ziyuzhou02 commited on
Commit
6b9809e
·
verified ·
1 Parent(s): 48fc8c4

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-27T07:15:27.083813+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",
 
1
  {
2
+ "generated_at": "2026-07-27T07:27:54.952704+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": "2026-07-27T07:15:24.942319+00:00",
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": 12,
14
  "num_models": 12,
15
  "num_rows_missing_prediction_length": 0
16
  }
 
1
  {
2
+ "generated_at": "2026-07-27T07:27:52.940168+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,Moving-Average,0.6885555599162482,0.7882638185220112,1,2,2,1.0
39
  Ocean,Sundial,1.0100384161323002,0.9753941694223817,2,2,2,1.0
40
  Ocean,TimesFM-2.5,0.6685946883150999,0.7997804319007484,3,2,2,1.0
 
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,Moirai-2.0,1.0,1.1811008163011596,2,1,1,1.0
40
+ Hydrology,ARIMA,1.000000000936299,1.18110235783726,3,1,1,1.0
41
+ Hydrology,ETS,1.000000000936299,1.18110235783726,4,1,1,1.0
42
+ Hydrology,Moving-Average,1.000000000936299,1.18110235783726,5,1,1,1.0
43
+ Hydrology,Chronos-2,1.0,1.1811023622047234,6,1,1,1.0
44
+ Hydrology,Chronos-Bolt,1.0,1.1811023622047234,7,1,1,1.0
45
+ Hydrology,Sundial,1.0,1.1811023622047234,8,1,1,1.0
46
+ Hydrology,TabPFN-TS,1.0,1.1811023622047234,9,1,1,1.0
47
+ Hydrology,TimesFM-2.5,1.0,1.1811023622047234,10,1,1,1.0
48
+ Hydrology,Toto-1.0,1.7839556631798548,1.3622767704574028,11,1,1,1.0
49
+ Hydrology,TiRex,0.9568451217122376,1.4505235406670343,12,1,1,1.0
50
  Ocean,Moving-Average,0.6885555599162482,0.7882638185220112,1,2,2,1.0
51
  Ocean,Sundial,1.0100384161323002,0.9753941694223817,2,2,2,1.0
52
  Ocean,TimesFM-2.5,0.6685946883150999,0.7997804319007484,3,2,2,1.0
results/aggregates/results_by_frequency.csv CHANGED
@@ -11,6 +11,18 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
11
  10min,Chronos-Bolt,1.0019529557526288,0.9863010922397192,10,1,1,1.0
12
  10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
13
  10min,Chronos-2,1.4062990275163183,1.0749886941936895,12,1,1,1.0
 
 
 
 
 
 
 
 
 
 
 
 
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,Chronos-Bolt,1.0019529557526288,0.9863010922397192,10,1,1,1.0
12
  10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
13
  10min,Chronos-2,1.4062990275163183,1.0749886941936895,12,1,1,1.0
14
+ 15min,Seasonal-Naive,1.0,1.0,1,1,1,1.0
15
+ 15min,Moirai-2.0,1.0,1.1811008163011596,2,1,1,1.0
16
+ 15min,ARIMA,1.000000000936299,1.18110235783726,3,1,1,1.0
17
+ 15min,ETS,1.000000000936299,1.18110235783726,4,1,1,1.0
18
+ 15min,Moving-Average,1.000000000936299,1.18110235783726,5,1,1,1.0
19
+ 15min,Chronos-2,1.0,1.1811023622047234,6,1,1,1.0
20
+ 15min,Chronos-Bolt,1.0,1.1811023622047234,7,1,1,1.0
21
+ 15min,Sundial,1.0,1.1811023622047234,8,1,1,1.0
22
+ 15min,TabPFN-TS,1.0,1.1811023622047234,9,1,1,1.0
23
+ 15min,TimesFM-2.5,1.0,1.1811023622047234,10,1,1,1.0
24
+ 15min,Toto-1.0,1.7839556631798548,1.3622767704574028,11,1,1,1.0
25
+ 15min,TiRex,0.9568451217122376,1.4505235406670343,12,1,1,1.0
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,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
24
  12,Toto-1.0,1010230.0309882049,13352.925178249696,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
- 24,TiRex,0.7610996943071011,0.878746331824924,1,6,6,1.0
27
- 24,Toto-1.0,3.7496443706833267,0.8493092732352021,2,6,6,1.0
28
- 24,Chronos-2,1.014246865952099,0.9083287947663047,3,6,6,1.0
29
- 24,Seasonal-Naive,1.0,1.0,4,6,6,1.0
30
- 24,Moirai-2.0,1.2211495654602278,0.9979878400623481,5,6,6,1.0
31
- 24,TabPFN-TS,0.7569397375884535,0.926257234094127,6,6,6,1.0
32
- 24,Sundial,1.3657000431154327,0.9576090002677531,7,6,6,1.0
33
- 24,Chronos-Bolt,1.159369986330377,0.9368498734192843,8,6,6,1.0
34
- 24,TimesFM-2.5,0.905722114763785,1.00979852986364,9,6,6,1.0
35
- 24,ARIMA,5.5976242951061925,2.579896730748346,10,6,6,1.0
36
- 24,Moving-Average,3.4357064155293853,1.9348925056984916,11,6,6,1.0
37
- 24,ETS,22.757191857667504,5.205578498615606,12,6,6,1.0
38
  36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
39
  36,Moving-Average,3735435890.1223984,1.0,2,1,1,1.0
40
  36,ETS,3735439850.1733017,454621.7794134911,3,1,1,1.0
 
23
  12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
24
  12,Toto-1.0,1010230.0309882049,13352.925178249696,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
+ 24,TiRex,0.7863964815415329,0.9439695608862385,1,7,7,1.0
27
+ 24,Seasonal-Naive,1.0,1.0,2,7,7,1.0
28
+ 24,Moirai-2.0,1.1867884414932584,1.022296617798916,3,7,7,1.0
29
+ 24,Toto-1.0,3.37212375775342,0.9086153682008863,4,7,7,1.0
30
+ 24,Chronos-2,1.0121992393929897,0.9430509286507205,5,7,7,1.0
31
+ 24,TabPFN-TS,0.7876590398010317,0.9589832700406598,6,7,7,1.0
32
+ 24,Sundial,1.3062275772015808,0.9867392589565129,7,7,7,1.0
33
+ 24,Chronos-Bolt,1.1351348942591646,0.9683758186291227,8,7,7,1.0
34
+ 24,TimesFM-2.5,0.9186256070061112,1.0326581173710205,9,7,7,1.0
35
+ 24,ARIMA,4.376692834011164,2.3074313100174684,10,7,7,1.0
36
+ 24,Moving-Average,2.880330512406768,1.803153320337502,11,7,7,1.0
37
+ 24,ETS,14.562789605162186,4.211560817547539,12,7,7,1.0
38
  36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
39
  36,Moving-Average,3735435890.1223984,1.0,2,1,1,1.0
40
  36,ETS,3735439850.1733017,454621.7794134911,3,1,1,1.0
results/aggregates/results_overall.csv CHANGED
@@ -1,13 +1,13 @@
1
  overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
- Overall,TiRex,2.3256481223355054,8.988959934799304,1,12,12,1.0
3
- Overall,Moirai-2.0,3.249534489510895,15.115560638970955,2,12,12,1.0
4
- Overall,Toto-1.0,197.61794269477892,24.55859641016325,3,12,12,1.0
5
- Overall,Chronos-2,3.380501641493073,10.046228544621957,4,12,12,1.0
6
- Overall,Sundial,7.157696111858197,15.088395546576766,5,12,12,1.0
7
- Overall,Seasonal-Naive,1.0,1.0,6,12,12,1.0
8
- Overall,ARIMA,13.399608450650895,18.951859903510005,7,12,12,1.0
9
- Overall,Moving-Average,10.137112660148707,3.547561920447639,8,12,12,1.0
10
- Overall,TimesFM-2.5,1.9120705136515608,5.747320300810148,9,12,12,1.0
11
- Overall,TabPFN-TS,3.943220550423178,5.949859710345681,10,12,12,1.0
12
- Overall,Chronos-Bolt,4.051225685192338,21.209505170259735,11,12,12,1.0
13
- Overall,ETS,28.38333752828785,18.114662924855367,12,12,12,1.0
 
1
  overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
+ Overall,TiRex,2.1720738801651374,7.812178590336612,1,13,13,1.0
3
+ Overall,Moirai-2.0,2.9679070336654596,12.423954520640057,2,13,13,1.0
4
+ Overall,Seasonal-Naive,1.0,1.0,3,13,13,1.0
5
+ Overall,Chronos-2,3.078153642699101,8.520919760891848,4,13,13,1.0
6
+ Overall,Toto-1.0,137.5819878731826,19.660425464030794,5,13,13,1.0
7
+ Overall,Sundial,6.152072814853696,12.403344026813425,6,13,13,1.0
8
+ Overall,ARIMA,10.974701460077151,15.308460096474754,7,13,13,1.0
9
+ Overall,Moving-Average,8.482741880163895,3.2597797515273625,8,13,13,1.0
10
+ Overall,TimesFM-2.5,1.819071450005093,5.088684972163042,9,13,13,1.0
11
+ Overall,TabPFN-TS,3.548267643446615,5.253997540906708,10,13,13,1.0
12
+ Overall,Chronos-Bolt,3.63788544470257,16.984403766515026,11,13,13,1.0
13
+ Overall,ETS,21.94266381738573,14.68315145941575,12,13,13,1.0
results/dataset_eval_intervals.json CHANGED
@@ -10,6 +10,5 @@
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
- "usgs_potomac_iv_usgs_00060": 900,
14
  "wikimedia_time_series_hourly_pageviews": 86400
15
  }
 
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
@@ -2,11 +2,11 @@
2
  "status": "ok",
3
  "evaluation_protocol": "issue-now-score-later",
4
  "metric_version": "livehouse-canonical-v1",
5
- "started_at": "2026-07-27T07:15:20.315946+00:00",
6
- "finished_at": "2026-07-27T07:15:27.096039+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,
@@ -19,7 +19,7 @@
19
  "admitted_at": "2026-06-01T00:00:00Z",
20
  "evaluation_protocol": "issue-now-score-later",
21
  "metric_version": "livehouse-canonical-v1",
22
- "evaluated_at": "2026-07-27T07:15:23.422107+00:00",
23
  "resolved_tasks": []
24
  },
25
  "TiRex": {
@@ -28,7 +28,7 @@
28
  "admitted_at": "2026-06-01T00:00:00Z",
29
  "evaluation_protocol": "issue-now-score-later",
30
  "metric_version": "livehouse-canonical-v1",
31
- "evaluated_at": "2026-07-27T07:15:23.422116+00:00",
32
  "resolved_tasks": []
33
  },
34
  "TimesFM-2.5": {
@@ -37,7 +37,7 @@
37
  "admitted_at": "2026-06-01T00:00:00Z",
38
  "evaluation_protocol": "issue-now-score-later",
39
  "metric_version": "livehouse-canonical-v1",
40
- "evaluated_at": "2026-07-27T07:15:23.422118+00:00",
41
  "resolved_tasks": []
42
  },
43
  "Toto-1.0": {
@@ -46,7 +46,7 @@
46
  "admitted_at": "2026-06-01T00:00:00Z",
47
  "evaluation_protocol": "issue-now-score-later",
48
  "metric_version": "livehouse-canonical-v1",
49
- "evaluated_at": "2026-07-27T07:15:23.422119+00:00",
50
  "resolved_tasks": []
51
  },
52
  "Moirai-2.0": {
@@ -55,7 +55,7 @@
55
  "admitted_at": "2026-06-01T00:00:00Z",
56
  "evaluation_protocol": "issue-now-score-later",
57
  "metric_version": "livehouse-canonical-v1",
58
- "evaluated_at": "2026-07-27T07:15:23.422120+00:00",
59
  "resolved_tasks": []
60
  },
61
  "Chronos-Bolt": {
@@ -64,7 +64,7 @@
64
  "admitted_at": "2026-06-01T00:00:00Z",
65
  "evaluation_protocol": "issue-now-score-later",
66
  "metric_version": "livehouse-canonical-v1",
67
- "evaluated_at": "2026-07-27T07:15:23.422121+00:00",
68
  "resolved_tasks": []
69
  },
70
  "TabPFN-TS": {
@@ -73,7 +73,7 @@
73
  "admitted_at": "2026-06-01T00:00:00Z",
74
  "evaluation_protocol": "issue-now-score-later",
75
  "metric_version": "livehouse-canonical-v1",
76
- "evaluated_at": "2026-07-27T07:15:23.422122+00:00",
77
  "resolved_tasks": []
78
  },
79
  "Sundial": {
@@ -82,7 +82,7 @@
82
  "admitted_at": "2026-06-01T00:00:00Z",
83
  "evaluation_protocol": "issue-now-score-later",
84
  "metric_version": "livehouse-canonical-v1",
85
- "evaluated_at": "2026-07-27T07:15:23.422123+00:00",
86
  "resolved_tasks": []
87
  },
88
  "Moving-Average": {
@@ -91,7 +91,7 @@
91
  "admitted_at": "2026-06-01T00:00:00Z",
92
  "evaluation_protocol": "issue-now-score-later",
93
  "metric_version": "livehouse-canonical-v1",
94
- "evaluated_at": "2026-07-27T07:15:23.422124+00:00",
95
  "resolved_tasks": []
96
  },
97
  "ETS": {
@@ -100,7 +100,7 @@
100
  "admitted_at": "2026-06-01T00:00:00Z",
101
  "evaluation_protocol": "issue-now-score-later",
102
  "metric_version": "livehouse-canonical-v1",
103
- "evaluated_at": "2026-07-27T07:15:23.422125+00:00",
104
  "resolved_tasks": []
105
  },
106
  "ARIMA": {
@@ -109,7 +109,7 @@
109
  "admitted_at": "2026-06-01T00:00:00Z",
110
  "evaluation_protocol": "issue-now-score-later",
111
  "metric_version": "livehouse-canonical-v1",
112
- "evaluated_at": "2026-07-27T07:15:23.422126+00:00",
113
  "resolved_tasks": []
114
  },
115
  "Seasonal-Naive": {
@@ -118,7 +118,7 @@
118
  "admitted_at": "2026-06-01T00:00:00Z",
119
  "evaluation_protocol": "issue-now-score-later",
120
  "metric_version": "livehouse-canonical-v1",
121
- "evaluated_at": "2026-07-27T07:15:23.422127+00:00",
122
  "resolved_tasks": []
123
  }
124
  },
@@ -142,7 +142,5 @@
142
  "live_overall_30d": "aggregates/live_overall_30d.csv",
143
  "live_metadata": "aggregates/live_metadata.json"
144
  },
145
- "push_status": "ok",
146
- "pushed_at": "2026-07-27T07:16:16.982424+00:00",
147
- "push_detail": "HF Hub API"
148
  }
 
2
  "status": "ok",
3
  "evaluation_protocol": "issue-now-score-later",
4
  "metric_version": "livehouse-canonical-v1",
5
+ "started_at": "2026-07-27T07:27:47.157633+00:00",
6
+ "finished_at": "2026-07-27T07:27:54.964278+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
+ "task_count": 1,
10
  "issued_tasks": 0,
11
  "issued_forecasts": 0,
12
  "resolved_forecasts": 0,
 
19
  "admitted_at": "2026-06-01T00:00:00Z",
20
  "evaluation_protocol": "issue-now-score-later",
21
  "metric_version": "livehouse-canonical-v1",
22
+ "evaluated_at": "2026-07-27T07:27:50.554149+00:00",
23
  "resolved_tasks": []
24
  },
25
  "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": "2026-07-27T07:27:50.554154+00:00",
32
  "resolved_tasks": []
33
  },
34
  "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": "2026-07-27T07:27:50.554155+00:00",
41
  "resolved_tasks": []
42
  },
43
  "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": "2026-07-27T07:27:50.554156+00:00",
50
  "resolved_tasks": []
51
  },
52
  "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": "2026-07-27T07:27:50.554157+00:00",
59
  "resolved_tasks": []
60
  },
61
  "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": "2026-07-27T07:27:50.554158+00:00",
68
  "resolved_tasks": []
69
  },
70
  "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": "2026-07-27T07:27:50.554159+00:00",
77
  "resolved_tasks": []
78
  },
79
  "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": "2026-07-27T07:27:50.554160+00:00",
86
  "resolved_tasks": []
87
  },
88
  "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": "2026-07-27T07:27:50.554161+00:00",
95
  "resolved_tasks": []
96
  },
97
  "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": "2026-07-27T07:27:50.554162+00:00",
104
  "resolved_tasks": []
105
  },
106
  "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": "2026-07-27T07:27:50.554163+00:00",
113
  "resolved_tasks": []
114
  },
115
  "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": "2026-07-27T07:27:50.554164+00:00",
122
  "resolved_tasks": []
123
  }
124
  },
 
142
  "live_overall_30d": "aggregates/live_overall_30d.csv",
143
  "live_metadata": "aggregates/live_metadata.json"
144
  },
145
+ "push_status": "pending"
 
 
146
  }