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 +0 -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": "2026-07-29T07:01:43.819196+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": "2026-07-29T07:01:41.776971+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,Toto-1.0,
|
| 3 |
-
Climate,
|
| 4 |
-
Climate,
|
| 5 |
-
Climate,Chronos-2,
|
| 6 |
-
Climate,
|
| 7 |
-
Climate,TabPFN-TS,
|
| 8 |
-
Climate,
|
| 9 |
-
Climate,
|
| 10 |
-
Climate,
|
| 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,Toto-1.0,2.10788408676814,0.7444982286752517,1,4,4,1.0
|
| 3 |
+
Climate,Moirai-2.0,0.26139857175176046,0.7987449648560268,2,4,4,1.0
|
| 4 |
+
Climate,Seasonal-Naive,1.0,1.0,3,4,4,1.0
|
| 5 |
+
Climate,Chronos-2,0.3511052230278436,0.8406087624335221,4,4,4,1.0
|
| 6 |
+
Climate,Chronos-Bolt,0.4736642972936194,0.8759108166985273,5,4,4,1.0
|
| 7 |
+
Climate,TabPFN-TS,0.5618684872816783,0.8160147919184494,6,4,4,1.0
|
| 8 |
+
Climate,Sundial,0.8781204086033556,0.8457655435196634,7,4,4,1.0
|
| 9 |
+
Climate,TiRex,0.25645820380075013,0.8748904165726592,8,4,4,1.0
|
| 10 |
+
Climate,TimesFM-2.5,0.48373052394112653,0.9590866974818474,9,4,4,1.0
|
| 11 |
+
Climate,ARIMA,4.800690937631407,2.1894644656096474,10,4,4,1.0
|
| 12 |
+
Climate,Moving-Average,4.164784946934952,2.283168490719553,11,4,4,1.0
|
| 13 |
+
Climate,ETS,18.087801508734604,4.849243130270303,12,4,4,1.0
|
| 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
|
@@ -59,18 +59,18 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 59 |
1mo,Moving-Average,0.9249973049108767,0.8887079460534169,10,1,1,1.0
|
| 60 |
1mo,TabPFN-TS,0.8352213750339312,0.8925810519947165,11,1,1,1.0
|
| 61 |
1mo,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
| 62 |
-
5min,Seasonal-Naive,1.0,1.0,1,
|
| 63 |
-
5min,TabPFN-TS,
|
| 64 |
-
5min,
|
| 65 |
-
5min,
|
| 66 |
-
5min,
|
| 67 |
-
5min,
|
| 68 |
-
5min,
|
| 69 |
-
5min,
|
| 70 |
-
5min,
|
| 71 |
-
5min,
|
| 72 |
-
5min,
|
| 73 |
-
5min,
|
| 74 |
6min,Chronos-2,0.004065646210503269,0.18017789189149058,1,1,1,1.0
|
| 75 |
6min,TimesFM-2.5,0.11897587453818394,0.30185471840281924,2,1,1,1.0
|
| 76 |
6min,Moirai-2.0,0.15529767214638196,0.43989214409973665,3,1,1,1.0
|
|
|
|
| 59 |
1mo,Moving-Average,0.9249973049108767,0.8887079460534169,10,1,1,1.0
|
| 60 |
1mo,TabPFN-TS,0.8352213750339312,0.8925810519947165,11,1,1,1.0
|
| 61 |
1mo,Seasonal-Naive,1.0,1.0,12,1,1,1.0
|
| 62 |
+
5min,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 63 |
+
5min,TabPFN-TS,1.0,1.0,2,1,1,1.0
|
| 64 |
+
5min,TimesFM-2.5,1.0,1.0,3,1,1,1.0
|
| 65 |
+
5min,TiRex,1.0,1397.7486927145103,4,1,1,1.0
|
| 66 |
+
5min,Chronos-2,1.0,2356.162747109683,5,1,1,1.0
|
| 67 |
+
5min,Sundial,1.0,20066.91263321144,6,1,1,1.0
|
| 68 |
+
5min,ARIMA,1.0,250217.138218906,7,1,1,1.0
|
| 69 |
+
5min,ETS,1.0,250217.138218906,8,1,1,1.0
|
| 70 |
+
5min,Moving-Average,1.0,250217.138218906,9,1,1,1.0
|
| 71 |
+
5min,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
|
| 72 |
+
5min,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
|
| 73 |
+
5min,Toto-1.0,94346114916.68228,269839906.6073004,12,1,1,1.0
|
| 74 |
6min,Chronos-2,0.004065646210503269,0.18017789189149058,1,1,1,1.0
|
| 75 |
6min,TimesFM-2.5,0.11897587453818394,0.30185471840281924,2,1,1,1.0
|
| 76 |
6min,Moirai-2.0,0.15529767214638196,0.43989214409973665,3,1,1,1.0
|
results/aggregates/results_by_prediction_length.csv
CHANGED
|
@@ -35,18 +35,6 @@ prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
| 35 |
24,Seasonal-Naive,1.0,1.0,10,7,7,1.0
|
| 36 |
24,ARIMA,2.0280756005522766,1.7363039984998985,11,7,7,1.0
|
| 37 |
24,ETS,5.524818260678021,2.5285715380243023,12,7,7,1.0
|
| 38 |
-
36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 39 |
-
36,Moving-Average,4197928397.0869946,1.0,2,1,1,1.0
|
| 40 |
-
36,ETS,4197931034.7064004,323190.1295744973,3,1,1,1.0
|
| 41 |
-
36,TiRex,140549.1442739884,399363455.5769006,4,1,1,1.0
|
| 42 |
-
36,TabPFN-TS,1113526.5836049833,1012151178.0338014,5,1,1,1.0
|
| 43 |
-
36,Chronos-2,2450954.1494589695,1355359885.5146005,6,1,1,1.0
|
| 44 |
-
36,Toto-1.0,794334807831.0154,1399064340.2187998,7,1,1,1.0
|
| 45 |
-
36,Moirai-2.0,4684138.793773595,1496697066.0160985,8,1,1,1.0
|
| 46 |
-
36,TimesFM-2.5,144920.23263968507,2087606835.7367973,9,1,1,1.0
|
| 47 |
-
36,Chronos-Bolt,18035366.95448861,4826573036.809504,10,1,1,1.0
|
| 48 |
-
36,Sundial,937568668.1934007,6509405314.10231,11,1,1,1.0
|
| 49 |
-
36,ARIMA,8870345887.065712,39254117859.681656,12,1,1,1.0
|
| 50 |
60,Chronos-2,0.004065646210503269,0.18017789189149058,1,1,1,1.0
|
| 51 |
60,TimesFM-2.5,0.11897587453818394,0.30185471840281924,2,1,1,1.0
|
| 52 |
60,Moirai-2.0,0.15529767214638196,0.43989214409973665,3,1,1,1.0
|
|
|
|
| 35 |
24,Seasonal-Naive,1.0,1.0,10,7,7,1.0
|
| 36 |
24,ARIMA,2.0280756005522766,1.7363039984998985,11,7,7,1.0
|
| 37 |
24,ETS,5.524818260678021,2.5285715380243023,12,7,7,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
60,Chronos-2,0.004065646210503269,0.18017789189149058,1,1,1,1.0
|
| 39 |
60,TimesFM-2.5,0.11897587453818394,0.30185471840281924,2,1,1,1.0
|
| 40 |
60,Moirai-2.0,0.15529767214638196,0.43989214409973665,3,1,1,1.0
|
results/aggregates/results_overall.csv
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
Overall,Chronos-2,
|
| 3 |
-
Overall,Moirai-2.0,
|
| 4 |
-
Overall,
|
| 5 |
-
Overall,
|
| 6 |
-
Overall,Chronos-Bolt,
|
| 7 |
-
Overall,TimesFM-2.5,
|
| 8 |
-
Overall,Moving-Average,
|
| 9 |
-
Overall,Toto-1.0,
|
| 10 |
-
Overall,
|
| 11 |
-
Overall,
|
| 12 |
-
Overall,
|
| 13 |
-
Overall,ETS,
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,Chronos-2,0.31894628649553414,1.2380257253097502,1,12,12,1.0
|
| 3 |
+
Overall,Moirai-2.0,0.39855882338778986,2.0399620196948294,2,12,12,1.0
|
| 4 |
+
Overall,Sundial,0.6421113129877262,1.609069703557794,3,12,12,1.0
|
| 5 |
+
Overall,TiRex,0.4268235684375872,1.362098447165561,4,12,12,1.0
|
| 6 |
+
Overall,Chronos-Bolt,0.6058989372918245,2.799009948857091,5,12,12,1.0
|
| 7 |
+
Overall,TimesFM-2.5,0.4001461782119439,0.6896858974822001,6,12,12,1.0
|
| 8 |
+
Overall,Moving-Average,1.2956781682236393,3.1533236653487573,7,12,12,1.0
|
| 9 |
+
Overall,Toto-1.0,11.262380852733084,3.976301727540666,8,12,12,1.0
|
| 10 |
+
Overall,ARIMA,1.407549863732539,3.651621611113589,9,12,12,1.0
|
| 11 |
+
Overall,Seasonal-Naive,1.0,1.0,10,12,12,1.0
|
| 12 |
+
Overall,TabPFN-TS,0.8057669872813471,0.9215876388113726,11,12,12,1.0
|
| 13 |
+
Overall,ETS,2.512336742921387,4.507459502855504,12,12,12,1.0
|
results/dataset_properties.csv
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
dataset,domain,frequency,num_variates
|
| 2 |
binance_btcusdt_1h_close,Finance,1h,1
|
| 3 |
data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd,Finance,M,1
|
| 4 |
-
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
|
|
|
|
| 1 |
dataset,domain,frequency,num_variates
|
| 2 |
binance_btcusdt_1h_close,Finance,1h,1
|
| 3 |
data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd,Finance,M,1
|
|
|
|
| 4 |
data_gov_sg_singapore_taxi_availability_available_taxi_count,Transportation,5min,1
|
| 5 |
nasa_power_shanghai_hourly_t2m,Weather,1h,1
|
| 6 |
noaa_coops_sf_water_level_water_level,Ocean,6min,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-f62bf1c75151e228c6d4",
|
| 27 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 28 |
-
"resolved_at": "2026-07-29T06:46:48.270570+00:00",
|
| 29 |
-
"target_end": "2026-07-27T20:50:00+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-f62bf1c75151e228c6d4",
|
| 46 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 47 |
-
"resolved_at": "2026-07-29T06:46:48.567951+00:00",
|
| 48 |
-
"target_end": "2026-07-27T20:50:00+00:00",
|
| 49 |
-
"prediction_length": 12,
|
| 50 |
-
"metric_version": "livehouse-canonical-v1"
|
| 51 |
-
}
|
| 52 |
-
]
|
| 53 |
},
|
| 54 |
"TimesFM-2.5": {
|
| 55 |
"model": "TimesFM-2.5",
|
|
@@ -57,18 +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-f62bf1c75151e228c6d4",
|
| 65 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 66 |
-
"resolved_at": "2026-07-29T06:46:48.520670+00:00",
|
| 67 |
-
"target_end": "2026-07-27T20:50:00+00:00",
|
| 68 |
-
"prediction_length": 12,
|
| 69 |
-
"metric_version": "livehouse-canonical-v1"
|
| 70 |
-
}
|
| 71 |
-
]
|
| 72 |
},
|
| 73 |
"Toto-1.0": {
|
| 74 |
"model": "Toto-1.0",
|
|
@@ -76,18 +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-f62bf1c75151e228c6d4",
|
| 84 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 85 |
-
"resolved_at": "2026-07-29T06:46:48.588538+00:00",
|
| 86 |
-
"target_end": "2026-07-27T20:50:00+00:00",
|
| 87 |
-
"prediction_length": 12,
|
| 88 |
-
"metric_version": "livehouse-canonical-v1"
|
| 89 |
-
}
|
| 90 |
-
]
|
| 91 |
},
|
| 92 |
"Moirai-2.0": {
|
| 93 |
"model": "Moirai-2.0",
|
|
@@ -95,18 +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-f62bf1c75151e228c6d4",
|
| 103 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 104 |
-
"resolved_at": "2026-07-29T06:46:48.385759+00:00",
|
| 105 |
-
"target_end": "2026-07-27T20:50:00+00:00",
|
| 106 |
-
"prediction_length": 12,
|
| 107 |
-
"metric_version": "livehouse-canonical-v1"
|
| 108 |
-
}
|
| 109 |
-
]
|
| 110 |
},
|
| 111 |
"Chronos-Bolt": {
|
| 112 |
"model": "Chronos-Bolt",
|
|
@@ -114,18 +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-f62bf1c75151e228c6d4",
|
| 122 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 123 |
-
"resolved_at": "2026-07-29T06:46:48.315655+00:00",
|
| 124 |
-
"target_end": "2026-07-27T20:50:00+00:00",
|
| 125 |
-
"prediction_length": 12,
|
| 126 |
-
"metric_version": "livehouse-canonical-v1"
|
| 127 |
-
}
|
| 128 |
-
]
|
| 129 |
},
|
| 130 |
"TabPFN-TS": {
|
| 131 |
"model": "TabPFN-TS",
|
|
@@ -133,18 +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-f62bf1c75151e228c6d4",
|
| 141 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 142 |
-
"resolved_at": "2026-07-29T06:46:48.491734+00:00",
|
| 143 |
-
"target_end": "2026-07-27T20:50:00+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-f62bf1c75151e228c6d4",
|
| 160 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 161 |
-
"resolved_at": "2026-07-29T06:46:48.467874+00:00",
|
| 162 |
-
"target_end": "2026-07-27T20:50:00+00:00",
|
| 163 |
-
"prediction_length": 12,
|
| 164 |
-
"metric_version": "livehouse-canonical-v1"
|
| 165 |
-
}
|
| 166 |
-
]
|
| 167 |
},
|
| 168 |
"Moving-Average": {
|
| 169 |
"model": "Moving-Average",
|
|
@@ -171,18 +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-f62bf1c75151e228c6d4",
|
| 179 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 180 |
-
"resolved_at": "2026-07-29T06:46:48.411757+00:00",
|
| 181 |
-
"target_end": "2026-07-27T20:50:00+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-f62bf1c75151e228c6d4",
|
| 198 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 199 |
-
"resolved_at": "2026-07-29T06:46:48.355858+00:00",
|
| 200 |
-
"target_end": "2026-07-27T20:50:00+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-f62bf1c75151e228c6d4",
|
| 217 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 218 |
-
"resolved_at": "2026-07-29T06:46:48.233596+00:00",
|
| 219 |
-
"target_end": "2026-07-27T20:50:00+00:00",
|
| 220 |
-
"prediction_length": 12,
|
| 221 |
-
"metric_version": "livehouse-canonical-v1"
|
| 222 |
-
}
|
| 223 |
-
]
|
| 224 |
},
|
| 225 |
"Seasonal-Naive": {
|
| 226 |
"model": "Seasonal-Naive",
|
|
@@ -228,18 +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-f62bf1c75151e228c6d4",
|
| 236 |
-
"issued_at": "2026-07-29T04:50:10.589491+00:00",
|
| 237 |
-
"resolved_at": "2026-07-29T06:46:48.433558+00:00",
|
| 238 |
-
"target_end": "2026-07-27T20:50:00+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": "2026-07-29T06:52:20.888016+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": "2026-07-29T07:01:35.096139+00:00",
|
| 6 |
+
"finished_at": "2026-07-29T07:01:43.830715+00:00",
|
| 7 |
"data_source": "ts_bench",
|
| 8 |
"data_config": "configs/datasets/ts_bench.yaml",
|
| 9 |
+
"task_count": 2,
|
| 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": "2026-07-29T07:01:39.730685+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": "2026-07-29T07:01:39.730708+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": "2026-07-29T07:01:39.730711+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": "2026-07-29T07:01:39.730714+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": "2026-07-29T07:01:39.730716+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": "2026-07-29T07:01:39.730718+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": "2026-07-29T07:01:39.730721+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": "2026-07-29T07:01:39.730723+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": "2026-07-29T07:01:39.730725+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": "2026-07-29T07:01:39.730727+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": "2026-07-29T07:01:39.730730+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": "2026-07-29T07:01:39.730732+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 |
}
|