Update leaderboard results from local eval

results/aggregates/live_metadata.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-07-27T16:33:34.154943+00:00",
+  "generated_at": "2026-07-27T17:00:22.984706+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",

results/aggregates/metadata.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-07-27T16:33:31.857059+00:00",
+  "generated_at": "2026-07-27T17:00:20.826334+00:00",
   "baseline_model": "Seasonal-Naive",
   "normalization": "Per-config metric / Seasonal-Naive metric",
   "metric_aggregation": "Geometric mean over dataset configurations",

results/online_status.json

@@ -2,14 +2,14 @@
     "status": "ok",
     "evaluation_protocol": "issue-now-score-later",
     "metric_version": "livehouse-canonical-v1",
-    "started_at": "2026-07-27T16:23:29.782220+00:00",
-    "finished_at": "2026-07-27T16:33:34.166142+00:00",
+    "started_at": "2026-07-27T16:59:25.696699+00:00",
+    "finished_at": "2026-07-27T17:00:22.995899+00:00",
     "data_source": "ts_bench",
     "data_config": "configs/datasets/ts_bench.yaml",
-    "task_count": 4,
-    "issued_tasks": 2,
-    "issued_forecasts": 24,
-    "resolved_forecasts": 24,
+    "task_count": 3,
+    "issued_tasks": 0,
+    "issued_forecasts": 1,
+    "resolved_forecasts": 0,
     "pending_tasks": 13,
     "failed_forecasts": [],
     "models": {
@@ -19,27 +19,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.364033+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.039101+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.854971+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986787+00:00",
+            "resolved_tasks": []
         },
         "TiRex": {
             "model": "TiRex",
@@ -47,27 +28,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.401885+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.619505+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.523668+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986813+00:00",
+            "resolved_tasks": []
         },
         "TimesFM-2.5": {
             "model": "TimesFM-2.5",
@@ -75,27 +37,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.405404+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.555476+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.448388+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986817+00:00",
+            "resolved_tasks": []
         },
         "Toto-1.0": {
             "model": "Toto-1.0",
@@ -103,27 +46,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.426556+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.683082+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.568807+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986820+00:00",
+            "resolved_tasks": []
         },
         "Moirai-2.0": {
             "model": "Moirai-2.0",
@@ -131,27 +55,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.445850+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.208172+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.174821+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986824+00:00",
+            "resolved_tasks": []
         },
         "Chronos-Bolt": {
             "model": "Chronos-Bolt",
@@ -159,27 +64,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.452119+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.097090+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.033889+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986827+00:00",
+            "resolved_tasks": []
         },
         "TabPFN-TS": {
             "model": "TabPFN-TS",
@@ -187,27 +73,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.485848+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.487584+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.402893+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986830+00:00",
+            "resolved_tasks": []
         },
         "Sundial": {
             "model": "Sundial",
@@ -215,27 +82,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.510189+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.439569+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.356568+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986838+00:00",
+            "resolved_tasks": []
         },
         "Moving-Average": {
             "model": "Moving-Average",
@@ -243,27 +91,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.525999+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.269170+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.224321+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986841+00:00",
+            "resolved_tasks": []
         },
         "ETS": {
             "model": "ETS",
@@ -271,27 +100,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.537940+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.152505+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.131361+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986844+00:00",
+            "resolved_tasks": []
         },
         "ARIMA": {
             "model": "ARIMA",
@@ -299,27 +109,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.546878+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:30.995638+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.810812+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986847+00:00",
+            "resolved_tasks": []
         },
         "Seasonal-Naive": {
             "model": "Seasonal-Naive",
@@ -327,27 +118,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-27T16:33:29.552147+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "noaa_ndbc_46013_realtime_wave_height/10min/short",
-                    "task_id": "future-c79c95d578faa818605b",
-                    "issued_at": "2026-07-27T03:25:31.051666+00:00",
-                    "resolved_at": "2026-07-27T16:23:31.393180+00:00",
-                    "target_end": "2026-07-26T16:10:00+00:00",
-                    "prediction_length": 72,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-c9c98587a2361b45d83d",
-                    "issued_at": "2026-07-27T15:01:33.945858+00:00",
-                    "resolved_at": "2026-07-27T16:23:32.268397+00:00",
-                    "target_end": "2026-07-26T13:00:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T17:00:18.986851+00:00",
+            "resolved_tasks": []
         }
     },
     "skipped_models": [],
@@ -370,7 +142,5 @@
         "live_overall_30d": "aggregates/live_overall_30d.csv",
         "live_metadata": "aggregates/live_metadata.json"
     },
-    "push_status": "ok",
-    "pushed_at": "2026-07-27T16:34:19.218987+00:00",
-    "push_detail": "HF Hub API"
+    "push_status": "pending"
 }