Spaces:
Sleeping
Sleeping
Update leaderboard results from local eval
Browse files- results/aggregates/live_metadata.json +1 -1
- results/aggregates/metadata.json +2 -2
- results/aggregates/results_by_domain.csv +12 -0
- results/aggregates/results_by_frequency.csv +12 -0
- results/aggregates/results_by_prediction_length.csv +12 -12
- results/aggregates/results_overall.csv +12 -12
- results/dataset_eval_intervals.json +0 -1
- results/dataset_properties.csv +1 -0
- results/online_status.json +16 -18
results/aggregates/live_metadata.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"generated_at": "2026-07-
|
| 3 |
"scope": "Canonical metrics-only release history when available; otherwise legacy release history plus latest allowlisted snapshots",
|
| 4 |
"release_deduplication": "One row per model, dataset, data source timestamp, and prediction length",
|
| 5 |
"dataset_aggregation": "Arithmetic mean over releases, then equal-weight mean over datasets",
|
|
|
|
| 1 |
{
|
| 2 |
+
"generated_at": "2026-07-29T03:00:29.971447+00:00",
|
| 3 |
"scope": "Canonical metrics-only release history when available; otherwise legacy release history plus latest allowlisted snapshots",
|
| 4 |
"release_deduplication": "One row per model, dataset, data source timestamp, and prediction length",
|
| 5 |
"dataset_aggregation": "Arithmetic mean over releases, then equal-weight mean over datasets",
|
results/aggregates/metadata.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"generated_at": "2026-07-
|
| 3 |
"baseline_model": "Seasonal-Naive",
|
| 4 |
"normalization": "Per-config metric / Seasonal-Naive metric",
|
| 5 |
"metric_aggregation": "Geometric mean over dataset configurations",
|
|
@@ -10,7 +10,7 @@
|
|
| 10 |
"frequency",
|
| 11 |
"prediction_length"
|
| 12 |
],
|
| 13 |
-
"num_configs":
|
| 14 |
"num_models": 12,
|
| 15 |
"num_rows_missing_prediction_length": 0
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"generated_at": "2026-07-29T03:00:27.887151+00:00",
|
| 3 |
"baseline_model": "Seasonal-Naive",
|
| 4 |
"normalization": "Per-config metric / Seasonal-Naive metric",
|
| 5 |
"metric_aggregation": "Geometric mean over dataset configurations",
|
|
|
|
| 10 |
"frequency",
|
| 11 |
"prediction_length"
|
| 12 |
],
|
| 13 |
+
"num_configs": 13,
|
| 14 |
"num_models": 12,
|
| 15 |
"num_rows_missing_prediction_length": 0
|
| 16 |
}
|
results/aggregates/results_by_domain.csv
CHANGED
|
@@ -35,6 +35,18 @@ Hazards,Toto-1.0,0.5447067827362504,0.6198857623270299,9,1,1,1.0
|
|
| 35 |
Hazards,TimesFM-2.5,0.5159030493533491,0.6552873663892604,10,1,1,1.0
|
| 36 |
Hazards,TabPFN-TS,0.5234081583087049,0.7154825875538315,11,1,1,1.0
|
| 37 |
Hazards,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
Ocean,ETS,0.09518516095471151,0.2761720625285491,1,2,2,1.0
|
| 39 |
Ocean,TimesFM-2.5,0.07281852879570394,0.2570119454529022,2,2,2,1.0
|
| 40 |
Ocean,Chronos-2,0.05541782384319625,0.2784674272092755,3,2,2,1.0
|
|
|
|
| 35 |
Hazards,TimesFM-2.5,0.5159030493533491,0.6552873663892604,10,1,1,1.0
|
| 36 |
Hazards,TabPFN-TS,0.5234081583087049,0.7154825875538315,11,1,1,1.0
|
| 37 |
Hazards,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
| 38 |
+
Hydrology,Moving-Average,1.0214140625,0.6370328425821091,1,1,1,1.0
|
| 39 |
+
Hydrology,TabPFN-TS,0.999726629540324,0.6371976997142226,2,1,1,1.0
|
| 40 |
+
Hydrology,Chronos-Bolt,0.9985341234579681,0.6392717717863047,3,1,1,1.0
|
| 41 |
+
Hydrology,Chronos-2,1.001236886292696,0.6392940292272022,4,1,1,1.0
|
| 42 |
+
Hydrology,TimesFM-2.5,0.9991976121589539,0.6429353154529154,5,1,1,1.0
|
| 43 |
+
Hydrology,Sundial,1.12480897089839,0.6844293199066155,6,1,1,1.0
|
| 44 |
+
Hydrology,Moirai-2.0,1.0619692907109857,0.7372901890583003,7,1,1,1.0
|
| 45 |
+
Hydrology,TiRex,1.0007208641320466,0.7887214842091093,8,1,1,1.0
|
| 46 |
+
Hydrology,Toto-1.0,1.033309433609247,0.8128151639806623,9,1,1,1.0
|
| 47 |
+
Hydrology,ETS,0.8679554287684873,0.9135102558601378,10,1,1,1.0
|
| 48 |
+
Hydrology,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 49 |
+
Hydrology,ARIMA,2.8471547283782317,3.1754261339537115,12,1,1,1.0
|
| 50 |
Ocean,ETS,0.09518516095471151,0.2761720625285491,1,2,2,1.0
|
| 51 |
Ocean,TimesFM-2.5,0.07281852879570394,0.2570119454529022,2,2,2,1.0
|
| 52 |
Ocean,Chronos-2,0.05541782384319625,0.2784674272092755,3,2,2,1.0
|
results/aggregates/results_by_frequency.csv
CHANGED
|
@@ -11,6 +11,18 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 11 |
10min,Moirai-2.0,0.9931170314987676,0.9506171711084153,10,1,1,1.0
|
| 12 |
10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 13 |
10min,TabPFN-TS,1.0965296750513482,1.1700878991909816,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
1D,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
|
| 15 |
1D,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
|
| 16 |
1D,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
|
|
|
|
| 11 |
10min,Moirai-2.0,0.9931170314987676,0.9506171711084153,10,1,1,1.0
|
| 12 |
10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 13 |
10min,TabPFN-TS,1.0965296750513482,1.1700878991909816,12,1,1,1.0
|
| 14 |
+
15min,Moving-Average,1.0214140625,0.6370328425821091,1,1,1,1.0
|
| 15 |
+
15min,TabPFN-TS,0.999726629540324,0.6371976997142226,2,1,1,1.0
|
| 16 |
+
15min,Chronos-Bolt,0.9985341234579681,0.6392717717863047,3,1,1,1.0
|
| 17 |
+
15min,Chronos-2,1.001236886292696,0.6392940292272022,4,1,1,1.0
|
| 18 |
+
15min,TimesFM-2.5,0.9991976121589539,0.6429353154529154,5,1,1,1.0
|
| 19 |
+
15min,Sundial,1.12480897089839,0.6844293199066155,6,1,1,1.0
|
| 20 |
+
15min,Moirai-2.0,1.0619692907109857,0.7372901890583003,7,1,1,1.0
|
| 21 |
+
15min,TiRex,1.0007208641320466,0.7887214842091093,8,1,1,1.0
|
| 22 |
+
15min,Toto-1.0,1.033309433609247,0.8128151639806623,9,1,1,1.0
|
| 23 |
+
15min,ETS,0.8679554287684873,0.9135102558601378,10,1,1,1.0
|
| 24 |
+
15min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 25 |
+
15min,ARIMA,2.8471547283782317,3.1754261339537115,12,1,1,1.0
|
| 26 |
1D,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
|
| 27 |
1D,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
|
| 28 |
1D,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
|
results/aggregates/results_by_prediction_length.csv
CHANGED
|
@@ -23,18 +23,18 @@ prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 23 |
12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
|
| 24 |
12,Toto-1.0,255690.8555968103,13030.420401776826,11,2,2,1.0
|
| 25 |
12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
|
| 26 |
-
24,
|
| 27 |
-
24,Chronos-
|
| 28 |
-
24,
|
| 29 |
-
24,
|
| 30 |
-
24,
|
| 31 |
-
24,
|
| 32 |
-
24,
|
| 33 |
-
24,TabPFN-TS,0.
|
| 34 |
-
24,
|
| 35 |
-
24,Seasonal-Naive,1.0,1.0,10,
|
| 36 |
-
24,
|
| 37 |
-
24,ETS,
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,Moving-Average,4301413138.721198,1.0,2,1,1,1.0
|
| 40 |
36,ETS,4301412560.972201,123967.05458766423,3,1,1,1.0
|
|
|
|
| 23 |
12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
|
| 24 |
12,Toto-1.0,255690.8555968103,13030.420401776826,11,2,2,1.0
|
| 25 |
12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
|
| 26 |
+
24,Chronos-2,0.33112343830775287,0.6408591087639055,1,7,7,1.0
|
| 27 |
+
24,Chronos-Bolt,0.44303153510032106,0.6530382053012764,2,7,7,1.0
|
| 28 |
+
24,TiRex,0.2907103671635409,0.6572440134253928,3,7,7,1.0
|
| 29 |
+
24,Sundial,0.5403622341038394,0.6078867021056567,4,7,7,1.0
|
| 30 |
+
24,Moirai-2.0,0.3567187274513251,0.6919534774596541,5,7,7,1.0
|
| 31 |
+
24,TimesFM-2.5,0.3059580583366679,0.622723097736219,6,7,7,1.0
|
| 32 |
+
24,Toto-1.0,1.1680858370126643,0.6735050933105378,7,7,7,1.0
|
| 33 |
+
24,TabPFN-TS,0.49750143180707923,0.7055098464842646,8,7,7,1.0
|
| 34 |
+
24,Moving-Average,1.5163338622973692,1.2480242202276746,9,7,7,1.0
|
| 35 |
+
24,Seasonal-Naive,1.0,1.0,10,7,7,1.0
|
| 36 |
+
24,ARIMA,1.6111643626474184,1.5559883799961705,11,7,7,1.0
|
| 37 |
+
24,ETS,4.232993404975467,2.235937000348479,12,7,7,1.0
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,Moving-Average,4301413138.721198,1.0,2,1,1,1.0
|
| 40 |
36,ETS,4301412560.972201,123967.05458766423,3,1,1,1.0
|
results/aggregates/results_overall.csv
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
Overall,TiRex,0.
|
| 3 |
-
Overall,Chronos-2,1.
|
| 4 |
-
Overall,Sundial,2.
|
| 5 |
-
Overall,
|
| 6 |
-
Overall,
|
| 7 |
-
Overall,
|
| 8 |
-
Overall,
|
| 9 |
-
Overall,
|
| 10 |
-
Overall,
|
| 11 |
-
Overall,
|
| 12 |
-
Overall,
|
| 13 |
-
Overall,
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,TiRex,0.8017260142696447,5.60310165565298,1,13,13,1.0
|
| 3 |
+
Overall,Chronos-2,1.0990823535166132,6.922901496899398,2,13,13,1.0
|
| 4 |
+
Overall,Sundial,2.336405644992367,7.308038988236886,3,13,13,1.0
|
| 5 |
+
Overall,TimesFM-2.5,0.7678796232570124,3.0811081667098477,4,13,13,1.0
|
| 6 |
+
Overall,Moirai-2.0,1.1656250122658105,8.650226658565176,5,13,13,1.0
|
| 7 |
+
Overall,Chronos-Bolt,1.6865390808253753,11.552018828811239,6,13,13,1.0
|
| 8 |
+
Overall,Moving-Average,6.300088763429552,2.7326347968300655,7,13,13,1.0
|
| 9 |
+
Overall,Toto-1.0,50.696070929765014,15.5992336705747,8,13,13,1.0
|
| 10 |
+
Overall,ARIMA,5.582983997675871,18.10276290637925,9,13,13,1.0
|
| 11 |
+
Overall,TabPFN-TS,1.9088862726566063,4.025370192511457,10,13,13,1.0
|
| 12 |
+
Overall,ETS,7.646102057230824,7.590098954379924,11,13,13,1.0
|
| 13 |
+
Overall,Seasonal-Naive,1.0,1.0,12,13,13,1.0
|
results/dataset_eval_intervals.json
CHANGED
|
@@ -10,6 +10,5 @@
|
|
| 10 |
"open_meteo_shanghai_air_quality_hourly_pm2_5": 3600,
|
| 11 |
"open_meteo_shanghai_hourly_temperature_2m": 3600,
|
| 12 |
"usgs_earthquake_all_week_hourly_earthquake_count": 3600,
|
| 13 |
-
"usgs_potomac_iv_usgs_00060": 900,
|
| 14 |
"wikimedia_time_series_hourly_pageviews": 86400
|
| 15 |
}
|
|
|
|
| 10 |
"open_meteo_shanghai_air_quality_hourly_pm2_5": 3600,
|
| 11 |
"open_meteo_shanghai_hourly_temperature_2m": 3600,
|
| 12 |
"usgs_earthquake_all_week_hourly_earthquake_count": 3600,
|
|
|
|
| 13 |
"wikimedia_time_series_hourly_pageviews": 86400
|
| 14 |
}
|
results/dataset_properties.csv
CHANGED
|
@@ -10,4 +10,5 @@ nws_ksfo_observations_temperature,Weather,1h,1
|
|
| 10 |
open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
|
| 11 |
open_meteo_shanghai_hourly_temperature_2m,Weather,1h,1
|
| 12 |
usgs_earthquake_all_week_hourly_earthquake_count,Hazards,1h,1
|
|
|
|
| 13 |
wikimedia_time_series_hourly_pageviews,Web,1D,1
|
|
|
|
| 10 |
open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
|
| 11 |
open_meteo_shanghai_hourly_temperature_2m,Weather,1h,1
|
| 12 |
usgs_earthquake_all_week_hourly_earthquake_count,Hazards,1h,1
|
| 13 |
+
usgs_potomac_iv_usgs_00060,Hydrology,15min,1
|
| 14 |
wikimedia_time_series_hourly_pageviews,Web,1D,1
|
results/online_status.json
CHANGED
|
@@ -2,11 +2,11 @@
|
|
| 2 |
"status": "ok",
|
| 3 |
"evaluation_protocol": "issue-now-score-later",
|
| 4 |
"metric_version": "livehouse-canonical-v1",
|
| 5 |
-
"started_at": "2026-07-
|
| 6 |
-
"finished_at": "2026-07-
|
| 7 |
"data_source": "ts_bench",
|
| 8 |
"data_config": "configs/datasets/ts_bench.yaml",
|
| 9 |
-
"task_count":
|
| 10 |
"issued_tasks": 0,
|
| 11 |
"issued_forecasts": 0,
|
| 12 |
"resolved_forecasts": 0,
|
|
@@ -19,7 +19,7 @@
|
|
| 19 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 20 |
"evaluation_protocol": "issue-now-score-later",
|
| 21 |
"metric_version": "livehouse-canonical-v1",
|
| 22 |
-
"evaluated_at": "2026-07-
|
| 23 |
"resolved_tasks": []
|
| 24 |
},
|
| 25 |
"TiRex": {
|
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 29 |
"evaluation_protocol": "issue-now-score-later",
|
| 30 |
"metric_version": "livehouse-canonical-v1",
|
| 31 |
-
"evaluated_at": "2026-07-
|
| 32 |
"resolved_tasks": []
|
| 33 |
},
|
| 34 |
"TimesFM-2.5": {
|
|
@@ -37,7 +37,7 @@
|
|
| 37 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 38 |
"evaluation_protocol": "issue-now-score-later",
|
| 39 |
"metric_version": "livehouse-canonical-v1",
|
| 40 |
-
"evaluated_at": "2026-07-
|
| 41 |
"resolved_tasks": []
|
| 42 |
},
|
| 43 |
"Toto-1.0": {
|
|
@@ -46,7 +46,7 @@
|
|
| 46 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 47 |
"evaluation_protocol": "issue-now-score-later",
|
| 48 |
"metric_version": "livehouse-canonical-v1",
|
| 49 |
-
"evaluated_at": "2026-07-
|
| 50 |
"resolved_tasks": []
|
| 51 |
},
|
| 52 |
"Moirai-2.0": {
|
|
@@ -55,7 +55,7 @@
|
|
| 55 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 56 |
"evaluation_protocol": "issue-now-score-later",
|
| 57 |
"metric_version": "livehouse-canonical-v1",
|
| 58 |
-
"evaluated_at": "2026-07-
|
| 59 |
"resolved_tasks": []
|
| 60 |
},
|
| 61 |
"Chronos-Bolt": {
|
|
@@ -64,7 +64,7 @@
|
|
| 64 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 65 |
"evaluation_protocol": "issue-now-score-later",
|
| 66 |
"metric_version": "livehouse-canonical-v1",
|
| 67 |
-
"evaluated_at": "2026-07-
|
| 68 |
"resolved_tasks": []
|
| 69 |
},
|
| 70 |
"TabPFN-TS": {
|
|
@@ -73,7 +73,7 @@
|
|
| 73 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 74 |
"evaluation_protocol": "issue-now-score-later",
|
| 75 |
"metric_version": "livehouse-canonical-v1",
|
| 76 |
-
"evaluated_at": "2026-07-
|
| 77 |
"resolved_tasks": []
|
| 78 |
},
|
| 79 |
"Sundial": {
|
|
@@ -82,7 +82,7 @@
|
|
| 82 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 83 |
"evaluation_protocol": "issue-now-score-later",
|
| 84 |
"metric_version": "livehouse-canonical-v1",
|
| 85 |
-
"evaluated_at": "2026-07-
|
| 86 |
"resolved_tasks": []
|
| 87 |
},
|
| 88 |
"Moving-Average": {
|
|
@@ -91,7 +91,7 @@
|
|
| 91 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 92 |
"evaluation_protocol": "issue-now-score-later",
|
| 93 |
"metric_version": "livehouse-canonical-v1",
|
| 94 |
-
"evaluated_at": "2026-07-
|
| 95 |
"resolved_tasks": []
|
| 96 |
},
|
| 97 |
"ETS": {
|
|
@@ -100,7 +100,7 @@
|
|
| 100 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 101 |
"evaluation_protocol": "issue-now-score-later",
|
| 102 |
"metric_version": "livehouse-canonical-v1",
|
| 103 |
-
"evaluated_at": "2026-07-
|
| 104 |
"resolved_tasks": []
|
| 105 |
},
|
| 106 |
"ARIMA": {
|
|
@@ -109,7 +109,7 @@
|
|
| 109 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 110 |
"evaluation_protocol": "issue-now-score-later",
|
| 111 |
"metric_version": "livehouse-canonical-v1",
|
| 112 |
-
"evaluated_at": "2026-07-
|
| 113 |
"resolved_tasks": []
|
| 114 |
},
|
| 115 |
"Seasonal-Naive": {
|
|
@@ -118,7 +118,7 @@
|
|
| 118 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 119 |
"evaluation_protocol": "issue-now-score-later",
|
| 120 |
"metric_version": "livehouse-canonical-v1",
|
| 121 |
-
"evaluated_at": "2026-07-
|
| 122 |
"resolved_tasks": []
|
| 123 |
}
|
| 124 |
},
|
|
@@ -142,7 +142,5 @@
|
|
| 142 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 143 |
"live_metadata": "aggregates/live_metadata.json"
|
| 144 |
},
|
| 145 |
-
"push_status": "
|
| 146 |
-
"pushed_at": "2026-07-29T02:49:13.230041+00:00",
|
| 147 |
-
"push_detail": "HF Hub API"
|
| 148 |
}
|
|
|
|
| 2 |
"status": "ok",
|
| 3 |
"evaluation_protocol": "issue-now-score-later",
|
| 4 |
"metric_version": "livehouse-canonical-v1",
|
| 5 |
+
"started_at": "2026-07-29T03:00:19.651567+00:00",
|
| 6 |
+
"finished_at": "2026-07-29T03:00:29.982711+00:00",
|
| 7 |
"data_source": "ts_bench",
|
| 8 |
"data_config": "configs/datasets/ts_bench.yaml",
|
| 9 |
+
"task_count": 2,
|
| 10 |
"issued_tasks": 0,
|
| 11 |
"issued_forecasts": 0,
|
| 12 |
"resolved_forecasts": 0,
|
|
|
|
| 19 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 20 |
"evaluation_protocol": "issue-now-score-later",
|
| 21 |
"metric_version": "livehouse-canonical-v1",
|
| 22 |
+
"evaluated_at": "2026-07-29T03:00:25.488129+00:00",
|
| 23 |
"resolved_tasks": []
|
| 24 |
},
|
| 25 |
"TiRex": {
|
|
|
|
| 28 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 29 |
"evaluation_protocol": "issue-now-score-later",
|
| 30 |
"metric_version": "livehouse-canonical-v1",
|
| 31 |
+
"evaluated_at": "2026-07-29T03:00:25.488152+00:00",
|
| 32 |
"resolved_tasks": []
|
| 33 |
},
|
| 34 |
"TimesFM-2.5": {
|
|
|
|
| 37 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 38 |
"evaluation_protocol": "issue-now-score-later",
|
| 39 |
"metric_version": "livehouse-canonical-v1",
|
| 40 |
+
"evaluated_at": "2026-07-29T03:00:25.488156+00:00",
|
| 41 |
"resolved_tasks": []
|
| 42 |
},
|
| 43 |
"Toto-1.0": {
|
|
|
|
| 46 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 47 |
"evaluation_protocol": "issue-now-score-later",
|
| 48 |
"metric_version": "livehouse-canonical-v1",
|
| 49 |
+
"evaluated_at": "2026-07-29T03:00:25.488158+00:00",
|
| 50 |
"resolved_tasks": []
|
| 51 |
},
|
| 52 |
"Moirai-2.0": {
|
|
|
|
| 55 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 56 |
"evaluation_protocol": "issue-now-score-later",
|
| 57 |
"metric_version": "livehouse-canonical-v1",
|
| 58 |
+
"evaluated_at": "2026-07-29T03:00:25.488161+00:00",
|
| 59 |
"resolved_tasks": []
|
| 60 |
},
|
| 61 |
"Chronos-Bolt": {
|
|
|
|
| 64 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 65 |
"evaluation_protocol": "issue-now-score-later",
|
| 66 |
"metric_version": "livehouse-canonical-v1",
|
| 67 |
+
"evaluated_at": "2026-07-29T03:00:25.488164+00:00",
|
| 68 |
"resolved_tasks": []
|
| 69 |
},
|
| 70 |
"TabPFN-TS": {
|
|
|
|
| 73 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 74 |
"evaluation_protocol": "issue-now-score-later",
|
| 75 |
"metric_version": "livehouse-canonical-v1",
|
| 76 |
+
"evaluated_at": "2026-07-29T03:00:25.488167+00:00",
|
| 77 |
"resolved_tasks": []
|
| 78 |
},
|
| 79 |
"Sundial": {
|
|
|
|
| 82 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 83 |
"evaluation_protocol": "issue-now-score-later",
|
| 84 |
"metric_version": "livehouse-canonical-v1",
|
| 85 |
+
"evaluated_at": "2026-07-29T03:00:25.488170+00:00",
|
| 86 |
"resolved_tasks": []
|
| 87 |
},
|
| 88 |
"Moving-Average": {
|
|
|
|
| 91 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 92 |
"evaluation_protocol": "issue-now-score-later",
|
| 93 |
"metric_version": "livehouse-canonical-v1",
|
| 94 |
+
"evaluated_at": "2026-07-29T03:00:25.488172+00:00",
|
| 95 |
"resolved_tasks": []
|
| 96 |
},
|
| 97 |
"ETS": {
|
|
|
|
| 100 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 101 |
"evaluation_protocol": "issue-now-score-later",
|
| 102 |
"metric_version": "livehouse-canonical-v1",
|
| 103 |
+
"evaluated_at": "2026-07-29T03:00:25.488175+00:00",
|
| 104 |
"resolved_tasks": []
|
| 105 |
},
|
| 106 |
"ARIMA": {
|
|
|
|
| 109 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 110 |
"evaluation_protocol": "issue-now-score-later",
|
| 111 |
"metric_version": "livehouse-canonical-v1",
|
| 112 |
+
"evaluated_at": "2026-07-29T03:00:25.488178+00:00",
|
| 113 |
"resolved_tasks": []
|
| 114 |
},
|
| 115 |
"Seasonal-Naive": {
|
|
|
|
| 118 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 119 |
"evaluation_protocol": "issue-now-score-later",
|
| 120 |
"metric_version": "livehouse-canonical-v1",
|
| 121 |
+
"evaluated_at": "2026-07-29T03:00:25.488182+00:00",
|
| 122 |
"resolved_tasks": []
|
| 123 |
}
|
| 124 |
},
|
|
|
|
| 142 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 143 |
"live_metadata": "aggregates/live_metadata.json"
|
| 144 |
},
|
| 145 |
+
"push_status": "pending"
|
|
|
|
|
|
|
| 146 |
}
|