Update leaderboard results from local eval

results/aggregates/live_metadata.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-07-30T04:24:10.035654+00:00",
+  "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",

results/aggregates/metadata.json

@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-07-30T04:24:07.615908+00:00",
+  "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",

results/online_status.json

@@ -2,14 +2,14 @@
     "status": "ok",
     "evaluation_protocol": "issue-now-score-later",
     "metric_version": "livehouse-canonical-v1",
-    "started_at": "2026-07-30T04:21:25.477386+00:00",
-    "finished_at": "2026-07-30T04:24:10.048725+00:00",
+    "started_at": "2026-07-30T04:35:49.225497+00:00",
+    "finished_at": "2026-07-30T04:35:52.414573+00:00",
     "data_source": "ts_bench",
     "data_config": "configs/datasets/ts_bench.yaml",
-    "task_count": 2,
-    "issued_tasks": 1,
-    "issued_forecasts": 12,
-    "resolved_forecasts": 12,
+    "task_count": 4,
+    "issued_tasks": 0,
+    "issued_forecasts": 0,
+    "resolved_forecasts": 0,
     "pending_tasks": 13,
     "failed_forecasts": [],
     "models": {
@@ -19,18 +19,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:04.960304+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": "2026-07-30T04:21:30.112569+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203710+00:00",
+            "resolved_tasks": []
         },
         "TiRex": {
             "model": "TiRex",
@@ -38,18 +28,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:04.996318+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": "2026-07-30T04:21:30.499531+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203718+00:00",
+            "resolved_tasks": []
         },
         "TimesFM-2.5": {
             "model": "TimesFM-2.5",
@@ -57,18 +37,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:04.999752+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": "2026-07-30T04:21:30.448552+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203719+00:00",
+            "resolved_tasks": []
         },
         "Toto-1.0": {
             "model": "Toto-1.0",
@@ -76,18 +46,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:05.007806+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": "2026-07-30T04:21:30.542676+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203721+00:00",
+            "resolved_tasks": []
         },
         "Moirai-2.0": {
             "model": "Moirai-2.0",
@@ -95,18 +55,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:05.029587+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": "2026-07-30T04:21:30.218542+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203722+00:00",
+            "resolved_tasks": []
         },
         "Chronos-Bolt": {
             "model": "Chronos-Bolt",
@@ -114,18 +64,8 @@
             "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"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203722+00:00",
+            "resolved_tasks": []
         },
         "TabPFN-TS": {
             "model": "TabPFN-TS",
@@ -133,18 +73,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:05.077987+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": "2026-07-30T04:21:30.400544+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203724+00:00",
+            "resolved_tasks": []
         },
         "Sundial": {
             "model": "Sundial",
@@ -152,18 +82,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:05.101349+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": "2026-07-30T04:21:30.344519+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203725+00:00",
+            "resolved_tasks": []
         },
         "Moving-Average": {
             "model": "Moving-Average",
@@ -171,18 +91,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:05.109060+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": "2026-07-30T04:21:30.260703+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203726+00:00",
+            "resolved_tasks": []
         },
         "ETS": {
             "model": "ETS",
@@ -190,18 +100,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:05.122619+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": "2026-07-30T04:21:30.182552+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203727+00:00",
+            "resolved_tasks": []
         },
         "ARIMA": {
             "model": "ARIMA",
@@ -209,18 +109,8 @@
             "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"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203728+00:00",
+            "resolved_tasks": []
         },
         "Seasonal-Naive": {
             "model": "Seasonal-Naive",
@@ -228,18 +118,8 @@
             "admitted_at": "2026-06-01T00:00:00Z",
             "evaluation_protocol": "issue-now-score-later",
             "metric_version": "livehouse-canonical-v1",
-            "evaluated_at": "2026-07-30T04:24:05.139978+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": "2026-07-30T04:21:30.302531+00:00",
-                    "target_end": "2026-07-28T15:40:00+00:00",
-                    "prediction_length": 12,
-                    "metric_version": "livehouse-canonical-v1"
-                }
-            ]
+            "evaluated_at": "2026-07-30T04:35:50.203729+00:00",
+            "resolved_tasks": []
         }
     },
     "skipped_models": [],
@@ -262,7 +142,5 @@
         "live_overall_30d": "aggregates/live_overall_30d.csv",
         "live_metadata": "aggregates/live_metadata.json"
     },
-    "push_status": "ok",
-    "pushed_at": "2026-07-30T04:25:10.889648+00:00",
-    "push_detail": "HF Hub API"
+    "push_status": "pending"
 }