_online_eval.py",
-    "org": "Statistical Baseline",
-    "testdata_leakage": "No",
-    "replication_code_available": "Yes",
-    "api_model_id": "baseline/arima",
-    "admitted_at": "2026-06-01T00:00:00Z",
-    "evaluation_protocol": "issue-now-score-later",
-    "metric_version": "livehouse-canonical-v1"
-}

results/arima/online_meta.json

@@ -1,19 +0,0 @@
-{
-    "model": "ARIMA",
-    "api_model_id": "baseline/arima",
-    "admitted_at": "2026-06-01T00:00:00Z",
-    "evaluation_protocol": "issue-now-score-later",
-    "metric_version": "livehouse-canonical-v1",
-    "evaluated_at": "2026-07-30T04:24:05.136177+00:00",
-    "resolved_tasks": [
-        {
-            "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-            "task_id": "future-15266e5c29a057842130",
-            "issued_at": "2026-07-30T03:08:19.402283+00:00",
-            "resolved_at": "2026-07-30T04:21:30.011653+00:00",
-            "target_end": "2026-07-28T15:40:00+00:00",
-            "prediction_length": 12,
-            "metric_version": "livehouse-canonical-v1"
-        }
-    ]
-}

results/baseline_rank_history.csv

@@ -1,2 +0,0 @@
-date,model,MASE_Rank,CRPS_Rank,MAE_Rank,RMSE_Rank,sMAPE_Rank,MSIS_Rank,ND_Rank,NRMSE_Rank,MAPE_Rank
-2026-06-08,Chronos-Bolt-Mini,3.091,3.545,3.091,3.273,3.091,3.000,3.091,3.273,3.000

results/baseline_rank_history_daily.csv

@@ -1,39 +0,0 @@
-date,model,MSE_Rank,CRPS_Rank,MASE_Rank,MAE_Rank,RMSE_Rank,sMAPE_Rank,MSIS_Rank,ND_Rank,NRMSE_Rank,MAPE_Rank
-2026-06-08,Chronos-Bolt-Mini,,2.636,2.909,2.909,2.636,3.091,2.909,2.909,2.636,3.545
-2026-06-09,Chronos-2,,2.182,2.636,2.636,2.545,2.636,2.000,2.636,2.545,2.364
-2026-06-10,Chronos-2,,3.091,2.818,2.909,2.909,2.818,2.818,2.909,2.909,2.727
-2026-06-11,Chronos-2,,3.091,2.818,2.818,3.000,2.727,2.909,2.818,3.000,2.818
-2026-06-12,Chronos-2,,2.667,2.889,2.889,3.000,2.889,3.000,2.889,3.111,2.889
-2026-06-13,Chronos-2,,2.889,3.778,3.778,3.222,3.778,2.000,3.778,3.222,3.778
-2026-06-14,Chronos-2,,2.700,3.600,3.600,3.000,3.600,1.900,3.600,3.000,3.600
-2026-06-15,Chronos-2,,3.000,3.300,3.300,3.100,3.300,2.600,3.300,3.100,3.400
-2026-06-16,Chronos-2,,3.800,4.400,4.400,4.100,4.400,3.400,4.400,4.100,4.200
-2026-06-17,Chronos-2,,4.900,4.900,4.900,4.900,5.100,4.700,4.900,4.900,5.000
-2026-06-18,Chronos-2,,3.300,3.700,3.700,3.900,3.700,2.900,3.700,3.900,3.700
-2026-06-19,Chronos-2,5.000,4.600,5.200,5.200,5.000,5.200,4.500,5.200,5.000,5.200
-2026-06-20,Chronos-2,5.300,4.900,5.000,5.000,5.300,5.000,4.800,5.000,5.300,5.200
-2026-06-21,Chronos-2,4.600,5.100,4.400,4.400,4.600,5.000,4.100,4.900,4.700,5.000
-2026-06-22,Chronos-2,4.900,4.000,4.000,4.600,4.900,4.600,2.900,4.600,5.000,4.700
-2026-06-23,Chronos-2,4.500,3.400,4.500,4.500,4.500,4.500,3.800,4.500,4.500,5.000
-2026-06-24,Chronos-2,4.385,4.154,4.167,4.231,4.385,3.692,4.083,4.077,4.308,4.000
-2026-06-25,Chronos-2,4.643,4.429,5.231,5.071,4.643,5.000,4.308,4.929,4.714,5.083
-2026-06-26,Chronos-2,4.857,4.429,5.308,5.143,4.857,4.929,4.615,5.000,4.929,5.167
-2026-06-27,Seasonal-Naive,1.532,1.661,1.532,1.523,1.532,1.532,1.642,1.532,1.541,1.505
-2026-06-28,ETS,6.154,6.308,6.455,6.615,6.154,6.692,7.182,6.692,6.231,6.182
-2026-06-29,Seasonal-Naive,7.143,9.750,7.750,6.357,7.143,7.833,9.583,7.500,7.583,8.250
-2026-06-30,Seasonal-Naive,8.357,10.167,9.692,8.571,8.357,10.083,9.846,10.000,9.667,9.583
-2026-07-01,Seasonal-Naive,9.071,10.667,10.250,9.214,9.071,10.500,10.583,10.333,10.000,9.917
-2026-07-02,Seasonal-Naive,11.500,13.167,13.667,11.500,11.500,12.667,12.333,12.833,12.917,12.583
-2026-07-03,Seasonal-Naive,9.929,11.583,11.500,9.714,9.929,10.917,11.333,11.083,11.250,9.917
-2026-07-04,Seasonal-Naive,7.929,9.333,9.500,8.429,7.929,9.667,9.750,9.417,9.000,9.333
-2026-07-05,Seasonal-Naive,9.357,11.500,10.750,9.357,9.357,10.667,11.083,10.583,10.500,10.250
-2026-07-06,Seasonal-Naive,8.857,10.750,10.462,9.643,8.857,10.917,9.769,11.000,10.333,10.750
-2026-07-07,Seasonal-Naive,8.214,9.833,9.462,8.714,8.214,9.750,9.308,10.000,9.583,9.667
-2026-07-08,Seasonal-Naive,9.643,10.000,10.333,9.571,9.643,11.077,9.750,9.769,9.846,10.385
-2026-07-09,Seasonal-Naive,10.214,11.083,11.667,10.143,10.214,11.417,10.667,11.417,11.583,11.333
-2026-07-10,Seasonal-Naive,10.857,12.167,12.250,10.786,10.857,11.833,11.500,12.083,12.333,11.583
-2026-07-11,Seasonal-Naive,10.643,11.231,11.000,10.857,10.643,11.077,11.692,11.231,10.923,10.750
-2026-07-12,Seasonal-Naive,8.714,11.000,9.231,9.000,8.714,10.500,10.846,10.583,10.250,10.250
-2026-07-13,Seasonal-Naive,9.857,12.250,11.833,10.429,9.857,12.583,11.667,12.000,11.417,11.583
-2026-07-14,Seasonal-Naive,10.571,11.417,11.833,10.357,10.571,11.583,11.000,11.583,11.167,11.500
-2026-07-15,Seasonal-Naive,12.643,12.385,13.833,12.429,12.643,13.692,11.750,12.846,13.000,13.231

results/baseline_rank_history_weekly.csv

@@ -1,10 +0,0 @@
-week,model,MSE_Rank,CRPS_Rank,MASE_Rank,MAE_Rank,RMSE_Rank,sMAPE_Rank,MSIS_Rank,ND_Rank,NRMSE_Rank,MAPE_Rank
-2026-W24,Chronos-2,,2.77,3.09,3.105,2.946,3.075,2.438,3.105,2.964,3.029
-2026-W24,Chronos-Bolt-Mini,,2.636,2.909,2.909,2.636,3.091,2.909,2.909,2.636,3.545
-2026-W25,Chronos-2,4.967,4.229,4.414,4.414,4.414,4.529,3.857,4.486,4.429,4.529
-2026-W26,Chronos-2,4.657,4.082,4.641,4.709,4.657,4.544,3.941,4.621,4.69,4.79
-2026-W26,ETS,6.154,6.308,6.455,6.615,6.154,6.692,7.182,6.692,6.231,6.182
-2026-W26,Seasonal-Naive,1.532,1.661,1.532,1.523,1.532,1.532,1.642,1.532,1.541,1.505
-2026-W27,Seasonal-Naive,9.041,10.881,10.444,9.02,9.041,10.333,10.644,10.25,10.131,9.976
-2026-W28,Seasonal-Naive,9.592,10.866,10.629,9.816,9.592,10.939,10.505,10.869,10.693,10.674
-2026-W29,Seasonal-Naive,11.024,12.017,12.5,11.072,11.024,12.619,11.472,12.143,11.861,12.105

results/chronos_2/all_results.csv

@@ -1,3 +0,0 @@
-dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates
-binance_btcusdt_1h_close/1h/short,Chronos-2,253427.98031171164,253427.98031171164,430.1599934895833,0.9318014749305178,0.007149086996462027,0.007183290602900378,3.2641156533937963,503.4163091435474,0.008389478022961463,0.007168654940634957,0.006453564120717358,Finance,1
-coingecko_bitcoin_7d_price_usd/1h/short,Chronos-2,151474.27375920615,151474.27375920615,331.1985677083333,0.6128762551879093,0.00555338622541073,0.005536958612993723,3.7665332417731356,389.19696011043834,0.006507699932794779,0.005537918117874429,0.004363665891866698,Finance,1

results/chronos_2/config.json

@@ -1,11 +0,0 @@
-{
-    "model": "Chronos-2",
-    "model_type": "zero-shot",
-    "model_dtype": "float32",
-    "model_link": "https://tsfm.ai/models/amazon/chronos-2",
-    "code_link": "https://github.com/zhouziyu02/TSFM_Bench/blob/main/scripts/run_online_eval.py",
-    "org": "Amazon / TSFM.ai",
-    "testdata_leakage": "No",
-    "replication_code_available": "Yes",
-    "api_model_id": "amazon/chronos-2"
-}

results/chronos_2/online_meta.json

@@ -1,19 +0,0 @@
-{
-    "model": "Chronos-2",
-    "api_model_id": "amazon/chronos-2",
-    "evaluated_at": "2026-06-30T10:59:48.162083+00:00",
-    "datasets": [
-        {
-            "dataset": "task_binance_btcusdt_1h_crypto_btcusdt_close_20260628t230000z",
-            "data_fetched_at": "2026-06-30T10:58:37.207440Z",
-            "context_length": 48,
-            "prediction_length": 24
-        },
-        {
-            "dataset": "task_coingecko_bitcoin_7d_coin_bitcoin_price_usd_20260629t100204z",
-            "data_fetched_at": "2026-06-30T10:58:37.207440Z",
-            "context_length": 96,
-            "prediction_length": 24
-        }
-    ]
-}

results/chronos_bolt/all_results.csv

@@ -1,15 +0,0 @@
-dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates,prediction_length
-binance_btcusdt_1h_close/1h/short,Chronos-Bolt,0.6548993434907633,0.6548993434907633,nan,nan,0.0062903535990643895,nan,nan,0.8092585146235801,nan,nan,0.6093308144220174,Finance,1,24
-coingecko_bitcoin_7d_price_usd/1h/short,Chronos-Bolt,0.18688054976150958,0.18688054976150958,nan,nan,0.0051711825704424995,nan,nan,0.4322968306170074,nan,nan,0.4058204324653165,Finance,1,24
-data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd/1mo/short,Chronos-Bolt,24494.29886562596,24494.29886562596,120.14190149307251,1.2667135440416435,0.6356253615465683,0.9144911966348365,18.167880022797153,156.5065457596773,0.9635125763281969,0.7396382845884965,0.5956771935646294,Finance,1,12
-data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Chronos-Bolt,3.2825236033380433e-15,3.2825236033380433e-15,nan,nan,nan,nan,nan,5.729331202974779e-08,nan,nan,6.615357107869962e-08,Climate,1,36
-data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Chronos-Bolt,1.0941039077622847e-12,1.0941039077622847e-12,nan,nan,nan,nan,nan,1.0459942197556757e-06,nan,nan,3.2148618499168906e-06,Transportation,1,12
-nasa_power_shanghai_hourly_T2M/1h/short,Chronos-Bolt,0.007747186746338719,0.007747186746338719,nan,nan,0.005542264374300185,nan,nan,0.08801810465091099,nan,nan,0.11419808179354105,Weather,1,24
-noaa_coops_sf_water_level_water_level/6min/short,Chronos-Bolt,1.2296511572905482,1.2296511572905482,nan,nan,2.4009125383799854,nan,nan,1.108896369049222,nan,nan,0.7076999953518223,Ocean,1,60
-noaa_ndbc_46013_realtime_wave_height/10min/short,Chronos-Bolt,0.3114524600462512,0.3114524600462512,nan,nan,0.06313480148614575,nan,nan,0.5580792596453045,nan,nan,0.6244183838597281,Ocean,1,72
-nws_ksfo_observations_temperature/1h/short,Chronos-Bolt,0.3455539255669464,0.3455539255669464,0.35915493965148926,0.2598910116071078,0.022263105377559073,0.021625170449781378,1.7395006304410234,0.5878383498606963,0.035156044918533885,0.021479488696328264,0.02138024583258913,Weather,1,24
-open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Chronos-Bolt,0.00419137205285544,0.00419137205285544,nan,nan,0.08074813595028014,nan,nan,0.0647408067053187,nan,nan,0.06697350033137703,Air Quality,1,24
-open_meteo_shanghai_hourly_temperature_2m/1h/short,Chronos-Bolt,0.09358705000746577,0.09358705000746577,nan,nan,0.02117007539002454,nan,nan,0.3059200058960933,nan,nan,0.19741241176071106,Weather,1,24
-usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Chronos-Bolt,0.6317047834657578,0.6317047834657578,nan,nan,0.319226988224063,nan,nan,0.794798580437684,nan,nan,0.5780425233055712,Hazards,1,24
-usgs_potomac_iv_usgs_00060/15min/short,Chronos-Bolt,1.0988000897556551,1.0988000897556551,nan,nan,0.024528386769324242,nan,nan,1.0482366573229802,nan,nan,0.593282561928467,Hydrology,1,24
-wikimedia_time_series_hourly_pageviews/1D/short,Chronos-Bolt,0.4719500001866968,0.4719500001866968,nan,nan,0.16251649824562261,nan,nan,0.6869861717579887,nan,nan,0.5467640302159011,Web,1,7

results/chronos_bolt/config.json

@@ -1,14 +0,0 @@
-{
-    "model": "Chronos-Bolt",
-    "model_type": "zero-shot",
-    "model_dtype": "float32",
-    "model_link": "https://tsfm.ai/models/amazon/chronos-bolt-base",
-    "code_link": "https://github.com/zhouziyu02/TS-Live/blob/main/scripts/run_online_eval.py",
-    "org": "Amazon / TSFM.ai",
-    "testdata_leakage": "No",
-    "replication_code_available": "Yes",
-    "api_model_id": "amazon/chronos-bolt-base",
-    "admitted_at": "2026-06-01T00:00:00Z",
-    "evaluation_protocol": "issue-now-score-later",
-    "metric_version": "livehouse-canonical-v1"
-}

results/chronos_bolt/online_meta.json

@@ -1,19 +0,0 @@
-{
-    "model": "Chronos-Bolt",
-    "api_model_id": "amazon/chronos-bolt-base",
-    "admitted_at": "2026-06-01T00:00:00Z",
-    "evaluation_protocol": "issue-now-score-later",
-    "metric_version": "livehouse-canonical-v1",
-    "evaluated_at": "2026-07-30T04:24:05.051118+00:00",
-    "resolved_tasks": [
-        {
-            "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-            "task_id": "future-15266e5c29a057842130",
-            "issued_at": "2026-07-30T03:08:19.402283+00:00",
-            "resolved_at": "2026-07-30T04:21:30.140564+00:00",
-            "target_end": "2026-07-28T15:40:00+00:00",
-            "prediction_length": 12,
-            "metric_version": "livehouse-canonical-v1"
-        }
-    ]
-}

results/chronos_bolt_base/all_results.csv

@@ -1,3 +0,0 @@
-dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates
-binance_btcusdt_1h_close/1h/short,Chronos-Bolt-Base,416749.6602268219,416749.6602268219,573.1502278645834,1.2415432298771267,0.009527884090354067,0.009585708560397069,5.7814579156144,645.5615077022653,0.010758340528442616,0.009551600043919455,0.00823864183230734,Finance,1
-coingecko_bitcoin_7d_price_usd/1h/short,Chronos-Bolt-Base,159091.01384035745,159091.01384035745,343.2364908854167,0.6351521887103867,0.005735781999632739,0.005738620143509443,3.1111823915282724,398.8621489190939,0.006669310004319204,0.005739202300125659,0.005590672342540177,Finance,1

results/chronos_bolt_base/config.json

@@ -1,11 +0,0 @@
-{
-    "model": "Chronos-Bolt-Base",
-    "model_type": "zero-shot",
-    "model_dtype": "float32",
-    "model_link": "https://tsfm.ai/models/amazon/chronos-bolt-base",
-    "code_link": "https://github.com/zhouziyu02/TSFM_Bench/blob/main/scripts/run_online_eval.py",
-    "org": "Amazon / TSFM.ai",
-    "testdata_leakage": "No",
-    "replication_code_available": "Yes",
-    "api_model_id": "amazon/chronos-bolt-base"
-}