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 +12 -12
- results/aggregates/results_by_prediction_length.csv +12 -12
- results/aggregates/results_overall.csv +12 -12
- results/dataset_properties.csv +0 -1
- results/online_status.json +31 -153
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": "2026-07-29T21:49:44.726529+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": "2026-07-29T21:49:42.473009+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
|
@@ -1,16 +1,16 @@
|
|
| 1 |
domain,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
Climate,
|
| 3 |
-
Climate,
|
| 4 |
-
Climate,
|
| 5 |
-
Climate,
|
| 6 |
-
Climate,
|
| 7 |
-
Climate,Chronos-Bolt,
|
| 8 |
-
Climate,
|
| 9 |
-
Climate,TabPFN-TS,
|
| 10 |
-
Climate,TimesFM-2.5,
|
| 11 |
-
Climate,
|
| 12 |
-
Climate,
|
| 13 |
-
Climate,ETS,
|
| 14 |
Finance,Moirai-2.0,0.22409481207132434,0.487951964417501,1,2,2,1.0
|
| 15 |
Finance,Chronos-Bolt,0.2736790800966687,0.5057014143672646,2,2,2,1.0
|
| 16 |
Finance,TiRex,0.20014521509059205,0.4804972472127513,3,2,2,1.0
|
|
|
|
| 1 |
domain,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Climate,Seasonal-Naive,1.0,1.0,1,4,4,1.0
|
| 3 |
+
Climate,Chronos-2,36.675848167030246,201.10058492462466,2,4,4,1.0
|
| 4 |
+
Climate,TiRex,11.09851215632723,152.67396458065787,3,4,4,1.0
|
| 5 |
+
Climate,Moirai-2.0,40.425234011545086,223.16454896905506,4,4,4,1.0
|
| 6 |
+
Climate,Sundial,210.12566895586264,313.061564621768,5,4,4,1.0
|
| 7 |
+
Climate,Chronos-Bolt,34.94133299104337,278.6490196554904,6,4,4,1.0
|
| 8 |
+
Climate,Toto-1.0,644.4764142229224,346.0154019891843,7,4,4,1.0
|
| 9 |
+
Climate,TabPFN-TS,19.134535274490723,152.05473959283918,8,4,4,1.0
|
| 10 |
+
Climate,TimesFM-2.5,25.9442647646039,373.1503538067695,9,4,4,1.0
|
| 11 |
+
Climate,Moving-Average,1325.028260031229,1179.4516121615643,10,4,4,1.0
|
| 12 |
+
Climate,ARIMA,3046.8638144933807,1160.9444252316086,11,4,4,1.0
|
| 13 |
+
Climate,ETS,6972.223952753726,2924.4898578319294,12,4,4,1.0
|
| 14 |
Finance,Moirai-2.0,0.22409481207132434,0.487951964417501,1,2,2,1.0
|
| 15 |
Finance,Chronos-Bolt,0.2736790800966687,0.5057014143672646,2,2,2,1.0
|
| 16 |
Finance,TiRex,0.20014521509059205,0.4804972472127513,3,2,2,1.0
|
results/aggregates/results_by_frequency.csv
CHANGED
|
@@ -35,18 +35,18 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 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,Sundial,0.
|
| 39 |
-
1h,Chronos-2,0.
|
| 40 |
-
1h,
|
| 41 |
-
1h,
|
| 42 |
-
1h,Moirai-2.0,0.
|
| 43 |
-
1h,
|
| 44 |
-
1h,
|
| 45 |
-
1h,Seasonal-Naive,1.0,1.0,8,
|
| 46 |
-
1h,
|
| 47 |
-
1h,TabPFN-TS,0.
|
| 48 |
-
1h,
|
| 49 |
-
1h,ETS,
|
| 50 |
1mo,Moirai-2.0,0.5701893078499076,0.5711658118752873,1,1,1,1.0
|
| 51 |
1mo,Chronos-Bolt,0.6722527938921684,0.6335328970612374,2,1,1,1.0
|
| 52 |
1mo,Toto-1.0,0.6317640740160342,0.6385745807295035,3,1,1,1.0
|
|
|
|
| 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,Sundial,0.5929488275540944,0.6676066531315284,1,5,5,1.0
|
| 39 |
+
1h,Chronos-2,0.4591365809362409,0.7736486277802658,2,5,5,1.0
|
| 40 |
+
1h,Chronos-Bolt,0.42975104038033024,0.8145532777511791,3,5,5,1.0
|
| 41 |
+
1h,TiRex,0.2948766604272711,0.8154869025188662,4,5,5,1.0
|
| 42 |
+
1h,Moirai-2.0,0.5027123887673739,0.8823906343684956,5,5,5,1.0
|
| 43 |
+
1h,TimesFM-2.5,0.38061362824285694,0.7972178483041099,6,5,5,1.0
|
| 44 |
+
1h,Toto-1.0,0.9588442971468709,0.9194173721283935,7,5,5,1.0
|
| 45 |
+
1h,Seasonal-Naive,1.0,1.0,8,5,5,1.0
|
| 46 |
+
1h,Moving-Average,3.0712641902052105,1.8757891044035515,9,5,5,1.0
|
| 47 |
+
1h,TabPFN-TS,0.8557960124642745,1.0882290856758259,10,5,5,1.0
|
| 48 |
+
1h,ARIMA,3.924671339530071,2.4135760373111195,11,5,5,1.0
|
| 49 |
+
1h,ETS,17.16719275626505,4.6079720425950095,12,5,5,1.0
|
| 50 |
1mo,Moirai-2.0,0.5701893078499076,0.5711658118752873,1,1,1,1.0
|
| 51 |
1mo,Chronos-Bolt,0.6722527938921684,0.6335328970612374,2,1,1,1.0
|
| 52 |
1mo,Toto-1.0,0.6317640740160342,0.6385745807295035,3,1,1,1.0
|
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-1.0,806035.7257398936,13298.536376002028,11,2,2,1.0
|
| 25 |
12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
|
| 26 |
-
24,
|
| 27 |
-
24,
|
| 28 |
-
24,
|
| 29 |
-
24,
|
| 30 |
-
24,
|
| 31 |
-
24,Toto-1.0,1.
|
| 32 |
-
24,
|
| 33 |
-
24,
|
| 34 |
-
24,Moving-Average,2.
|
| 35 |
-
24,
|
| 36 |
-
24,
|
| 37 |
-
24,ETS,
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,TabPFN-TS,34657.508680568775,161714991.14220017,2,1,1,1.0
|
| 40 |
36,TiRex,218854.47576766848,378635726.5998005,3,1,1,1.0
|
|
|
|
| 23 |
12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
|
| 24 |
12,Toto-1.0,806035.7257398936,13298.536376002028,11,2,2,1.0
|
| 25 |
12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
|
| 26 |
+
24,Chronos-2,0.542718917335337,0.7814218649047795,1,6,6,1.0
|
| 27 |
+
24,Sundial,0.6768392161365542,0.7414346907316497,2,6,6,1.0
|
| 28 |
+
24,TiRex,0.36763923399077486,0.8055123084386985,3,6,6,1.0
|
| 29 |
+
24,Moirai-2.0,0.520347192714634,0.8255150607549664,4,6,6,1.0
|
| 30 |
+
24,Chronos-Bolt,0.5219274414461282,0.8276923447862357,5,6,6,1.0
|
| 31 |
+
24,Toto-1.0,1.006797460669809,0.9023634996113736,6,6,6,1.0
|
| 32 |
+
24,Seasonal-Naive,1.0,1.0,7,6,6,1.0
|
| 33 |
+
24,TimesFM-2.5,0.4634779804622581,0.847797400283842,8,6,6,1.0
|
| 34 |
+
24,Moving-Average,2.444240306035469,1.6851874822725985,9,6,6,1.0
|
| 35 |
+
24,TabPFN-TS,0.8734089671598486,1.098057981179467,10,6,6,1.0
|
| 36 |
+
24,ARIMA,3.325337103982027,2.1714633994742605,11,6,6,1.0
|
| 37 |
+
24,ETS,10.646421202947378,3.6326039731193625,12,6,6,1.0
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,TabPFN-TS,34657.508680568775,161714991.14220017,2,1,1,1.0
|
| 40 |
36,TiRex,218854.47576766848,378635726.5998005,3,1,1,1.0
|
results/aggregates/results_overall.csv
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
Overall,
|
| 3 |
-
Overall,
|
| 4 |
-
Overall,Moirai-2.0,
|
| 5 |
-
Overall,Chronos-Bolt,
|
| 6 |
-
Overall,Sundial,3.
|
| 7 |
-
Overall,
|
| 8 |
-
Overall,
|
| 9 |
-
Overall,
|
| 10 |
-
Overall,
|
| 11 |
-
Overall,
|
| 12 |
-
Overall,TabPFN-TS,
|
| 13 |
-
Overall,ETS,
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,Chronos-2,2.065558263872329,8.078349372982936,1,12,12,1.0
|
| 3 |
+
Overall,TiRex,1.4926087353534092,7.484164884076894,2,12,12,1.0
|
| 4 |
+
Overall,Moirai-2.0,2.351068357392339,13.58735183474385,3,12,12,1.0
|
| 5 |
+
Overall,Chronos-Bolt,2.1577745707033182,17.43856711411005,4,12,12,1.0
|
| 6 |
+
Overall,Sundial,3.651040125169862,11.56430357302543,5,12,12,1.0
|
| 7 |
+
Overall,TimesFM-2.5,1.5483254674369333,5.4109308157288885,6,12,12,1.0
|
| 8 |
+
Overall,Seasonal-Naive,1.0,1.0,7,12,12,1.0
|
| 9 |
+
Overall,Toto-1.0,91.56806858441708,29.269684986041874,8,12,12,1.0
|
| 10 |
+
Overall,Moving-Average,8.672324760684338,26.309722235047634,9,12,12,1.0
|
| 11 |
+
Overall,ARIMA,11.018966413107494,26.917487507636114,10,12,12,1.0
|
| 12 |
+
Overall,TabPFN-TS,2.0755396379508495,4.962592941445592,11,12,12,1.0
|
| 13 |
+
Overall,ETS,17.54792352824851,37.823552690782506,12,12,12,1.0
|
results/dataset_properties.csv
CHANGED
|
@@ -6,7 +6,6 @@ data_gov_sg_singapore_taxi_availability_available_taxi_count,Transportation,5min
|
|
| 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
|
| 12 |
usgs_earthquake_all_week_hourly_earthquake_count,Hazards,1h,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 |
open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
|
| 10 |
open_meteo_shanghai_hourly_temperature_2m,Weather,1h,1
|
| 11 |
usgs_earthquake_all_week_hourly_earthquake_count,Hazards,1h,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-
|
| 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": {
|
|
@@ -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-
|
| 23 |
-
"resolved_tasks": [
|
| 24 |
-
{
|
| 25 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 26 |
-
"task_id": "future-bbad8080b63351089494",
|
| 27 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 28 |
-
"resolved_at": "2026-07-29T16:56:27.442744+00:00",
|
| 29 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 42 |
-
"resolved_tasks": [
|
| 43 |
-
{
|
| 44 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 45 |
-
"task_id": "future-bbad8080b63351089494",
|
| 46 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 47 |
-
"resolved_at": "2026-07-29T16:56:27.844829+00:00",
|
| 48 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 61 |
-
"resolved_tasks": [
|
| 62 |
-
{
|
| 63 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 64 |
-
"task_id": "future-bbad8080b63351089494",
|
| 65 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 66 |
-
"resolved_at": "2026-07-29T16:56:27.774121+00:00",
|
| 67 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 80 |
-
"resolved_tasks": [
|
| 81 |
-
{
|
| 82 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 83 |
-
"task_id": "future-bbad8080b63351089494",
|
| 84 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 85 |
-
"resolved_at": "2026-07-29T16:56:27.887128+00:00",
|
| 86 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 99 |
-
"resolved_tasks": [
|
| 100 |
-
{
|
| 101 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 102 |
-
"task_id": "future-bbad8080b63351089494",
|
| 103 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 104 |
-
"resolved_at": "2026-07-29T16:56:27.579151+00:00",
|
| 105 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 118 |
-
"resolved_tasks": [
|
| 119 |
-
{
|
| 120 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 121 |
-
"task_id": "future-bbad8080b63351089494",
|
| 122 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 123 |
-
"resolved_at": "2026-07-29T16:56:27.481123+00:00",
|
| 124 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 137 |
-
"resolved_tasks": [
|
| 138 |
-
{
|
| 139 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 140 |
-
"task_id": "future-bbad8080b63351089494",
|
| 141 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 142 |
-
"resolved_at": "2026-07-29T16:56:27.750179+00:00",
|
| 143 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 156 |
-
"resolved_tasks": [
|
| 157 |
-
{
|
| 158 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 159 |
-
"task_id": "future-bbad8080b63351089494",
|
| 160 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 161 |
-
"resolved_at": "2026-07-29T16:56:27.706156+00:00",
|
| 162 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 175 |
-
"resolved_tasks": [
|
| 176 |
-
{
|
| 177 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 178 |
-
"task_id": "future-bbad8080b63351089494",
|
| 179 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 180 |
-
"resolved_at": "2026-07-29T16:56:27.629291+00:00",
|
| 181 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 194 |
-
"resolved_tasks": [
|
| 195 |
-
{
|
| 196 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 197 |
-
"task_id": "future-bbad8080b63351089494",
|
| 198 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 199 |
-
"resolved_at": "2026-07-29T16:56:27.534586+00:00",
|
| 200 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 213 |
-
"resolved_tasks": [
|
| 214 |
-
{
|
| 215 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 216 |
-
"task_id": "future-bbad8080b63351089494",
|
| 217 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 218 |
-
"resolved_at": "2026-07-29T16:56:27.378146+00:00",
|
| 219 |
-
"target_end": "2026-07-28T13:05:00+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-
|
| 232 |
-
"resolved_tasks": [
|
| 233 |
-
{
|
| 234 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 235 |
-
"task_id": "future-bbad8080b63351089494",
|
| 236 |
-
"issued_at": "2026-07-29T14:20:28.516607+00:00",
|
| 237 |
-
"resolved_at": "2026-07-29T16:56:27.675169+00:00",
|
| 238 |
-
"target_end": "2026-07-28T13:05:00+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": "2026-07-29T18:24:07.639994+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": "2026-07-29T20:41:32.511348+00:00",
|
| 6 |
+
"finished_at": "2026-07-29T21:49:44.737784+00:00",
|
| 7 |
"data_source": "ts_bench",
|
| 8 |
"data_config": "configs/datasets/ts_bench.yaml",
|
| 9 |
+
"task_count": 3,
|
| 10 |
+
"issued_tasks": 0,
|
| 11 |
+
"issued_forecasts": 6,
|
| 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": "2026-07-29T21:49:40.252355+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": "2026-07-29T21:49:40.252393+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": "2026-07-29T21:49:40.252397+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": "2026-07-29T21:49:40.252399+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": "2026-07-29T21:49:40.252403+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": "2026-07-29T21:49:40.252409+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": "2026-07-29T21:49:40.252412+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": "2026-07-29T21:49:40.252415+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": "2026-07-29T21:49:40.252418+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": "2026-07-29T21:49:40.252420+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": "2026-07-29T21:49:40.252423+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": "2026-07-29T21:49:40.252425+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 |
}
|