Spaces:
Running
Running
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 +31 -153
results/aggregates/live_metadata.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"generated_at": "2026-07-27T09:
|
| 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": "2026-07-27T09:56:42.558415+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": "2026-07-27T09:
|
| 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": "2026-07-27T09:56:40.519948+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,TimesFM-2.5,0.7247978632328378,0.8249918557759415,9,1,1,1.0
|
|
| 35 |
Hazards,Sundial,1.0169587977425802,0.9183235752037384,10,1,1,1.0
|
| 36 |
Hazards,TabPFN-TS,0.7939141618582515,0.9372016432334698,11,1,1,1.0
|
| 37 |
Hazards,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
Ocean,Moving-Average,0.6885555599162482,0.7882638185220112,1,2,2,1.0
|
| 39 |
Ocean,Sundial,1.0100384161323002,0.9753941694223817,2,2,2,1.0
|
| 40 |
Ocean,TimesFM-2.5,0.6685946883150999,0.7997804319007484,3,2,2,1.0
|
|
|
|
| 35 |
Hazards,Sundial,1.0169587977425802,0.9183235752037384,10,1,1,1.0
|
| 36 |
Hazards,TabPFN-TS,0.7939141618582515,0.9372016432334698,11,1,1,1.0
|
| 37 |
Hazards,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
| 38 |
+
Hydrology,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
+
Hydrology,Moirai-2.0,1.0,1.1811008163011596,2,1,1,1.0
|
| 40 |
+
Hydrology,ARIMA,1.000000000936299,1.18110235783726,3,1,1,1.0
|
| 41 |
+
Hydrology,ETS,1.000000000936299,1.18110235783726,4,1,1,1.0
|
| 42 |
+
Hydrology,Moving-Average,1.000000000936299,1.18110235783726,5,1,1,1.0
|
| 43 |
+
Hydrology,Chronos-2,1.0,1.1811023622047234,6,1,1,1.0
|
| 44 |
+
Hydrology,Chronos-Bolt,1.0,1.1811023622047234,7,1,1,1.0
|
| 45 |
+
Hydrology,Sundial,1.0,1.1811023622047234,8,1,1,1.0
|
| 46 |
+
Hydrology,TabPFN-TS,1.0,1.1811023622047234,9,1,1,1.0
|
| 47 |
+
Hydrology,TimesFM-2.5,1.0,1.1811023622047234,10,1,1,1.0
|
| 48 |
+
Hydrology,Toto-1.0,1.7839556631798548,1.3622767704574028,11,1,1,1.0
|
| 49 |
+
Hydrology,TiRex,0.9568451217122376,1.4505235406670343,12,1,1,1.0
|
| 50 |
Ocean,Moving-Average,0.6885555599162482,0.7882638185220112,1,2,2,1.0
|
| 51 |
Ocean,Sundial,1.0100384161323002,0.9753941694223817,2,2,2,1.0
|
| 52 |
Ocean,TimesFM-2.5,0.6685946883150999,0.7997804319007484,3,2,2,1.0
|
results/aggregates/results_by_frequency.csv
CHANGED
|
@@ -11,6 +11,18 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 11 |
10min,Chronos-Bolt,1.0019529557526288,0.9863010922397192,10,1,1,1.0
|
| 12 |
10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 13 |
10min,Chronos-2,1.4062990275163183,1.0749886941936895,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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,Chronos-Bolt,1.0019529557526288,0.9863010922397192,10,1,1,1.0
|
| 12 |
10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 13 |
10min,Chronos-2,1.4062990275163183,1.0749886941936895,12,1,1,1.0
|
| 14 |
+
15min,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 15 |
+
15min,Moirai-2.0,1.0,1.1811008163011596,2,1,1,1.0
|
| 16 |
+
15min,ARIMA,1.000000000936299,1.18110235783726,3,1,1,1.0
|
| 17 |
+
15min,ETS,1.000000000936299,1.18110235783726,4,1,1,1.0
|
| 18 |
+
15min,Moving-Average,1.000000000936299,1.18110235783726,5,1,1,1.0
|
| 19 |
+
15min,Chronos-2,1.0,1.1811023622047234,6,1,1,1.0
|
| 20 |
+
15min,Chronos-Bolt,1.0,1.1811023622047234,7,1,1,1.0
|
| 21 |
+
15min,Sundial,1.0,1.1811023622047234,8,1,1,1.0
|
| 22 |
+
15min,TabPFN-TS,1.0,1.1811023622047234,9,1,1,1.0
|
| 23 |
+
15min,TimesFM-2.5,1.0,1.1811023622047234,10,1,1,1.0
|
| 24 |
+
15min,Toto-1.0,1.7839556631798548,1.3622767704574028,11,1,1,1.0
|
| 25 |
+
15min,TiRex,0.9568451217122376,1.4505235406670343,12,1,1,1.0
|
| 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-1.0,296910.5495133771,13406.731654855768,11,2,2,1.0
|
| 25 |
12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
|
| 26 |
-
24,TiRex,0.
|
| 27 |
-
24,
|
| 28 |
-
24,
|
| 29 |
-
24,
|
| 30 |
-
24,
|
| 31 |
-
24,TabPFN-TS,0.
|
| 32 |
-
24,Sundial,1.
|
| 33 |
-
24,Chronos-Bolt,1.
|
| 34 |
-
24,TimesFM-2.5,0.
|
| 35 |
-
24,ARIMA,
|
| 36 |
-
24,Moving-Average,
|
| 37 |
-
24,ETS,
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,Moving-Average,1208318634.7525988,1.0,2,1,1,1.0
|
| 40 |
36,ARIMA,1083193423.3268,342.79755336616876,3,1,1,1.0
|
|
|
|
| 23 |
12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
|
| 24 |
12,Toto-1.0,296910.5495133771,13406.731654855768,11,2,2,1.0
|
| 25 |
12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
|
| 26 |
+
24,TiRex,0.7863964815415329,0.9439695608862385,1,7,7,1.0
|
| 27 |
+
24,Seasonal-Naive,1.0,1.0,2,7,7,1.0
|
| 28 |
+
24,Moirai-2.0,1.1867884414932584,1.022296617798916,3,7,7,1.0
|
| 29 |
+
24,Toto-1.0,3.37212375775342,0.9086153682008863,4,7,7,1.0
|
| 30 |
+
24,Chronos-2,1.0121992393929897,0.9430509286507205,5,7,7,1.0
|
| 31 |
+
24,TabPFN-TS,0.7876590398010317,0.9589832700406598,6,7,7,1.0
|
| 32 |
+
24,Sundial,1.3062275772015808,0.9867392589565129,7,7,7,1.0
|
| 33 |
+
24,Chronos-Bolt,1.1351348942591646,0.9683758186291227,8,7,7,1.0
|
| 34 |
+
24,TimesFM-2.5,0.9186256070061112,1.0326581173710205,9,7,7,1.0
|
| 35 |
+
24,ARIMA,4.376692834011164,2.3074313100174684,10,7,7,1.0
|
| 36 |
+
24,Moving-Average,2.880330512406768,1.803153320337502,11,7,7,1.0
|
| 37 |
+
24,ETS,14.562789605162186,4.211560817547539,12,7,7,1.0
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,Moving-Average,1208318634.7525988,1.0,2,1,1,1.0
|
| 40 |
36,ARIMA,1083193423.3268,342.79755336616876,3,1,1,1.0
|
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,2.
|
| 3 |
-
Overall,
|
| 4 |
-
Overall,
|
| 5 |
-
Overall,
|
| 6 |
-
Overall,
|
| 7 |
-
Overall,
|
| 8 |
-
Overall,
|
| 9 |
-
Overall,Moving-Average,
|
| 10 |
-
Overall,TimesFM-2.5,2.
|
| 11 |
-
Overall,TabPFN-TS,
|
| 12 |
-
Overall,
|
| 13 |
-
Overall,
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,TiRex,2.0991582488730605,7.272594589450372,1,13,13,1.0
|
| 3 |
+
Overall,Moirai-2.0,3.2557943084109247,12.790585698948476,2,13,13,1.0
|
| 4 |
+
Overall,Seasonal-Naive,1.0,1.0,3,13,13,1.0
|
| 5 |
+
Overall,Chronos-2,2.757971452657122,8.127813702723484,4,13,13,1.0
|
| 6 |
+
Overall,ARIMA,10.006371577164353,5.965546569331156,5,13,13,1.0
|
| 7 |
+
Overall,Sundial,5.4243836782106065,11.709954106357802,6,13,13,1.0
|
| 8 |
+
Overall,Toto-1.0,97.80852746293337,20.122322317037032,7,13,13,1.0
|
| 9 |
+
Overall,Moving-Average,7.77735013145603,3.2597797515273625,8,13,13,1.0
|
| 10 |
+
Overall,TimesFM-2.5,2.3957050062333347,5.060254160244622,9,13,13,1.0
|
| 11 |
+
Overall,TabPFN-TS,2.810376272659753,5.13691000772867,10,13,13,1.0
|
| 12 |
+
Overall,ETS,20.117996726113848,12.208099157961373,11,13,13,1.0
|
| 13 |
+
Overall,Chronos-Bolt,4.1807698383593035,17.633100330024003,12,13,13,1.0
|
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
|
@@ -2,14 +2,14 @@
|
|
| 2 |
"status": "ok",
|
| 3 |
"evaluation_protocol": "issue-now-score-later",
|
| 4 |
"metric_version": "livehouse-canonical-v1",
|
| 5 |
-
"started_at": "2026-07-27T09:
|
| 6 |
-
"finished_at": "2026-07-27T09:
|
| 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": {
|
|
@@ -19,18 +19,8 @@
|
|
| 19 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 20 |
"evaluation_protocol": "issue-now-score-later",
|
| 21 |
"metric_version": "livehouse-canonical-v1",
|
| 22 |
-
"evaluated_at": "2026-07-27T09:
|
| 23 |
-
"resolved_tasks": [
|
| 24 |
-
{
|
| 25 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 26 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 27 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 28 |
-
"resolved_at": "2026-07-27T09:42:48.855197+00:00",
|
| 29 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 30 |
-
"prediction_length": 12,
|
| 31 |
-
"metric_version": "livehouse-canonical-v1"
|
| 32 |
-
}
|
| 33 |
-
]
|
| 34 |
},
|
| 35 |
"TiRex": {
|
| 36 |
"model": "TiRex",
|
|
@@ -38,18 +28,8 @@
|
|
| 38 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 39 |
"evaluation_protocol": "issue-now-score-later",
|
| 40 |
"metric_version": "livehouse-canonical-v1",
|
| 41 |
-
"evaluated_at": "2026-07-27T09:
|
| 42 |
-
"resolved_tasks": [
|
| 43 |
-
{
|
| 44 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 45 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 46 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 47 |
-
"resolved_at": "2026-07-27T09:42:49.269283+00:00",
|
| 48 |
-
"target_end": "2026-07-26T00:05:00+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 +37,8 @@
|
|
| 57 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 58 |
"evaluation_protocol": "issue-now-score-later",
|
| 59 |
"metric_version": "livehouse-canonical-v1",
|
| 60 |
-
"evaluated_at": "2026-07-27T09:
|
| 61 |
-
"resolved_tasks": [
|
| 62 |
-
{
|
| 63 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 64 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 65 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 66 |
-
"resolved_at": "2026-07-27T09:42:49.213115+00:00",
|
| 67 |
-
"target_end": "2026-07-26T00:05:00+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 +46,8 @@
|
|
| 76 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 77 |
"evaluation_protocol": "issue-now-score-later",
|
| 78 |
"metric_version": "livehouse-canonical-v1",
|
| 79 |
-
"evaluated_at": "2026-07-27T09:
|
| 80 |
-
"resolved_tasks": [
|
| 81 |
-
{
|
| 82 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 83 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 84 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 85 |
-
"resolved_at": "2026-07-27T09:42:49.324286+00:00",
|
| 86 |
-
"target_end": "2026-07-26T00:05:00+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 +55,8 @@
|
|
| 95 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 96 |
"evaluation_protocol": "issue-now-score-later",
|
| 97 |
"metric_version": "livehouse-canonical-v1",
|
| 98 |
-
"evaluated_at": "2026-07-27T09:
|
| 99 |
-
"resolved_tasks": [
|
| 100 |
-
{
|
| 101 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 102 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 103 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 104 |
-
"resolved_at": "2026-07-27T09:42:49.042964+00:00",
|
| 105 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 106 |
-
"prediction_length": 12,
|
| 107 |
-
"metric_version": "livehouse-canonical-v1"
|
| 108 |
-
}
|
| 109 |
-
]
|
| 110 |
},
|
| 111 |
"Chronos-Bolt": {
|
| 112 |
"model": "Chronos-Bolt",
|
|
@@ -114,18 +64,8 @@
|
|
| 114 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 115 |
"evaluation_protocol": "issue-now-score-later",
|
| 116 |
"metric_version": "livehouse-canonical-v1",
|
| 117 |
-
"evaluated_at": "2026-07-27T09:
|
| 118 |
-
"resolved_tasks": [
|
| 119 |
-
{
|
| 120 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 121 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 122 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 123 |
-
"resolved_at": "2026-07-27T09:42:48.931036+00:00",
|
| 124 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 125 |
-
"prediction_length": 12,
|
| 126 |
-
"metric_version": "livehouse-canonical-v1"
|
| 127 |
-
}
|
| 128 |
-
]
|
| 129 |
},
|
| 130 |
"TabPFN-TS": {
|
| 131 |
"model": "TabPFN-TS",
|
|
@@ -133,18 +73,8 @@
|
|
| 133 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 134 |
"evaluation_protocol": "issue-now-score-later",
|
| 135 |
"metric_version": "livehouse-canonical-v1",
|
| 136 |
-
"evaluated_at": "2026-07-27T09:
|
| 137 |
-
"resolved_tasks": [
|
| 138 |
-
{
|
| 139 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 140 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 141 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 142 |
-
"resolved_at": "2026-07-27T09:42:49.161563+00:00",
|
| 143 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 144 |
-
"prediction_length": 12,
|
| 145 |
-
"metric_version": "livehouse-canonical-v1"
|
| 146 |
-
}
|
| 147 |
-
]
|
| 148 |
},
|
| 149 |
"Sundial": {
|
| 150 |
"model": "Sundial",
|
|
@@ -152,18 +82,8 @@
|
|
| 152 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 153 |
"evaluation_protocol": "issue-now-score-later",
|
| 154 |
"metric_version": "livehouse-canonical-v1",
|
| 155 |
-
"evaluated_at": "2026-07-27T09:
|
| 156 |
-
"resolved_tasks": [
|
| 157 |
-
{
|
| 158 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 159 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 160 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 161 |
-
"resolved_at": "2026-07-27T09:42:49.113043+00:00",
|
| 162 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 163 |
-
"prediction_length": 12,
|
| 164 |
-
"metric_version": "livehouse-canonical-v1"
|
| 165 |
-
}
|
| 166 |
-
]
|
| 167 |
},
|
| 168 |
"Moving-Average": {
|
| 169 |
"model": "Moving-Average",
|
|
@@ -171,18 +91,8 @@
|
|
| 171 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 172 |
"evaluation_protocol": "issue-now-score-later",
|
| 173 |
"metric_version": "livehouse-canonical-v1",
|
| 174 |
-
"evaluated_at": "2026-07-27T09:
|
| 175 |
-
"resolved_tasks": [
|
| 176 |
-
{
|
| 177 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 178 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 179 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 180 |
-
"resolved_at": "2026-07-27T09:42:49.063161+00:00",
|
| 181 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 182 |
-
"prediction_length": 12,
|
| 183 |
-
"metric_version": "livehouse-canonical-v1"
|
| 184 |
-
}
|
| 185 |
-
]
|
| 186 |
},
|
| 187 |
"ETS": {
|
| 188 |
"model": "ETS",
|
|
@@ -190,18 +100,8 @@
|
|
| 190 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 191 |
"evaluation_protocol": "issue-now-score-later",
|
| 192 |
"metric_version": "livehouse-canonical-v1",
|
| 193 |
-
"evaluated_at": "2026-07-27T09:
|
| 194 |
-
"resolved_tasks": [
|
| 195 |
-
{
|
| 196 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 197 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 198 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 199 |
-
"resolved_at": "2026-07-27T09:42:48.996024+00:00",
|
| 200 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 201 |
-
"prediction_length": 12,
|
| 202 |
-
"metric_version": "livehouse-canonical-v1"
|
| 203 |
-
}
|
| 204 |
-
]
|
| 205 |
},
|
| 206 |
"ARIMA": {
|
| 207 |
"model": "ARIMA",
|
|
@@ -209,18 +109,8 @@
|
|
| 209 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 210 |
"evaluation_protocol": "issue-now-score-later",
|
| 211 |
"metric_version": "livehouse-canonical-v1",
|
| 212 |
-
"evaluated_at": "2026-07-27T09:
|
| 213 |
-
"resolved_tasks": [
|
| 214 |
-
{
|
| 215 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 216 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 217 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 218 |
-
"resolved_at": "2026-07-27T09:42:48.775574+00:00",
|
| 219 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 220 |
-
"prediction_length": 12,
|
| 221 |
-
"metric_version": "livehouse-canonical-v1"
|
| 222 |
-
}
|
| 223 |
-
]
|
| 224 |
},
|
| 225 |
"Seasonal-Naive": {
|
| 226 |
"model": "Seasonal-Naive",
|
|
@@ -228,18 +118,8 @@
|
|
| 228 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 229 |
"evaluation_protocol": "issue-now-score-later",
|
| 230 |
"metric_version": "livehouse-canonical-v1",
|
| 231 |
-
"evaluated_at": "2026-07-27T09:
|
| 232 |
-
"resolved_tasks": [
|
| 233 |
-
{
|
| 234 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 235 |
-
"task_id": "future-8f0dd89c2daa53783fa6",
|
| 236 |
-
"issued_at": "2026-07-27T08:34:30.317021+00:00",
|
| 237 |
-
"resolved_at": "2026-07-27T09:42:49.085103+00:00",
|
| 238 |
-
"target_end": "2026-07-26T00:05:00+00:00",
|
| 239 |
-
"prediction_length": 12,
|
| 240 |
-
"metric_version": "livehouse-canonical-v1"
|
| 241 |
-
}
|
| 242 |
-
]
|
| 243 |
}
|
| 244 |
},
|
| 245 |
"skipped_models": [],
|
|
@@ -262,7 +142,5 @@
|
|
| 262 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 263 |
"live_metadata": "aggregates/live_metadata.json"
|
| 264 |
},
|
| 265 |
-
"push_status": "
|
| 266 |
-
"pushed_at": "2026-07-27T09:45:55.031887+00:00",
|
| 267 |
-
"push_detail": "HF Hub API"
|
| 268 |
}
|
|
|
|
| 2 |
"status": "ok",
|
| 3 |
"evaluation_protocol": "issue-now-score-later",
|
| 4 |
"metric_version": "livehouse-canonical-v1",
|
| 5 |
+
"started_at": "2026-07-27T09:56:35.563556+00:00",
|
| 6 |
+
"finished_at": "2026-07-27T09:56:42.569509+00:00",
|
| 7 |
"data_source": "ts_bench",
|
| 8 |
"data_config": "configs/datasets/ts_bench.yaml",
|
| 9 |
+
"task_count": 1,
|
| 10 |
+
"issued_tasks": 0,
|
| 11 |
+
"issued_forecasts": 0,
|
| 12 |
+
"resolved_forecasts": 0,
|
| 13 |
"pending_tasks": 13,
|
| 14 |
"failed_forecasts": [],
|
| 15 |
"models": {
|
|
|
|
| 19 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 20 |
"evaluation_protocol": "issue-now-score-later",
|
| 21 |
"metric_version": "livehouse-canonical-v1",
|
| 22 |
+
"evaluated_at": "2026-07-27T09:56:38.634259+00:00",
|
| 23 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
},
|
| 25 |
"TiRex": {
|
| 26 |
"model": "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": "2026-07-27T09:56:38.634266+00:00",
|
| 32 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
"TimesFM-2.5": {
|
| 35 |
"model": "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": "2026-07-27T09:56:38.634268+00:00",
|
| 41 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
},
|
| 43 |
"Toto-1.0": {
|
| 44 |
"model": "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": "2026-07-27T09:56:38.634269+00:00",
|
| 50 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
},
|
| 52 |
"Moirai-2.0": {
|
| 53 |
"model": "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": "2026-07-27T09:56:38.634270+00:00",
|
| 59 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
"Chronos-Bolt": {
|
| 62 |
"model": "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": "2026-07-27T09:56:38.634271+00:00",
|
| 68 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
},
|
| 70 |
"TabPFN-TS": {
|
| 71 |
"model": "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": "2026-07-27T09:56:38.634272+00:00",
|
| 77 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
},
|
| 79 |
"Sundial": {
|
| 80 |
"model": "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": "2026-07-27T09:56:38.634273+00:00",
|
| 86 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
},
|
| 88 |
"Moving-Average": {
|
| 89 |
"model": "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": "2026-07-27T09:56:38.634274+00:00",
|
| 95 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
},
|
| 97 |
"ETS": {
|
| 98 |
"model": "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": "2026-07-27T09:56:38.634275+00:00",
|
| 104 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
},
|
| 106 |
"ARIMA": {
|
| 107 |
"model": "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": "2026-07-27T09:56:38.634276+00:00",
|
| 113 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
},
|
| 115 |
"Seasonal-Naive": {
|
| 116 |
"model": "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": "2026-07-27T09:56:38.634277+00:00",
|
| 122 |
+
"resolved_tasks": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
}
|
| 124 |
},
|
| 125 |
"skipped_models": [],
|
|
|
|
| 142 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 143 |
"live_metadata": "aggregates/live_metadata.json"
|
| 144 |
},
|
| 145 |
+
"push_status": "pending"
|
|
|
|
|
|
|
| 146 |
}
|