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 +0 -12
- results/aggregates/results_by_frequency.csv +0 -12
- results/aggregates/results_by_prediction_length.csv +0 -12
- results/aggregates/results_overall.csv +12 -12
- results/dataset_eval_intervals.json +1 -0
- results/dataset_properties.csv +0 -1
- results/online_status.json +39 -155
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": "2026-07-28T22:56:37.586274+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": "2026-07-28T22:56:35.560484+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": 12,
|
| 14 |
"num_models": 12,
|
| 15 |
"num_rows_missing_prediction_length": 0
|
| 16 |
}
|
results/aggregates/results_by_domain.csv
CHANGED
|
@@ -71,15 +71,3 @@ Transportation,Moving-Average,1.0,250217.138218906,9,1,1,1.0
|
|
| 71 |
Transportation,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
|
| 72 |
Transportation,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
|
| 73 |
Transportation,Toto-1.0,18677488.633820288,280673160.4289003,12,1,1,1.0
|
| 74 |
-
Web,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
|
| 75 |
-
Web,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
|
| 76 |
-
Web,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
|
| 77 |
-
Web,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
|
| 78 |
-
Web,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
|
| 79 |
-
Web,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
|
| 80 |
-
Web,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
|
| 81 |
-
Web,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
|
| 82 |
-
Web,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
|
| 83 |
-
Web,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
|
| 84 |
-
Web,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 85 |
-
Web,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
|
|
|
|
| 71 |
Transportation,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
|
| 72 |
Transportation,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
|
| 73 |
Transportation,Toto-1.0,18677488.633820288,280673160.4289003,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/aggregates/results_by_frequency.csv
CHANGED
|
@@ -23,18 +23,6 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 23 |
15min,Chronos-2,1.0073362506270407,1.4859340309570945,10,1,1,1.0
|
| 24 |
15min,TiRex,1.0012405403812725,1.4861053101432065,11,1,1,1.0
|
| 25 |
15min,Sundial,1.440734424960613,1.5535414274488537,12,1,1,1.0
|
| 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
|
| 29 |
-
1D,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
|
| 30 |
-
1D,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
|
| 31 |
-
1D,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
|
| 32 |
-
1D,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
|
| 33 |
-
1D,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
|
| 34 |
-
1D,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
|
| 35 |
-
1D,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
|
| 36 |
-
1D,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 37 |
-
1D,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
|
| 38 |
1h,TiRex,0.3508509668853035,0.7055885069620663,1,6,6,1.0
|
| 39 |
1h,Chronos-2,0.37951076735916145,0.6934037615919085,2,6,6,1.0
|
| 40 |
1h,Chronos-Bolt,0.5094193160936651,0.704481403367288,3,6,6,1.0
|
|
|
|
| 23 |
15min,Chronos-2,1.0073362506270407,1.4859340309570945,10,1,1,1.0
|
| 24 |
15min,TiRex,1.0012405403812725,1.4861053101432065,11,1,1,1.0
|
| 25 |
15min,Sundial,1.440734424960613,1.5535414274488537,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
1h,TiRex,0.3508509668853035,0.7055885069620663,1,6,6,1.0
|
| 27 |
1h,Chronos-2,0.37951076735916145,0.6934037615919085,2,6,6,1.0
|
| 28 |
1h,Chronos-Bolt,0.5094193160936651,0.704481403367288,3,6,6,1.0
|
results/aggregates/results_by_prediction_length.csv
CHANGED
|
@@ -1,16 +1,4 @@
|
|
| 1 |
prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
7,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
|
| 3 |
-
7,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
|
| 4 |
-
7,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
|
| 5 |
-
7,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
|
| 6 |
-
7,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
|
| 7 |
-
7,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
|
| 8 |
-
7,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
|
| 9 |
-
7,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
|
| 10 |
-
7,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
|
| 11 |
-
7,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
|
| 12 |
-
7,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 13 |
-
7,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
|
| 14 |
12,Chronos-2,0.8294476545156683,38.946376459967496,1,2,2,1.0
|
| 15 |
12,TiRex,0.847802672121473,30.22591777828443,2,2,2,1.0
|
| 16 |
12,Moirai-2.0,0.7551088053055054,483.94979926515697,3,2,2,1.0
|
|
|
|
| 1 |
prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
12,Chronos-2,0.8294476545156683,38.946376459967496,1,2,2,1.0
|
| 3 |
12,TiRex,0.847802672121473,30.22591777828443,2,2,2,1.0
|
| 4 |
12,Moirai-2.0,0.7551088053055054,483.94979926515697,3,2,2,1.0
|
results/aggregates/results_overall.csv
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
Overall,
|
| 3 |
-
Overall,TiRex,0.
|
| 4 |
-
Overall,
|
| 5 |
-
Overall,
|
| 6 |
-
Overall,
|
| 7 |
-
Overall,
|
| 8 |
-
Overall,
|
| 9 |
-
Overall,
|
| 10 |
-
Overall,
|
| 11 |
-
Overall,
|
| 12 |
-
Overall,Moving-Average,0.
|
| 13 |
-
Overall,Seasonal-Naive,1.0,1.0,12,
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,Toto-1.0,3.959144807171818,2.185096517903194,1,12,12,1.0
|
| 3 |
+
Overall,TiRex,0.1086130417957728,1.0541127797728755,2,12,12,1.0
|
| 4 |
+
Overall,Chronos-2,0.1214688997582712,1.071436536306947,3,12,12,1.0
|
| 5 |
+
Overall,Chronos-Bolt,0.2021881479559937,2.0282759208606773,4,12,12,1.0
|
| 6 |
+
Overall,Moirai-2.0,0.15216359533435747,1.2872760141754034,5,12,12,1.0
|
| 7 |
+
Overall,Sundial,0.36733302503728377,1.2198874052997883,6,12,12,1.0
|
| 8 |
+
Overall,TimesFM-2.5,0.1491124083764099,0.47462341034676336,7,12,12,1.0
|
| 9 |
+
Overall,ARIMA,0.6791059008593225,1.6333728627003652,8,12,12,1.0
|
| 10 |
+
Overall,TabPFN-TS,0.1628968510702974,0.45255265181200255,9,12,12,1.0
|
| 11 |
+
Overall,ETS,0.8258469012616879,0.37098898626911986,10,12,12,1.0
|
| 12 |
+
Overall,Moving-Average,0.9861145211003569,3.19532291572967,11,12,12,1.0
|
| 13 |
+
Overall,Seasonal-Naive,1.0,1.0,12,12,12,1.0
|
results/dataset_eval_intervals.json
CHANGED
|
@@ -5,6 +5,7 @@
|
|
| 5 |
"data_gov_sg_singapore_taxi_availability_available_taxi_count": 300,
|
| 6 |
"nasa_power_shanghai_hourly_T2M": 3600,
|
| 7 |
"noaa_coops_sf_water_level_water_level": 360,
|
|
|
|
| 8 |
"nws_ksfo_observations_temperature": 3600,
|
| 9 |
"open_meteo_shanghai_air_quality_hourly_pm2_5": 3600,
|
| 10 |
"open_meteo_shanghai_hourly_temperature_2m": 3600,
|
|
|
|
| 5 |
"data_gov_sg_singapore_taxi_availability_available_taxi_count": 300,
|
| 6 |
"nasa_power_shanghai_hourly_T2M": 3600,
|
| 7 |
"noaa_coops_sf_water_level_water_level": 360,
|
| 8 |
+
"noaa_ndbc_46013_realtime_wave_height": 600,
|
| 9 |
"nws_ksfo_observations_temperature": 3600,
|
| 10 |
"open_meteo_shanghai_air_quality_hourly_pm2_5": 3600,
|
| 11 |
"open_meteo_shanghai_hourly_temperature_2m": 3600,
|
results/dataset_properties.csv
CHANGED
|
@@ -11,4 +11,3 @@ 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
|
|
|
|
| 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
|
|
|
results/online_status.json
CHANGED
|
@@ -1,17 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"status": "
|
| 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":
|
| 11 |
-
"issued_forecasts":
|
| 12 |
-
"resolved_forecasts":
|
| 13 |
"pending_tasks": 13,
|
| 14 |
-
"failed_forecasts": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"models": {
|
| 16 |
"Chronos-2": {
|
| 17 |
"model": "Chronos-2",
|
|
@@ -19,18 +25,8 @@
|
|
| 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 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 26 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 27 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 28 |
-
"resolved_at": "2026-07-28T19:38:04.276069+00:00",
|
| 29 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 30 |
-
"prediction_length": 12,
|
| 31 |
-
"metric_version": "livehouse-canonical-v1"
|
| 32 |
-
}
|
| 33 |
-
]
|
| 34 |
},
|
| 35 |
"TiRex": {
|
| 36 |
"model": "TiRex",
|
|
@@ -38,18 +34,8 @@
|
|
| 38 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 39 |
"evaluation_protocol": "issue-now-score-later",
|
| 40 |
"metric_version": "livehouse-canonical-v1",
|
| 41 |
-
"evaluated_at": "2026-07-
|
| 42 |
-
"resolved_tasks": [
|
| 43 |
-
{
|
| 44 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 45 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 46 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 47 |
-
"resolved_at": "2026-07-28T19:38:04.719991+00:00",
|
| 48 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 49 |
-
"prediction_length": 12,
|
| 50 |
-
"metric_version": "livehouse-canonical-v1"
|
| 51 |
-
}
|
| 52 |
-
]
|
| 53 |
},
|
| 54 |
"TimesFM-2.5": {
|
| 55 |
"model": "TimesFM-2.5",
|
|
@@ -57,18 +43,8 @@
|
|
| 57 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 58 |
"evaluation_protocol": "issue-now-score-later",
|
| 59 |
"metric_version": "livehouse-canonical-v1",
|
| 60 |
-
"evaluated_at": "2026-07-
|
| 61 |
-
"resolved_tasks": [
|
| 62 |
-
{
|
| 63 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 64 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 65 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 66 |
-
"resolved_at": "2026-07-28T19:38:04.666035+00:00",
|
| 67 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 68 |
-
"prediction_length": 12,
|
| 69 |
-
"metric_version": "livehouse-canonical-v1"
|
| 70 |
-
}
|
| 71 |
-
]
|
| 72 |
},
|
| 73 |
"Toto-1.0": {
|
| 74 |
"model": "Toto-1.0",
|
|
@@ -76,18 +52,8 @@
|
|
| 76 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 77 |
"evaluation_protocol": "issue-now-score-later",
|
| 78 |
"metric_version": "livehouse-canonical-v1",
|
| 79 |
-
"evaluated_at": "2026-07-
|
| 80 |
-
"resolved_tasks": [
|
| 81 |
-
{
|
| 82 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 83 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 84 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 85 |
-
"resolved_at": "2026-07-28T19:38:04.763051+00:00",
|
| 86 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 87 |
-
"prediction_length": 12,
|
| 88 |
-
"metric_version": "livehouse-canonical-v1"
|
| 89 |
-
}
|
| 90 |
-
]
|
| 91 |
},
|
| 92 |
"Moirai-2.0": {
|
| 93 |
"model": "Moirai-2.0",
|
|
@@ -95,18 +61,8 @@
|
|
| 95 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 96 |
"evaluation_protocol": "issue-now-score-later",
|
| 97 |
"metric_version": "livehouse-canonical-v1",
|
| 98 |
-
"evaluated_at": "2026-07-
|
| 99 |
-
"resolved_tasks": [
|
| 100 |
-
{
|
| 101 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 102 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 103 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 104 |
-
"resolved_at": "2026-07-28T19:38:04.382007+00:00",
|
| 105 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 106 |
-
"prediction_length": 12,
|
| 107 |
-
"metric_version": "livehouse-canonical-v1"
|
| 108 |
-
}
|
| 109 |
-
]
|
| 110 |
},
|
| 111 |
"Chronos-Bolt": {
|
| 112 |
"model": "Chronos-Bolt",
|
|
@@ -114,18 +70,8 @@
|
|
| 114 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 115 |
"evaluation_protocol": "issue-now-score-later",
|
| 116 |
"metric_version": "livehouse-canonical-v1",
|
| 117 |
-
"evaluated_at": "2026-07-
|
| 118 |
-
"resolved_tasks": [
|
| 119 |
-
{
|
| 120 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 121 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 122 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 123 |
-
"resolved_at": "2026-07-28T19:38:04.308155+00:00",
|
| 124 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 125 |
-
"prediction_length": 12,
|
| 126 |
-
"metric_version": "livehouse-canonical-v1"
|
| 127 |
-
}
|
| 128 |
-
]
|
| 129 |
},
|
| 130 |
"TabPFN-TS": {
|
| 131 |
"model": "TabPFN-TS",
|
|
@@ -133,18 +79,8 @@
|
|
| 133 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 134 |
"evaluation_protocol": "issue-now-score-later",
|
| 135 |
"metric_version": "livehouse-canonical-v1",
|
| 136 |
-
"evaluated_at": "2026-07-
|
| 137 |
-
"resolved_tasks": [
|
| 138 |
-
{
|
| 139 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 140 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 141 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 142 |
-
"resolved_at": "2026-07-28T19:38:04.602994+00:00",
|
| 143 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 144 |
-
"prediction_length": 12,
|
| 145 |
-
"metric_version": "livehouse-canonical-v1"
|
| 146 |
-
}
|
| 147 |
-
]
|
| 148 |
},
|
| 149 |
"Sundial": {
|
| 150 |
"model": "Sundial",
|
|
@@ -152,18 +88,8 @@
|
|
| 152 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 153 |
"evaluation_protocol": "issue-now-score-later",
|
| 154 |
"metric_version": "livehouse-canonical-v1",
|
| 155 |
-
"evaluated_at": "2026-07-
|
| 156 |
-
"resolved_tasks": [
|
| 157 |
-
{
|
| 158 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 159 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 160 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 161 |
-
"resolved_at": "2026-07-28T19:38:04.532044+00:00",
|
| 162 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 163 |
-
"prediction_length": 12,
|
| 164 |
-
"metric_version": "livehouse-canonical-v1"
|
| 165 |
-
}
|
| 166 |
-
]
|
| 167 |
},
|
| 168 |
"Moving-Average": {
|
| 169 |
"model": "Moving-Average",
|
|
@@ -171,18 +97,8 @@
|
|
| 171 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 172 |
"evaluation_protocol": "issue-now-score-later",
|
| 173 |
"metric_version": "livehouse-canonical-v1",
|
| 174 |
-
"evaluated_at": "2026-07-
|
| 175 |
-
"resolved_tasks": [
|
| 176 |
-
{
|
| 177 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 178 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 179 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 180 |
-
"resolved_at": "2026-07-28T19:38:04.431187+00:00",
|
| 181 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 182 |
-
"prediction_length": 12,
|
| 183 |
-
"metric_version": "livehouse-canonical-v1"
|
| 184 |
-
}
|
| 185 |
-
]
|
| 186 |
},
|
| 187 |
"ETS": {
|
| 188 |
"model": "ETS",
|
|
@@ -190,18 +106,8 @@
|
|
| 190 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 191 |
"evaluation_protocol": "issue-now-score-later",
|
| 192 |
"metric_version": "livehouse-canonical-v1",
|
| 193 |
-
"evaluated_at": "2026-07-
|
| 194 |
-
"resolved_tasks": [
|
| 195 |
-
{
|
| 196 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 197 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 198 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 199 |
-
"resolved_at": "2026-07-28T19:38:04.346964+00:00",
|
| 200 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 201 |
-
"prediction_length": 12,
|
| 202 |
-
"metric_version": "livehouse-canonical-v1"
|
| 203 |
-
}
|
| 204 |
-
]
|
| 205 |
},
|
| 206 |
"ARIMA": {
|
| 207 |
"model": "ARIMA",
|
|
@@ -209,18 +115,8 @@
|
|
| 209 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 210 |
"evaluation_protocol": "issue-now-score-later",
|
| 211 |
"metric_version": "livehouse-canonical-v1",
|
| 212 |
-
"evaluated_at": "2026-07-
|
| 213 |
-
"resolved_tasks": [
|
| 214 |
-
{
|
| 215 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 216 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 217 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 218 |
-
"resolved_at": "2026-07-28T19:38:04.168245+00:00",
|
| 219 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 220 |
-
"prediction_length": 12,
|
| 221 |
-
"metric_version": "livehouse-canonical-v1"
|
| 222 |
-
}
|
| 223 |
-
]
|
| 224 |
},
|
| 225 |
"Seasonal-Naive": {
|
| 226 |
"model": "Seasonal-Naive",
|
|
@@ -228,18 +124,8 @@
|
|
| 228 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 229 |
"evaluation_protocol": "issue-now-score-later",
|
| 230 |
"metric_version": "livehouse-canonical-v1",
|
| 231 |
-
"evaluated_at": "2026-07-
|
| 232 |
-
"resolved_tasks": [
|
| 233 |
-
{
|
| 234 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 235 |
-
"task_id": "future-48cd6c99a9ffcddbf31a",
|
| 236 |
-
"issued_at": "2026-07-28T17:42:40.359220+00:00",
|
| 237 |
-
"resolved_at": "2026-07-28T19:38:04.480914+00:00",
|
| 238 |
-
"target_end": "2026-07-27T15:50:00+00:00",
|
| 239 |
-
"prediction_length": 12,
|
| 240 |
-
"metric_version": "livehouse-canonical-v1"
|
| 241 |
-
}
|
| 242 |
-
]
|
| 243 |
}
|
| 244 |
},
|
| 245 |
"skipped_models": [],
|
|
@@ -262,7 +148,5 @@
|
|
| 262 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 263 |
"live_metadata": "aggregates/live_metadata.json"
|
| 264 |
},
|
| 265 |
-
"push_status": "
|
| 266 |
-
"pushed_at": "2026-07-28T20:56:18.861848+00:00",
|
| 267 |
-
"push_detail": "HF Hub API"
|
| 268 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"status": "partial",
|
| 3 |
"evaluation_protocol": "issue-now-score-later",
|
| 4 |
"metric_version": "livehouse-canonical-v1",
|
| 5 |
+
"started_at": "2026-07-28T22:56:28.040831+00:00",
|
| 6 |
+
"finished_at": "2026-07-28T22:56:37.597741+00:00",
|
| 7 |
"data_source": "ts_bench",
|
| 8 |
"data_config": "configs/datasets/ts_bench.yaml",
|
| 9 |
+
"task_count": 4,
|
| 10 |
+
"issued_tasks": 0,
|
| 11 |
+
"issued_forecasts": 0,
|
| 12 |
+
"resolved_forecasts": 0,
|
| 13 |
"pending_tasks": 13,
|
| 14 |
+
"failed_forecasts": [
|
| 15 |
+
{
|
| 16 |
+
"model": "Seasonal-Naive",
|
| 17 |
+
"dataset": "nws_ksfo_observations_temperature/1h/short",
|
| 18 |
+
"error": "Mean forecast length 10 < 24"
|
| 19 |
+
}
|
| 20 |
+
],
|
| 21 |
"models": {
|
| 22 |
"Chronos-2": {
|
| 23 |
"model": "Chronos-2",
|
|
|
|
| 25 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 26 |
"evaluation_protocol": "issue-now-score-later",
|
| 27 |
"metric_version": "livehouse-canonical-v1",
|
| 28 |
+
"evaluated_at": "2026-07-28T22:56:33.262512+00:00",
|
| 29 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
},
|
| 31 |
"TiRex": {
|
| 32 |
"model": "TiRex",
|
|
|
|
| 34 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 35 |
"evaluation_protocol": "issue-now-score-later",
|
| 36 |
"metric_version": "livehouse-canonical-v1",
|
| 37 |
+
"evaluated_at": "2026-07-28T22:56:33.262520+00:00",
|
| 38 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
},
|
| 40 |
"TimesFM-2.5": {
|
| 41 |
"model": "TimesFM-2.5",
|
|
|
|
| 43 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 44 |
"evaluation_protocol": "issue-now-score-later",
|
| 45 |
"metric_version": "livehouse-canonical-v1",
|
| 46 |
+
"evaluated_at": "2026-07-28T22:56:33.262521+00:00",
|
| 47 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
},
|
| 49 |
"Toto-1.0": {
|
| 50 |
"model": "Toto-1.0",
|
|
|
|
| 52 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 53 |
"evaluation_protocol": "issue-now-score-later",
|
| 54 |
"metric_version": "livehouse-canonical-v1",
|
| 55 |
+
"evaluated_at": "2026-07-28T22:56:33.262523+00:00",
|
| 56 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
},
|
| 58 |
"Moirai-2.0": {
|
| 59 |
"model": "Moirai-2.0",
|
|
|
|
| 61 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 62 |
"evaluation_protocol": "issue-now-score-later",
|
| 63 |
"metric_version": "livehouse-canonical-v1",
|
| 64 |
+
"evaluated_at": "2026-07-28T22:56:33.262524+00:00",
|
| 65 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
},
|
| 67 |
"Chronos-Bolt": {
|
| 68 |
"model": "Chronos-Bolt",
|
|
|
|
| 70 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 71 |
"evaluation_protocol": "issue-now-score-later",
|
| 72 |
"metric_version": "livehouse-canonical-v1",
|
| 73 |
+
"evaluated_at": "2026-07-28T22:56:33.262525+00:00",
|
| 74 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
},
|
| 76 |
"TabPFN-TS": {
|
| 77 |
"model": "TabPFN-TS",
|
|
|
|
| 79 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 80 |
"evaluation_protocol": "issue-now-score-later",
|
| 81 |
"metric_version": "livehouse-canonical-v1",
|
| 82 |
+
"evaluated_at": "2026-07-28T22:56:33.262525+00:00",
|
| 83 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
},
|
| 85 |
"Sundial": {
|
| 86 |
"model": "Sundial",
|
|
|
|
| 88 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 89 |
"evaluation_protocol": "issue-now-score-later",
|
| 90 |
"metric_version": "livehouse-canonical-v1",
|
| 91 |
+
"evaluated_at": "2026-07-28T22:56:33.262526+00:00",
|
| 92 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
},
|
| 94 |
"Moving-Average": {
|
| 95 |
"model": "Moving-Average",
|
|
|
|
| 97 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 98 |
"evaluation_protocol": "issue-now-score-later",
|
| 99 |
"metric_version": "livehouse-canonical-v1",
|
| 100 |
+
"evaluated_at": "2026-07-28T22:56:33.262527+00:00",
|
| 101 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
},
|
| 103 |
"ETS": {
|
| 104 |
"model": "ETS",
|
|
|
|
| 106 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 107 |
"evaluation_protocol": "issue-now-score-later",
|
| 108 |
"metric_version": "livehouse-canonical-v1",
|
| 109 |
+
"evaluated_at": "2026-07-28T22:56:33.262528+00:00",
|
| 110 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
},
|
| 112 |
"ARIMA": {
|
| 113 |
"model": "ARIMA",
|
|
|
|
| 115 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 116 |
"evaluation_protocol": "issue-now-score-later",
|
| 117 |
"metric_version": "livehouse-canonical-v1",
|
| 118 |
+
"evaluated_at": "2026-07-28T22:56:33.262529+00:00",
|
| 119 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
},
|
| 121 |
"Seasonal-Naive": {
|
| 122 |
"model": "Seasonal-Naive",
|
|
|
|
| 124 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 125 |
"evaluation_protocol": "issue-now-score-later",
|
| 126 |
"metric_version": "livehouse-canonical-v1",
|
| 127 |
+
"evaluated_at": "2026-07-28T22:56:33.262530+00:00",
|
| 128 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
}
|
| 130 |
},
|
| 131 |
"skipped_models": [],
|
|
|
|
| 148 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 149 |
"live_metadata": "aggregates/live_metadata.json"
|
| 150 |
},
|
| 151 |
+
"push_status": "pending"
|
|
|
|
|
|
|
| 152 |
}
|