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 -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_properties.csv +0 -1
- results/online_status.json +39 -155
results/aggregates/live_metadata.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"generated_at": "2026-07-28T11:
|
| 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": "2026-07-28T11:19:36.148110+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": "2026-07-28T11:
|
| 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": "2026-07-28T11:19:33.977330+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
|
@@ -47,18 +47,18 @@ Hydrology,TimesFM-2.5,0.9803612181482216,1.233648004890988,9,1,1,1.0
|
|
| 47 |
Hydrology,Toto-1.0,1.1451138792621596,1.306230026308965,10,1,1,1.0
|
| 48 |
Hydrology,Chronos-2,2.457496578202893,1.3091303454283423,11,1,1,1.0
|
| 49 |
Hydrology,ARIMA,1.5227614333785564,3.981677710914025,12,1,1,1.0
|
| 50 |
-
Ocean,ETS,0.
|
| 51 |
-
Ocean,
|
| 52 |
-
Ocean,Toto-1.0,0.
|
| 53 |
-
Ocean,
|
| 54 |
-
Ocean,
|
| 55 |
-
Ocean,
|
| 56 |
-
Ocean,
|
| 57 |
-
Ocean,
|
| 58 |
-
Ocean,
|
| 59 |
-
Ocean,
|
| 60 |
-
Ocean,
|
| 61 |
-
Ocean,
|
| 62 |
Transportation,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 63 |
Transportation,TabPFN-TS,1.0,1.0,2,1,1,1.0
|
| 64 |
Transportation,TimesFM-2.5,1.0,1.0,3,1,1,1.0
|
|
|
|
| 47 |
Hydrology,Toto-1.0,1.1451138792621596,1.306230026308965,10,1,1,1.0
|
| 48 |
Hydrology,Chronos-2,2.457496578202893,1.3091303454283423,11,1,1,1.0
|
| 49 |
Hydrology,ARIMA,1.5227614333785564,3.981677710914025,12,1,1,1.0
|
| 50 |
+
Ocean,ETS,0.031050189676036656,0.14314006512872457,1,1,1,1.0
|
| 51 |
+
Ocean,TiRex,0.03752870175584104,0.1890409737883149,2,1,1,1.0
|
| 52 |
+
Ocean,Toto-1.0,0.1764663682104904,0.19336747018849068,3,1,1,1.0
|
| 53 |
+
Ocean,ARIMA,0.07678327550120892,0.25582709334217635,4,1,1,1.0
|
| 54 |
+
Ocean,TimesFM-2.5,0.2903315834748498,0.40636815846095625,5,1,1,1.0
|
| 55 |
+
Ocean,Chronos-Bolt,0.2294921504912728,0.4201749753531201,6,1,1,1.0
|
| 56 |
+
Ocean,Chronos-2,0.669972758870577,0.5000607028464571,7,1,1,1.0
|
| 57 |
+
Ocean,Sundial,0.5785787197639195,0.5641623333193234,8,1,1,1.0
|
| 58 |
+
Ocean,Moirai-2.0,1.1482811386021479,0.6762267218142929,9,1,1,1.0
|
| 59 |
+
Ocean,TabPFN-TS,0.753906838734417,0.7856627814848356,10,1,1,1.0
|
| 60 |
+
Ocean,Moving-Average,0.9973907228666833,0.9916980332443733,11,1,1,1.0
|
| 61 |
+
Ocean,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
| 62 |
Transportation,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 63 |
Transportation,TabPFN-TS,1.0,1.0,2,1,1,1.0
|
| 64 |
Transportation,TimesFM-2.5,1.0,1.0,3,1,1,1.0
|
results/aggregates/results_by_frequency.csv
CHANGED
|
@@ -1,16 +1,4 @@
|
|
| 1 |
frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
10min,Moving-Average,0.715655939906452,0.8046108612426879,1,1,1,1.0
|
| 3 |
-
10min,Sundial,0.9478346272616678,0.8512985533110731,2,1,1,1.0
|
| 4 |
-
10min,ETS,0.8446294028868107,0.8650664883451831,3,1,1,1.0
|
| 5 |
-
10min,ARIMA,0.998031220467021,0.878316920566861,4,1,1,1.0
|
| 6 |
-
10min,TimesFM-2.5,0.9284392794634112,0.9147245318220383,5,1,1,1.0
|
| 7 |
-
10min,Toto-1.0,2.142260641579121,0.9605682331137553,6,1,1,1.0
|
| 8 |
-
10min,Seasonal-Naive,1.0,1.0,7,1,1,1.0
|
| 9 |
-
10min,Moirai-2.0,0.9563740759422352,1.0533637272294145,8,1,1,1.0
|
| 10 |
-
10min,TiRex,1.1938300014223484,1.1305635314839364,9,1,1,1.0
|
| 11 |
-
10min,Chronos-2,1.0556494832507781,1.1392385682255801,10,1,1,1.0
|
| 12 |
-
10min,Chronos-Bolt,1.4884642794846972,1.4269476835433796,11,1,1,1.0
|
| 13 |
-
10min,TabPFN-TS,1.7478073281306592,1.5117066126516778,12,1,1,1.0
|
| 14 |
15min,TabPFN-TS,0.999629604599128,0.707716762271388,1,1,1,1.0
|
| 15 |
15min,Moving-Average,0.8837777777779868,0.8318514644351539,2,1,1,1.0
|
| 16 |
15min,Sundial,0.7169457146463295,0.8879194379351649,3,1,1,1.0
|
|
|
|
| 1 |
frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
15min,TabPFN-TS,0.999629604599128,0.707716762271388,1,1,1,1.0
|
| 3 |
15min,Moving-Average,0.8837777777779868,0.8318514644351539,2,1,1,1.0
|
| 4 |
15min,Sundial,0.7169457146463295,0.8879194379351649,3,1,1,1.0
|
results/aggregates/results_by_prediction_length.csv
CHANGED
|
@@ -59,15 +59,3 @@ prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 59 |
60,TabPFN-TS,0.753906838734417,0.7856627814848356,10,1,1,1.0
|
| 60 |
60,Moving-Average,0.9973907228666833,0.9916980332443733,11,1,1,1.0
|
| 61 |
60,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
| 62 |
-
72,Moving-Average,0.715655939906452,0.8046108612426879,1,1,1,1.0
|
| 63 |
-
72,Sundial,0.9478346272616678,0.8512985533110731,2,1,1,1.0
|
| 64 |
-
72,ETS,0.8446294028868107,0.8650664883451831,3,1,1,1.0
|
| 65 |
-
72,ARIMA,0.998031220467021,0.878316920566861,4,1,1,1.0
|
| 66 |
-
72,TimesFM-2.5,0.9284392794634112,0.9147245318220383,5,1,1,1.0
|
| 67 |
-
72,Toto-1.0,2.142260641579121,0.9605682331137553,6,1,1,1.0
|
| 68 |
-
72,Seasonal-Naive,1.0,1.0,7,1,1,1.0
|
| 69 |
-
72,Moirai-2.0,0.9563740759422352,1.0533637272294145,8,1,1,1.0
|
| 70 |
-
72,TiRex,1.1938300014223484,1.1305635314839364,9,1,1,1.0
|
| 71 |
-
72,Chronos-2,1.0556494832507781,1.1392385682255801,10,1,1,1.0
|
| 72 |
-
72,Chronos-Bolt,1.4884642794846972,1.4269476835433796,11,1,1,1.0
|
| 73 |
-
72,TabPFN-TS,1.7478073281306592,1.5117066126516778,12,1,1,1.0
|
|
|
|
| 59 |
60,TabPFN-TS,0.753906838734417,0.7856627814848356,10,1,1,1.0
|
| 60 |
60,Moving-Average,0.9973907228666833,0.9916980332443733,11,1,1,1.0
|
| 61 |
60,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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,
|
| 4 |
-
Overall,
|
| 5 |
-
Overall,Chronos-Bolt,0.
|
| 6 |
-
Overall,Moirai-2.0,0.
|
| 7 |
-
Overall,
|
| 8 |
-
Overall,
|
| 9 |
-
Overall,Toto-1.0,
|
| 10 |
-
Overall,
|
| 11 |
-
Overall,
|
| 12 |
-
Overall,
|
| 13 |
-
Overall,
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,TiRex,0.4139934794332643,1.2369681537228583,1,12,12,1.0
|
| 3 |
+
Overall,Chronos-2,0.5823909227630778,1.4130146647961979,2,12,12,1.0
|
| 4 |
+
Overall,Sundial,0.6817035838726988,1.6922879477563222,3,12,12,1.0
|
| 5 |
+
Overall,Chronos-Bolt,0.5723873519534353,2.5454507696302926,4,12,12,1.0
|
| 6 |
+
Overall,Moirai-2.0,0.5684899699004231,2.2198608221772145,5,12,12,1.0
|
| 7 |
+
Overall,TabPFN-TS,0.6947533112441893,0.8116818778678158,6,12,12,1.0
|
| 8 |
+
Overall,TimesFM-2.5,0.5507417794606603,0.7847459191625626,7,12,12,1.0
|
| 9 |
+
Overall,Toto-1.0,5.2642142695079475,3.4867898781685396,8,12,12,1.0
|
| 10 |
+
Overall,ARIMA,1.0226994612016658,3.014792510116591,9,12,12,1.0
|
| 11 |
+
Overall,Seasonal-Naive,1.0,1.0,10,12,12,1.0
|
| 12 |
+
Overall,Moving-Average,1.139437182143812,3.0051804477088764,11,12,12,1.0
|
| 13 |
+
Overall,ETS,1.3839928099765386,3.3000988257288935,12,12,12,1.0
|
results/dataset_properties.csv
CHANGED
|
@@ -5,7 +5,6 @@ data_gov_sg_singapore_rainfall_5min_rainfall_5min_total,Climate,5min,1
|
|
| 5 |
data_gov_sg_singapore_taxi_availability_available_taxi_count,Transportation,5min,1
|
| 6 |
nasa_power_shanghai_hourly_t2m,Weather,1h,1
|
| 7 |
noaa_coops_sf_water_level_water_level,Ocean,6min,1
|
| 8 |
-
noaa_ndbc_46013_realtime_wave_height,Ocean,10min,1
|
| 9 |
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
|
|
|
|
| 5 |
data_gov_sg_singapore_taxi_availability_available_taxi_count,Transportation,5min,1
|
| 6 |
nasa_power_shanghai_hourly_t2m,Weather,1h,1
|
| 7 |
noaa_coops_sf_water_level_water_level,Ocean,6min,1
|
|
|
|
| 8 |
nws_ksfo_observations_temperature,Weather,1h,1
|
| 9 |
open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
|
| 10 |
open_meteo_shanghai_hourly_temperature_2m,Weather,1h,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": "2026-07-28T11:
|
| 6 |
-
"finished_at": "2026-07-28T11:
|
| 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": "2026-07-28T11:
|
| 23 |
-
"resolved_tasks": [
|
| 24 |
-
{
|
| 25 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 26 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 27 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 28 |
-
"resolved_at": "2026-07-28T11:04:14.041460+00:00",
|
| 29 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 42 |
-
"resolved_tasks": [
|
| 43 |
-
{
|
| 44 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 45 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 46 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 47 |
-
"resolved_at": "2026-07-28T11:04:14.373058+00:00",
|
| 48 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 61 |
-
"resolved_tasks": [
|
| 62 |
-
{
|
| 63 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 64 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 65 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 66 |
-
"resolved_at": "2026-07-28T11:04:14.337094+00:00",
|
| 67 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 80 |
-
"resolved_tasks": [
|
| 81 |
-
{
|
| 82 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 83 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 84 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 85 |
-
"resolved_at": "2026-07-28T11:04:14.404902+00:00",
|
| 86 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 99 |
-
"resolved_tasks": [
|
| 100 |
-
{
|
| 101 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 102 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 103 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 104 |
-
"resolved_at": "2026-07-28T11:04:14.175044+00:00",
|
| 105 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 118 |
-
"resolved_tasks": [
|
| 119 |
-
{
|
| 120 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 121 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 122 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 123 |
-
"resolved_at": "2026-07-28T11:04:14.088963+00:00",
|
| 124 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 137 |
-
"resolved_tasks": [
|
| 138 |
-
{
|
| 139 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 140 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 141 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 142 |
-
"resolved_at": "2026-07-28T11:04:14.283160+00:00",
|
| 143 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 156 |
-
"resolved_tasks": [
|
| 157 |
-
{
|
| 158 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 159 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 160 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 161 |
-
"resolved_at": "2026-07-28T11:04:14.261038+00:00",
|
| 162 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 175 |
-
"resolved_tasks": [
|
| 176 |
-
{
|
| 177 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 178 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 179 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 180 |
-
"resolved_at": "2026-07-28T11:04:14.200349+00:00",
|
| 181 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 194 |
-
"resolved_tasks": [
|
| 195 |
-
{
|
| 196 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 197 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 198 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 199 |
-
"resolved_at": "2026-07-28T11:04:14.141945+00:00",
|
| 200 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 213 |
-
"resolved_tasks": [
|
| 214 |
-
{
|
| 215 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 216 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 217 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 218 |
-
"resolved_at": "2026-07-28T11:04:14.000331+00:00",
|
| 219 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:
|
| 232 |
-
"resolved_tasks": [
|
| 233 |
-
{
|
| 234 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 235 |
-
"task_id": "future-38fbf697b6a3396bc559",
|
| 236 |
-
"issued_at": "2026-07-28T10:41:05.473988+00:00",
|
| 237 |
-
"resolved_at": "2026-07-28T11:04:14.230904+00:00",
|
| 238 |
-
"target_end": "2026-07-27T06:40:00+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": "2026-07-28T11:07:45.924562+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": "2026-07-28T11:19:27.154814+00:00",
|
| 6 |
+
"finished_at": "2026-07-28T11:19:36.160049+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": "2026-07-28T11:19:31.891131+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": "2026-07-28T11:19:31.891139+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": "2026-07-28T11:19:31.891140+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": "2026-07-28T11:19:31.891141+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": "2026-07-28T11:19:31.891142+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": "2026-07-28T11:19:31.891143+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": "2026-07-28T11:19:31.891144+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": "2026-07-28T11:19:31.891145+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": "2026-07-28T11:19:31.891146+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": "2026-07-28T11:19:31.891146+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": "2026-07-28T11:19:31.891147+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": "2026-07-28T11:19:31.891148+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 |
}
|