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 -2
- 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": "2026-07-28T02:
|
| 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": "2026-07-28T02:41:52.410327+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": "2026-07-28T02:
|
| 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": "2026-07-28T02:41:50.347078+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,Sundial,0.48228798448389376,0.5634499277519537,1,2,2,1.0
|
| 39 |
Ocean,Moving-Average,0.5615559138192499,0.7295325981764587,2,2,2,1.0
|
| 40 |
Ocean,TiRex,0.6069904501867864,0.6895789871096983,3,2,2,1.0
|
|
|
|
| 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,Moving-Average,0.7652594641159696,1.057507146740559,2,1,1,1.0
|
| 40 |
+
Hydrology,Moirai-2.0,1.282185062935625,1.1593661273750293,3,1,1,1.0
|
| 41 |
+
Hydrology,TiRex,1.7601434797977764,1.2181115345220714,4,1,1,1.0
|
| 42 |
+
Hydrology,Chronos-2,1.669749502744596,1.230016084276731,5,1,1,1.0
|
| 43 |
+
Hydrology,Chronos-Bolt,1.502772356186331,1.345630170545535,6,1,1,1.0
|
| 44 |
+
Hydrology,Sundial,1.3149358626625043,1.3578813294245928,7,1,1,1.0
|
| 45 |
+
Hydrology,Toto-1.0,1.3933078304239097,1.3656846750610254,8,1,1,1.0
|
| 46 |
+
Hydrology,TimesFM-2.5,1.822857718065862,1.5697987766413375,9,1,1,1.0
|
| 47 |
+
Hydrology,TabPFN-TS,1.7823948120487276,1.6723544394535688,10,1,1,1.0
|
| 48 |
+
Hydrology,ETS,2.3101830377998778,1.8643116894683234,11,1,1,1.0
|
| 49 |
+
Hydrology,ARIMA,1.7969075767873166,2.166778271475671,12,1,1,1.0
|
| 50 |
Ocean,Sundial,0.48228798448389376,0.5634499277519537,1,2,2,1.0
|
| 51 |
Ocean,Moving-Average,0.5615559138192499,0.7295325981764587,2,2,2,1.0
|
| 52 |
Ocean,TiRex,0.6069904501867864,0.6895789871096983,3,2,2,1.0
|
results/aggregates/results_by_frequency.csv
CHANGED
|
@@ -11,6 +11,18 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 11 |
10min,Moirai-2.0,0.770942001251268,0.8004585833278894,10,1,1,1.0
|
| 12 |
10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 13 |
10min,TabPFN-TS,1.3847975089964943,1.244085275075577,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
1D,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
|
| 15 |
1D,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
|
| 16 |
1D,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
|
|
|
|
| 11 |
10min,Moirai-2.0,0.770942001251268,0.8004585833278894,10,1,1,1.0
|
| 12 |
10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
|
| 13 |
10min,TabPFN-TS,1.3847975089964943,1.244085275075577,12,1,1,1.0
|
| 14 |
+
15min,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 15 |
+
15min,Moving-Average,0.7652594641159696,1.057507146740559,2,1,1,1.0
|
| 16 |
+
15min,Moirai-2.0,1.282185062935625,1.1593661273750293,3,1,1,1.0
|
| 17 |
+
15min,TiRex,1.7601434797977764,1.2181115345220714,4,1,1,1.0
|
| 18 |
+
15min,Chronos-2,1.669749502744596,1.230016084276731,5,1,1,1.0
|
| 19 |
+
15min,Chronos-Bolt,1.502772356186331,1.345630170545535,6,1,1,1.0
|
| 20 |
+
15min,Sundial,1.3149358626625043,1.3578813294245928,7,1,1,1.0
|
| 21 |
+
15min,Toto-1.0,1.3933078304239097,1.3656846750610254,8,1,1,1.0
|
| 22 |
+
15min,TimesFM-2.5,1.822857718065862,1.5697987766413375,9,1,1,1.0
|
| 23 |
+
15min,TabPFN-TS,1.7823948120487276,1.6723544394535688,10,1,1,1.0
|
| 24 |
+
15min,ETS,2.3101830377998778,1.8643116894683234,11,1,1,1.0
|
| 25 |
+
15min,ARIMA,1.7969075767873166,2.166778271475671,12,1,1,1.0
|
| 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,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
|
| 24 |
12,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
|
| 25 |
12,Toto-1.0,637193131.9497002,273899848.7647005,12,1,1,1.0
|
| 26 |
-
24,
|
| 27 |
-
24,
|
| 28 |
-
24,
|
| 29 |
-
24,Sundial,
|
| 30 |
-
24,
|
| 31 |
-
24,
|
| 32 |
-
24,
|
| 33 |
-
24,
|
| 34 |
-
24,Moving-Average,1.
|
| 35 |
-
24,TimesFM-2.5,0.
|
| 36 |
-
24,ARIMA,
|
| 37 |
-
24,ETS,
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,TabPFN-TS,1.0,1.0,2,1,1,1.0
|
| 40 |
36,TimesFM-2.5,1.0,1.0,3,1,1,1.0
|
|
|
|
| 23 |
12,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
|
| 24 |
12,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
|
| 25 |
12,Toto-1.0,637193131.9497002,273899848.7647005,12,1,1,1.0
|
| 26 |
+
24,TiRex,0.9527609339183264,0.9605745727706534,1,8,8,1.0
|
| 27 |
+
24,Toto-1.0,3.602323017176498,0.8432406870994948,2,8,8,1.0
|
| 28 |
+
24,Moirai-2.0,1.111084333625263,0.9898177814254066,3,8,8,1.0
|
| 29 |
+
24,Sundial,1.0038603917412252,0.9192080776377297,4,8,8,1.0
|
| 30 |
+
24,Chronos-2,1.1823722520634963,0.9705394339322146,5,8,8,1.0
|
| 31 |
+
24,TabPFN-TS,0.7242476822679981,0.9271751264471223,6,8,8,1.0
|
| 32 |
+
24,Seasonal-Naive,1.0,1.0,7,8,8,1.0
|
| 33 |
+
24,Chronos-Bolt,1.1796942750676118,0.9826233393849123,8,8,8,1.0
|
| 34 |
+
24,Moving-Average,1.6527865810129951,1.3584130189398083,9,8,8,1.0
|
| 35 |
+
24,TimesFM-2.5,0.9727496323823376,1.0581547926205321,10,8,8,1.0
|
| 36 |
+
24,ARIMA,3.66237586472674,2.2529456335212767,11,8,8,1.0
|
| 37 |
+
24,ETS,11.043531905703498,3.6664262832258556,12,8,8,1.0
|
| 38 |
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
36,TabPFN-TS,1.0,1.0,2,1,1,1.0
|
| 40 |
36,TimesFM-2.5,1.0,1.0,3,1,1,1.0
|
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,
|
| 5 |
-
Overall,
|
| 6 |
-
Overall,
|
| 7 |
-
Overall,
|
| 8 |
-
Overall,
|
| 9 |
-
Overall,
|
| 10 |
-
Overall,
|
| 11 |
-
Overall,Chronos-Bolt,1.
|
| 12 |
-
Overall,ARIMA,2.
|
| 13 |
-
Overall,ETS,4.
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,TiRex,0.8467850759145127,2.9341386037216024,1,13,13,1.0
|
| 3 |
+
Overall,Sundial,0.8175293807783756,4.121891527885902,2,13,13,1.0
|
| 4 |
+
Overall,Chronos-2,1.1179255120985898,3.026894947528056,3,13,13,1.0
|
| 5 |
+
Overall,TabPFN-TS,0.7942885160596794,0.9549326555251644,4,13,13,1.0
|
| 6 |
+
Overall,Seasonal-Naive,1.0,1.0,5,13,13,1.0
|
| 7 |
+
Overall,Moving-Average,1.1697139091940043,7.443289823238669,6,13,13,1.0
|
| 8 |
+
Overall,TimesFM-2.5,0.8713163512332048,0.985890128781775,7,13,13,1.0
|
| 9 |
+
Overall,Moirai-2.0,1.0406169006686057,6.736785009938807,8,13,13,1.0
|
| 10 |
+
Overall,Toto-1.0,116.20694791599352,17.175805443016646,9,13,13,1.0
|
| 11 |
+
Overall,Chronos-Bolt,1.1217393107418068,7.278973915414856,10,13,13,1.0
|
| 12 |
+
Overall,ARIMA,2.2549263577188103,10.99486145392376,11,13,13,1.0
|
| 13 |
+
Overall,ETS,4.697689307471637,15.376880140327657,12,13,13,1.0
|
results/dataset_eval_intervals.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"binance_btcusdt_1h_close": 300,
|
| 3 |
"coingecko_bitcoin_7d_price_usd": 300,
|
| 4 |
-
"data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd": 2592000,
|
| 5 |
"data_gov_sg_singapore_rainfall_5min_rainfall_5min_total": 900,
|
| 6 |
"data_gov_sg_singapore_taxi_availability_available_taxi_count": 300,
|
| 7 |
"nasa_power_shanghai_hourly_T2M": 3600,
|
|
@@ -11,6 +10,5 @@
|
|
| 11 |
"open_meteo_shanghai_air_quality_hourly_pm2_5": 3600,
|
| 12 |
"open_meteo_shanghai_hourly_temperature_2m": 3600,
|
| 13 |
"usgs_earthquake_all_week_hourly_earthquake_count": 3600,
|
| 14 |
-
"usgs_potomac_iv_usgs_00060": 900,
|
| 15 |
"wikimedia_time_series_hourly_pageviews": 86400
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"binance_btcusdt_1h_close": 300,
|
| 3 |
"coingecko_bitcoin_7d_price_usd": 300,
|
|
|
|
| 4 |
"data_gov_sg_singapore_rainfall_5min_rainfall_5min_total": 900,
|
| 5 |
"data_gov_sg_singapore_taxi_availability_available_taxi_count": 300,
|
| 6 |
"nasa_power_shanghai_hourly_T2M": 3600,
|
|
|
|
| 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": "2026-07-28T02:
|
| 6 |
-
"finished_at": "2026-07-28T02:
|
| 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": "2026-07-28T02:
|
| 23 |
-
"resolved_tasks": [
|
| 24 |
-
{
|
| 25 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 26 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 27 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 28 |
-
"resolved_at": "2026-07-28T02:30:24.311067+00:00",
|
| 29 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 42 |
-
"resolved_tasks": [
|
| 43 |
-
{
|
| 44 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 45 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 46 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 47 |
-
"resolved_at": "2026-07-28T02:30:24.504223+00:00",
|
| 48 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 61 |
-
"resolved_tasks": [
|
| 62 |
-
{
|
| 63 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 64 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 65 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 66 |
-
"resolved_at": "2026-07-28T02:30:24.486916+00:00",
|
| 67 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 80 |
-
"resolved_tasks": [
|
| 81 |
-
{
|
| 82 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 83 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 84 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 85 |
-
"resolved_at": "2026-07-28T02:30:24.529949+00:00",
|
| 86 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 99 |
-
"resolved_tasks": [
|
| 100 |
-
{
|
| 101 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 102 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 103 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 104 |
-
"resolved_at": "2026-07-28T02:30:24.369988+00:00",
|
| 105 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 118 |
-
"resolved_tasks": [
|
| 119 |
-
{
|
| 120 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 121 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 122 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 123 |
-
"resolved_at": "2026-07-28T02:30:24.328057+00:00",
|
| 124 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 137 |
-
"resolved_tasks": [
|
| 138 |
-
{
|
| 139 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 140 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 141 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 142 |
-
"resolved_at": "2026-07-28T02:30:24.473971+00:00",
|
| 143 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 156 |
-
"resolved_tasks": [
|
| 157 |
-
{
|
| 158 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 159 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 160 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 161 |
-
"resolved_at": "2026-07-28T02:30:24.466980+00:00",
|
| 162 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 175 |
-
"resolved_tasks": [
|
| 176 |
-
{
|
| 177 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 178 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 179 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 180 |
-
"resolved_at": "2026-07-28T02:30:24.424202+00:00",
|
| 181 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 194 |
-
"resolved_tasks": [
|
| 195 |
-
{
|
| 196 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 197 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 198 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 199 |
-
"resolved_at": "2026-07-28T02:30:24.354048+00:00",
|
| 200 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 213 |
-
"resolved_tasks": [
|
| 214 |
-
{
|
| 215 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 216 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 217 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 218 |
-
"resolved_at": "2026-07-28T02:30:24.293201+00:00",
|
| 219 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:
|
| 232 |
-
"resolved_tasks": [
|
| 233 |
-
{
|
| 234 |
-
"dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
|
| 235 |
-
"task_id": "future-139a65bc2c084866b2d3",
|
| 236 |
-
"issued_at": "2026-07-28T01:37:12.611331+00:00",
|
| 237 |
-
"resolved_at": "2026-07-28T02:30:24.443935+00:00",
|
| 238 |
-
"target_end": "2026-07-26T16:35:00+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": "2026-07-28T02:33:43.550632+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": "2026-07-28T02:41:42.662307+00:00",
|
| 6 |
+
"finished_at": "2026-07-28T02:41:52.421209+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 |
"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": "2026-07-28T02:41:47.734752+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": "2026-07-28T02:41:47.734775+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": "2026-07-28T02:41:47.734779+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": "2026-07-28T02:41:47.734782+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": "2026-07-28T02:41:47.734785+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": "2026-07-28T02:41:47.734788+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": "2026-07-28T02:41:47.734791+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": "2026-07-28T02:41:47.734794+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": "2026-07-28T02:41:47.734796+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": "2026-07-28T02:41:47.734797+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": "2026-07-28T02:41:47.734800+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": "2026-07-28T02:41:47.734804+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 |
}
|