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 +24 -20
results/aggregates/live_metadata.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"generated_at": "2026-07-29T08:
|
| 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": "2026-07-29T08:38:57.853569+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": "2026-07-29T08:
|
| 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": "2026-07-29T08:38:55.778248+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,Chronos-2,0.9878412392964167,1.0111200784587953,9,1,1,1.0
|
|
| 47 |
Hydrology,TiRex,0.9880750420668056,1.0113745182170464,10,1,1,1.0
|
| 48 |
Hydrology,Chronos-Bolt,0.9959839316857422,1.0129095028376935,11,1,1,1.0
|
| 49 |
Hydrology,ARIMA,0.9850111992171071,1.0608896634781397,12,1,1,1.0
|
| 50 |
-
Ocean,Chronos-2,0.
|
| 51 |
-
Ocean,
|
| 52 |
-
Ocean,
|
| 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,TiRex,0.9880750420668056,1.0113745182170464,10,1,1,1.0
|
| 48 |
Hydrology,Chronos-Bolt,0.9959839316857422,1.0129095028376935,11,1,1,1.0
|
| 49 |
Hydrology,ARIMA,0.9850111992171071,1.0608896634781397,12,1,1,1.0
|
| 50 |
+
Ocean,Chronos-2,0.004065646210503269,0.18017789189149058,1,1,1,1.0
|
| 51 |
+
Ocean,TimesFM-2.5,0.11897587453818394,0.30185471840281924,2,1,1,1.0
|
| 52 |
+
Ocean,Moirai-2.0,0.15529767214638196,0.43989214409973665,3,1,1,1.0
|
| 53 |
+
Ocean,TiRex,0.6376297045685118,0.6707335479358393,4,1,1,1.0
|
| 54 |
+
Ocean,Sundial,0.9959918135802209,0.7833070865839833,5,1,1,1.0
|
| 55 |
+
Ocean,Moving-Average,0.9775155990789853,0.9475054070613252,6,1,1,1.0
|
| 56 |
+
Ocean,Seasonal-Naive,1.0,1.0,7,1,1,1.0
|
| 57 |
+
Ocean,Toto-1.0,1.9088894806295245,1.0227024399756848,8,1,1,1.0
|
| 58 |
+
Ocean,ARIMA,2.540064093386627,1.6083878608681195,9,1,1,1.0
|
| 59 |
+
Ocean,ETS,3.412470602278523,1.8188179208652995,10,1,1,1.0
|
| 60 |
+
Ocean,TabPFN-TS,5.662366765178726,2.4144987331689447,11,1,1,1.0
|
| 61 |
+
Ocean,Chronos-Bolt,8.296209105081665,2.741122381016384,12,1,1,1.0
|
| 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,ETS,0.3666070969635438,0.5570986119712091,1,1,1,1.0
|
| 3 |
-
10min,Chronos-Bolt,0.4310739979655584,0.7382053936764865,2,1,1,1.0
|
| 4 |
-
10min,ARIMA,0.6442444888090875,0.7960045937174731,3,1,1,1.0
|
| 5 |
-
10min,Moving-Average,0.7758094155974984,0.8747522400846098,4,1,1,1.0
|
| 6 |
-
10min,TiRex,1.245456590775428,0.9632472512111627,5,1,1,1.0
|
| 7 |
-
10min,Seasonal-Naive,1.0,1.0,6,1,1,1.0
|
| 8 |
-
10min,Toto-1.0,1.607502148925569,1.0325688583671666,7,1,1,1.0
|
| 9 |
-
10min,Chronos-2,1.384065219501788,1.0800978022511833,8,1,1,1.0
|
| 10 |
-
10min,TimesFM-2.5,1.343885874583737,1.1092521058511466,9,1,1,1.0
|
| 11 |
-
10min,Moirai-2.0,1.8429417027285986,1.1791865151434529,10,1,1,1.0
|
| 12 |
-
10min,Sundial,1.5833101299543884,1.2742717261766512,11,1,1,1.0
|
| 13 |
-
10min,TabPFN-TS,1.5520828724990656,1.3298337127875746,12,1,1,1.0
|
| 14 |
15min,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 15 |
15min,Toto-1.0,0.9943660646221287,1.0009272600088706,2,1,1,1.0
|
| 16 |
15min,ETS,0.9906410276164291,1.0010085634811112,3,1,1,1.0
|
|
|
|
| 1 |
frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
15min,Seasonal-Naive,1.0,1.0,1,1,1,1.0
|
| 3 |
15min,Toto-1.0,0.9943660646221287,1.0009272600088706,2,1,1,1.0
|
| 4 |
15min,ETS,0.9906410276164291,1.0010085634811112,3,1,1,1.0
|
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,ETS,3.412470602278523,1.8188179208652995,10,1,1,1.0
|
| 60 |
60,TabPFN-TS,5.662366765178726,2.4144987331689447,11,1,1,1.0
|
| 61 |
60,Chronos-Bolt,8.296209105081665,2.741122381016384,12,1,1,1.0
|
| 62 |
-
72,ETS,0.3666070969635438,0.5570986119712091,1,1,1,1.0
|
| 63 |
-
72,Chronos-Bolt,0.4310739979655584,0.7382053936764865,2,1,1,1.0
|
| 64 |
-
72,ARIMA,0.6442444888090875,0.7960045937174731,3,1,1,1.0
|
| 65 |
-
72,Moving-Average,0.7758094155974984,0.8747522400846098,4,1,1,1.0
|
| 66 |
-
72,TiRex,1.245456590775428,0.9632472512111627,5,1,1,1.0
|
| 67 |
-
72,Seasonal-Naive,1.0,1.0,6,1,1,1.0
|
| 68 |
-
72,Toto-1.0,1.607502148925569,1.0325688583671666,7,1,1,1.0
|
| 69 |
-
72,Chronos-2,1.384065219501788,1.0800978022511833,8,1,1,1.0
|
| 70 |
-
72,TimesFM-2.5,1.343885874583737,1.1092521058511466,9,1,1,1.0
|
| 71 |
-
72,Moirai-2.0,1.8429417027285986,1.1791865151434529,10,1,1,1.0
|
| 72 |
-
72,Sundial,1.5833101299543884,1.2742717261766512,11,1,1,1.0
|
| 73 |
-
72,TabPFN-TS,1.5520828724990656,1.3298337127875746,12,1,1,1.0
|
|
|
|
| 59 |
60,ETS,3.412470602278523,1.8188179208652995,10,1,1,1.0
|
| 60 |
60,TabPFN-TS,5.662366765178726,2.4144987331689447,11,1,1,1.0
|
| 61 |
60,Chronos-Bolt,8.296209105081665,2.741122381016384,12,1,1,1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/aggregates/results_overall.csv
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
-
Overall,Chronos-2,1.
|
| 3 |
-
Overall,
|
| 4 |
-
Overall,
|
| 5 |
-
Overall,Sundial,3.
|
| 6 |
-
Overall,TimesFM-2.5,1.
|
| 7 |
-
Overall,Toto-1.0,
|
| 8 |
-
Overall,Seasonal-Naive,1.0,1.0,7,
|
| 9 |
-
Overall,Chronos-Bolt,2.
|
| 10 |
-
Overall,Moving-Average,
|
| 11 |
-
Overall,ARIMA,
|
| 12 |
-
Overall,
|
| 13 |
-
Overall,
|
|
|
|
| 1 |
overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
|
| 2 |
+
Overall,Chronos-2,1.211031460396387,7.2875908551911435,1,12,12,1.0
|
| 3 |
+
Overall,Moirai-2.0,1.6905157582194856,12.479728463263214,2,12,12,1.0
|
| 4 |
+
Overall,TiRex,1.1627542822323917,7.095566162007958,3,12,12,1.0
|
| 5 |
+
Overall,Sundial,3.801867511089004,10.863867865059087,4,12,12,1.0
|
| 6 |
+
Overall,TimesFM-2.5,1.1478678899654162,4.260880104494603,5,12,12,1.0
|
| 7 |
+
Overall,Toto-1.0,113.82367285862311,23.535779284371472,6,12,12,1.0
|
| 8 |
+
Overall,Seasonal-Naive,1.0,1.0,7,12,12,1.0
|
| 9 |
+
Overall,Chronos-Bolt,2.7059352878135767,18.99584101515884,8,12,12,1.0
|
| 10 |
+
Overall,Moving-Average,9.402810089605852,3.4589413079363243,9,12,12,1.0
|
| 11 |
+
Overall,ARIMA,10.197473194256876,27.169268191967188,10,12,12,1.0
|
| 12 |
+
Overall,TabPFN-TS,3.00921450895394,5.7702898647453456,11,12,12,1.0
|
| 13 |
+
Overall,ETS,23.961846088404652,16.09414612028139,12,12,12,1.0
|
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": "2026-07-29T08:
|
| 6 |
-
"finished_at": "2026-07-29T08:
|
| 7 |
"data_source": "ts_bench",
|
| 8 |
"data_config": "configs/datasets/ts_bench.yaml",
|
| 9 |
-
"task_count":
|
| 10 |
"issued_tasks": 0,
|
| 11 |
"issued_forecasts": 0,
|
| 12 |
"resolved_forecasts": 0,
|
| 13 |
"pending_tasks": 13,
|
| 14 |
-
"failed_forecasts": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"models": {
|
| 16 |
"Chronos-2": {
|
| 17 |
"model": "Chronos-2",
|
|
@@ -19,7 +25,7 @@
|
|
| 19 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 20 |
"evaluation_protocol": "issue-now-score-later",
|
| 21 |
"metric_version": "livehouse-canonical-v1",
|
| 22 |
-
"evaluated_at": "2026-07-29T08:
|
| 23 |
"resolved_tasks": []
|
| 24 |
},
|
| 25 |
"TiRex": {
|
|
@@ -28,7 +34,7 @@
|
|
| 28 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 29 |
"evaluation_protocol": "issue-now-score-later",
|
| 30 |
"metric_version": "livehouse-canonical-v1",
|
| 31 |
-
"evaluated_at": "2026-07-29T08:
|
| 32 |
"resolved_tasks": []
|
| 33 |
},
|
| 34 |
"TimesFM-2.5": {
|
|
@@ -37,7 +43,7 @@
|
|
| 37 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 38 |
"evaluation_protocol": "issue-now-score-later",
|
| 39 |
"metric_version": "livehouse-canonical-v1",
|
| 40 |
-
"evaluated_at": "2026-07-29T08:
|
| 41 |
"resolved_tasks": []
|
| 42 |
},
|
| 43 |
"Toto-1.0": {
|
|
@@ -46,7 +52,7 @@
|
|
| 46 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 47 |
"evaluation_protocol": "issue-now-score-later",
|
| 48 |
"metric_version": "livehouse-canonical-v1",
|
| 49 |
-
"evaluated_at": "2026-07-29T08:
|
| 50 |
"resolved_tasks": []
|
| 51 |
},
|
| 52 |
"Moirai-2.0": {
|
|
@@ -55,7 +61,7 @@
|
|
| 55 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 56 |
"evaluation_protocol": "issue-now-score-later",
|
| 57 |
"metric_version": "livehouse-canonical-v1",
|
| 58 |
-
"evaluated_at": "2026-07-29T08:
|
| 59 |
"resolved_tasks": []
|
| 60 |
},
|
| 61 |
"Chronos-Bolt": {
|
|
@@ -64,7 +70,7 @@
|
|
| 64 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 65 |
"evaluation_protocol": "issue-now-score-later",
|
| 66 |
"metric_version": "livehouse-canonical-v1",
|
| 67 |
-
"evaluated_at": "2026-07-29T08:
|
| 68 |
"resolved_tasks": []
|
| 69 |
},
|
| 70 |
"TabPFN-TS": {
|
|
@@ -73,7 +79,7 @@
|
|
| 73 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 74 |
"evaluation_protocol": "issue-now-score-later",
|
| 75 |
"metric_version": "livehouse-canonical-v1",
|
| 76 |
-
"evaluated_at": "2026-07-29T08:
|
| 77 |
"resolved_tasks": []
|
| 78 |
},
|
| 79 |
"Sundial": {
|
|
@@ -82,7 +88,7 @@
|
|
| 82 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 83 |
"evaluation_protocol": "issue-now-score-later",
|
| 84 |
"metric_version": "livehouse-canonical-v1",
|
| 85 |
-
"evaluated_at": "2026-07-29T08:
|
| 86 |
"resolved_tasks": []
|
| 87 |
},
|
| 88 |
"Moving-Average": {
|
|
@@ -91,7 +97,7 @@
|
|
| 91 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 92 |
"evaluation_protocol": "issue-now-score-later",
|
| 93 |
"metric_version": "livehouse-canonical-v1",
|
| 94 |
-
"evaluated_at": "2026-07-29T08:
|
| 95 |
"resolved_tasks": []
|
| 96 |
},
|
| 97 |
"ETS": {
|
|
@@ -100,7 +106,7 @@
|
|
| 100 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 101 |
"evaluation_protocol": "issue-now-score-later",
|
| 102 |
"metric_version": "livehouse-canonical-v1",
|
| 103 |
-
"evaluated_at": "2026-07-29T08:
|
| 104 |
"resolved_tasks": []
|
| 105 |
},
|
| 106 |
"ARIMA": {
|
|
@@ -109,7 +115,7 @@
|
|
| 109 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 110 |
"evaluation_protocol": "issue-now-score-later",
|
| 111 |
"metric_version": "livehouse-canonical-v1",
|
| 112 |
-
"evaluated_at": "2026-07-29T08:
|
| 113 |
"resolved_tasks": []
|
| 114 |
},
|
| 115 |
"Seasonal-Naive": {
|
|
@@ -118,7 +124,7 @@
|
|
| 118 |
"admitted_at": "2026-06-01T00:00:00Z",
|
| 119 |
"evaluation_protocol": "issue-now-score-later",
|
| 120 |
"metric_version": "livehouse-canonical-v1",
|
| 121 |
-
"evaluated_at": "2026-07-29T08:
|
| 122 |
"resolved_tasks": []
|
| 123 |
}
|
| 124 |
},
|
|
@@ -142,7 +148,5 @@
|
|
| 142 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 143 |
"live_metadata": "aggregates/live_metadata.json"
|
| 144 |
},
|
| 145 |
-
"push_status": "
|
| 146 |
-
"pushed_at": "2026-07-29T08:27:51.945544+00:00",
|
| 147 |
-
"push_detail": "HF Hub API"
|
| 148 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"status": "partial",
|
| 3 |
"evaluation_protocol": "issue-now-score-later",
|
| 4 |
"metric_version": "livehouse-canonical-v1",
|
| 5 |
+
"started_at": "2026-07-29T08:38:50.545226+00:00",
|
| 6 |
+
"finished_at": "2026-07-29T08:38:57.865550+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": "2026-07-29T08:38:54.276408+00:00",
|
| 29 |
"resolved_tasks": []
|
| 30 |
},
|
| 31 |
"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": "2026-07-29T08:38:54.276415+00:00",
|
| 38 |
"resolved_tasks": []
|
| 39 |
},
|
| 40 |
"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": "2026-07-29T08:38:54.276417+00:00",
|
| 47 |
"resolved_tasks": []
|
| 48 |
},
|
| 49 |
"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": "2026-07-29T08:38:54.276418+00:00",
|
| 56 |
"resolved_tasks": []
|
| 57 |
},
|
| 58 |
"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": "2026-07-29T08:38:54.276419+00:00",
|
| 65 |
"resolved_tasks": []
|
| 66 |
},
|
| 67 |
"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": "2026-07-29T08:38:54.276420+00:00",
|
| 74 |
"resolved_tasks": []
|
| 75 |
},
|
| 76 |
"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": "2026-07-29T08:38:54.276421+00:00",
|
| 83 |
"resolved_tasks": []
|
| 84 |
},
|
| 85 |
"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": "2026-07-29T08:38:54.276421+00:00",
|
| 92 |
"resolved_tasks": []
|
| 93 |
},
|
| 94 |
"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": "2026-07-29T08:38:54.276422+00:00",
|
| 101 |
"resolved_tasks": []
|
| 102 |
},
|
| 103 |
"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": "2026-07-29T08:38:54.276423+00:00",
|
| 110 |
"resolved_tasks": []
|
| 111 |
},
|
| 112 |
"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": "2026-07-29T08:38:54.276424+00:00",
|
| 119 |
"resolved_tasks": []
|
| 120 |
},
|
| 121 |
"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": "2026-07-29T08:38:54.276425+00:00",
|
| 128 |
"resolved_tasks": []
|
| 129 |
}
|
| 130 |
},
|
|
|
|
| 148 |
"live_overall_30d": "aggregates/live_overall_30d.csv",
|
| 149 |
"live_metadata": "aggregates/live_metadata.json"
|
| 150 |
},
|
| 151 |
+
"push_status": "pending"
|
|
|
|
|
|
|
| 152 |
}
|