Update leaderboard results from local eval

results/aggregates/live_metadata.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-07-27T08:35:28.287086+00:00",
+  "generated_at": "2026-07-27T08:46:58.052864+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": "2026-07-27T08:35:25.855631+00:00",
+  "generated_at": "2026-07-27T08:46:55.987573+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": "2026-07-27T08:31:58.057361+00:00",
-    "finished_at": "2026-07-27T08:35:28.298698+00:00",
+    "started_at": "2026-07-27T08:46:50.455516+00:00",
+    "finished_at": "2026-07-27T08:46:58.064750+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": 2,
+    "issued_tasks": 0,
+    "issued_forecasts": 0,
+    "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": "2026-07-27T08:35:23.881247+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.427493+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.919735+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952605+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": "2026-07-27T08:35:23.914599+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.760773+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.260800+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952610+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": "2026-07-27T08:35:23.925707+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.722722+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.215484+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952611+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": "2026-07-27T08:35:23.928521+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.792632+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.292323+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952612+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": "2026-07-27T08:35:23.937982+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.516431+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.031518+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952613+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": "2026-07-27T08:35:23.947904+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.448121+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.952518+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952613+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": "2026-07-27T08:35:23.950264+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.680854+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.177996+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952614+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": "2026-07-27T08:35:23.965396+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.648400+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.147295+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952615+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": "2026-07-27T08:35:23.976393+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.562483+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.074354+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952616+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": "2026-07-27T08:35:23.984524+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.487874+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.003434+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952617+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": "2026-07-27T08:35:23.990338+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.374034+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.891554+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952617+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": "2026-07-27T08:35:24.013992+00:00",
-            "resolved_tasks": [
-                {
-                    "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
-                    "task_id": "future-0fbad1f57007f37b49fb",
-                    "issued_at": "2026-07-27T06:48:00.790180+00:00",
-                    "resolved_at": "2026-07-27T08:32:00.594606+00:00",
-                    "target_end": "2026-07-25T22:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                },
-                {
-                    "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
-                    "task_id": "future-f42f5f3c2ea702bea052",
-                    "issued_at": "2026-07-27T01:48:00.972373+00:00",
-                    "resolved_at": "2026-07-27T08:32:01.108337+00:00",
-                    "target_end": "2026-07-27T04:35:00+00:00",
-                    "prediction_length": 36,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-27T08:46:53.952618+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": "2026-07-27T08:36:08.923571+00:00",
-    "push_detail": "HF Hub API"
+    "push_status": "pending"
 }