ziyuzhou02 commited on
Commit
d35dbe9
·
verified ·
1 Parent(s): 837d109

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-28T17:46:14.552914+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": "2026-07-28T17:59:02.793511+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": "2026-07-28T17:46:12.360995+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": 13,
14
  "num_models": 12,
15
  "num_rows_missing_prediction_length": 0
16
  }
 
1
  {
2
+ "generated_at": "2026-07-28T17:59:00.872037+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
@@ -35,18 +35,6 @@ Hazards,Toto-1.0,0.5447067827362504,0.6198857623270299,9,1,1,1.0
35
  Hazards,TimesFM-2.5,0.5159030493533491,0.6552873663892604,10,1,1,1.0
36
  Hazards,TabPFN-TS,0.5234081583087049,0.7154825875538315,11,1,1,1.0
37
  Hazards,Seasonal-Naive,1.0,1.0,12,1,1,1.0
38
- Hydrology,ARIMA,0.9751306749691749,0.38486182748098285,1,1,1,1.0
39
- Hydrology,Moirai-2.0,1.0813692464527007,0.9924021595681446,2,1,1,1.0
40
- Hydrology,Seasonal-Naive,1.0,1.0,3,1,1,1.0
41
- Hydrology,Chronos-2,1.1276077437591416,1.010443151113958,4,1,1,1.0
42
- Hydrology,TiRex,1.127237170726061,1.0311739352853535,5,1,1,1.0
43
- Hydrology,Toto-1.0,1.0790332247777732,1.0470160067587573,6,1,1,1.0
44
- Hydrology,Chronos-Bolt,1.093508711981219,1.082295632689394,7,1,1,1.0
45
- Hydrology,Moving-Average,0.9761363565890064,1.1132157631177908,8,1,1,1.0
46
- Hydrology,ETS,1.0814189920897397,1.17781549355183,9,1,1,1.0
47
- Hydrology,Sundial,0.9824313277425463,1.1871040987080808,10,1,1,1.0
48
- Hydrology,TimesFM-2.5,1.13126434578556,1.255403146176928,11,1,1,1.0
49
- Hydrology,TabPFN-TS,1.130074924317557,1.3225726844593262,12,1,1,1.0
50
  Ocean,TimesFM-2.5,0.03684048004661691,0.20206259110870364,1,2,2,1.0
51
  Ocean,Chronos-2,0.0369650586967402,0.21429367126674892,2,2,2,1.0
52
  Ocean,TiRex,0.06099399090461052,0.2882552025089681,3,2,2,1.0
 
35
  Hazards,TimesFM-2.5,0.5159030493533491,0.6552873663892604,10,1,1,1.0
36
  Hazards,TabPFN-TS,0.5234081583087049,0.7154825875538315,11,1,1,1.0
37
  Hazards,Seasonal-Naive,1.0,1.0,12,1,1,1.0
 
 
 
 
 
 
 
 
 
 
 
 
38
  Ocean,TimesFM-2.5,0.03684048004661691,0.20206259110870364,1,2,2,1.0
39
  Ocean,Chronos-2,0.0369650586967402,0.21429367126674892,2,2,2,1.0
40
  Ocean,TiRex,0.06099399090461052,0.2882552025089681,3,2,2,1.0
results/aggregates/results_by_frequency.csv CHANGED
@@ -11,18 +11,6 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
11
  10min,Moirai-2.0,0.9931170314987676,0.9506171711084153,10,1,1,1.0
12
  10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
13
  10min,TabPFN-TS,1.0965296750513482,1.1700878991909816,12,1,1,1.0
14
- 15min,ARIMA,0.9751306749691749,0.38486182748098285,1,1,1,1.0
15
- 15min,Moirai-2.0,1.0813692464527007,0.9924021595681446,2,1,1,1.0
16
- 15min,Seasonal-Naive,1.0,1.0,3,1,1,1.0
17
- 15min,Chronos-2,1.1276077437591416,1.010443151113958,4,1,1,1.0
18
- 15min,TiRex,1.127237170726061,1.0311739352853535,5,1,1,1.0
19
- 15min,Toto-1.0,1.0790332247777732,1.0470160067587573,6,1,1,1.0
20
- 15min,Chronos-Bolt,1.093508711981219,1.082295632689394,7,1,1,1.0
21
- 15min,Moving-Average,0.9761363565890064,1.1132157631177908,8,1,1,1.0
22
- 15min,ETS,1.0814189920897397,1.17781549355183,9,1,1,1.0
23
- 15min,Sundial,0.9824313277425463,1.1871040987080808,10,1,1,1.0
24
- 15min,TimesFM-2.5,1.13126434578556,1.255403146176928,11,1,1,1.0
25
- 15min,TabPFN-TS,1.130074924317557,1.3225726844593262,12,1,1,1.0
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
 
11
  10min,Moirai-2.0,0.9931170314987676,0.9506171711084153,10,1,1,1.0
12
  10min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
13
  10min,TabPFN-TS,1.0965296750513482,1.1700878991909816,12,1,1,1.0
 
 
 
 
 
 
 
 
 
 
 
 
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
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-1.0,7534.1263954366505,13038.851881781453,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
- 24,Chronos-2,0.44339020476480734,0.7317235055481944,1,7,7,1.0
27
- 24,TiRex,0.4145108564513675,0.7448889973096526,2,7,7,1.0
28
- 24,Chronos-Bolt,0.5681562833990131,0.7490469070437524,3,7,7,1.0
29
- 24,Moirai-2.0,0.4799992195385256,0.775419565634457,4,7,7,1.0
30
- 24,Toto-1.0,1.520374525220479,0.7287828451205441,5,7,7,1.0
31
- 24,Sundial,0.7255009526147621,0.7651853252476193,6,7,7,1.0
32
- 24,ARIMA,1.7038724348964605,1.1269151847404395,7,7,7,1.0
33
- 24,Seasonal-Naive,1.0,1.0,8,7,7,1.0
34
- 24,TabPFN-TS,0.594705587085834,0.803937793274539,9,7,7,1.0
35
- 24,Moving-Average,1.4444563689905403,1.2919521417914248,10,7,7,1.0
36
- 24,TimesFM-2.5,0.5331643601238124,0.8304626910315389,11,7,7,1.0
37
- 24,ETS,3.6175474085585955,2.013352278105239,12,7,7,1.0
38
  36,ETS,0.0003160064870084056,1.000000000000001e-12,1,1,1,1.0
39
  36,TabPFN-TS,1.0553883777131202e-07,0.0008433365473335877,2,1,1,1.0
40
  36,Toto-1.0,0.05469192573721511,0.0020086340389211823,3,1,1,1.0
 
23
  12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
24
  12,Toto-1.0,7534.1263954366505,13038.851881781453,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
+ 24,TiRex,0.3508509668853035,0.7055885069620663,1,6,6,1.0
27
+ 24,Chronos-2,0.37951076735916145,0.6934037615919085,2,6,6,1.0
28
+ 24,Chronos-Bolt,0.5094193160936651,0.704481403367288,3,6,6,1.0
29
+ 24,Sundial,0.6897535606282527,0.7111801131149522,4,6,6,1.0
30
+ 24,Toto-1.0,1.6097924218006927,0.6860760798646774,5,6,6,1.0
31
+ 24,Moirai-2.0,0.419229289802811,0.7441804627400953,6,6,6,1.0
32
+ 24,TabPFN-TS,0.534360665395711,0.7399282263361974,7,6,6,1.0
33
+ 24,TimesFM-2.5,0.4703385898665995,0.7751925886506386,8,6,6,1.0
34
+ 24,ARIMA,1.8699620239083985,1.3478936574541842,9,6,6,1.0
35
+ 24,Moving-Average,1.5419492666405061,1.3244155547545262,10,6,6,1.0
36
+ 24,Seasonal-Naive,1.0,1.0,11,6,6,1.0
37
+ 24,ETS,4.424025325844782,2.20154139110127,12,6,6,1.0
38
  36,ETS,0.0003160064870084056,1.000000000000001e-12,1,1,1,1.0
39
  36,TabPFN-TS,1.0553883777131202e-07,0.0008433365473335877,2,1,1,1.0
40
  36,Toto-1.0,0.05469192573721511,0.0020086340389211823,3,1,1,1.0
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-2,0.13551095513746933,0.9913608467642023,1,13,13,1.0
3
- Overall,TiRex,0.1224806415900693,0.9807742198495171,2,13,13,1.0
4
- Overall,Moirai-2.0,0.16287258118758158,1.1658420026831902,3,13,13,1.0
5
- Overall,Sundial,0.35149707747707265,1.1190372381053564,4,13,13,1.0
6
- Overall,Toto-1.0,3.989385957790437,1.9736567361922646,5,13,13,1.0
7
- Overall,ARIMA,0.6341595777487467,1.9472211116426137,6,13,13,1.0
8
- Overall,Chronos-Bolt,0.21501646886290463,1.817335776045877,7,13,13,1.0
9
- Overall,TimesFM-2.5,0.1597427274112271,0.4790935805746809,8,13,13,1.0
10
- Overall,ETS,0.7923273256040497,0.37679264853892164,9,13,13,1.0
11
- Overall,TabPFN-TS,0.18690240444673736,0.47855028852547243,10,13,13,1.0
12
- Overall,Moving-Average,0.9256421422364086,2.735750287222228,11,13,13,1.0
13
- Overall,Seasonal-Naive,1.0,1.0,12,13,13,1.0
 
1
  overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
+ Overall,TiRex,0.10179781709203017,0.9766871365860337,1,12,12,1.0
3
+ Overall,Chronos-2,0.11357753428061074,0.9897870162036663,2,12,12,1.0
4
+ Overall,Moirai-2.0,0.1391033138051579,1.1815960514755193,3,12,12,1.0
5
+ Overall,Sundial,0.32264381538941844,1.1135443446285107,4,12,12,1.0
6
+ Overall,Toto-1.0,4.448654292431631,2.080725611373261,5,12,12,1.0
7
+ Overall,Chronos-Bolt,0.187762639510678,1.8975473220496613,6,12,12,1.0
8
+ Overall,TimesFM-2.5,0.13569874928075795,0.4421369184156991,7,12,12,1.0
9
+ Overall,ARIMA,0.6118240353757025,2.2289028463405396,8,12,12,1.0
10
+ Overall,ETS,0.7720531291181013,0.34265298329472405,9,12,12,1.0
11
+ Overall,TabPFN-TS,0.16087572829886923,0.4396798726030351,10,12,12,1.0
12
+ Overall,Moving-Average,0.9215541049043304,2.948613699720417,11,12,12,1.0
13
+ Overall,Seasonal-Naive,1.0,1.0,12,12,12,1.0
results/dataset_properties.csv CHANGED
@@ -10,5 +10,4 @@ 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
- usgs_potomac_iv_usgs_00060,Hydrology,15min,1
14
  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
  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": "2026-07-28T17:42:34.701264+00:00",
6
- "finished_at": "2026-07-28T17:46:14.563659+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
- "task_count": 4,
10
- "issued_tasks": 1,
11
- "issued_forecasts": 12,
12
- "resolved_forecasts": 12,
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": "2026-07-28T17:46:10.072503+00:00",
23
- "resolved_tasks": [
24
- {
25
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
26
- "task_id": "future-11a4cfc38ecb272f5f2d",
27
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
28
- "resolved_at": "2026-07-28T17:42:39.369270+00:00",
29
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.122596+00:00",
42
- "resolved_tasks": [
43
- {
44
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
45
- "task_id": "future-11a4cfc38ecb272f5f2d",
46
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
47
- "resolved_at": "2026-07-28T17:42:39.760321+00:00",
48
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.142955+00:00",
61
- "resolved_tasks": [
62
- {
63
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
64
- "task_id": "future-11a4cfc38ecb272f5f2d",
65
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
66
- "resolved_at": "2026-07-28T17:42:39.734065+00:00",
67
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.152520+00:00",
80
- "resolved_tasks": [
81
- {
82
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
83
- "task_id": "future-11a4cfc38ecb272f5f2d",
84
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
85
- "resolved_at": "2026-07-28T17:42:39.829301+00:00",
86
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.162006+00:00",
99
- "resolved_tasks": [
100
- {
101
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
102
- "task_id": "future-11a4cfc38ecb272f5f2d",
103
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
104
- "resolved_at": "2026-07-28T17:42:39.511668+00:00",
105
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.168982+00:00",
118
- "resolved_tasks": [
119
- {
120
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
121
- "task_id": "future-11a4cfc38ecb272f5f2d",
122
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
123
- "resolved_at": "2026-07-28T17:42:39.409356+00:00",
124
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.216276+00:00",
137
- "resolved_tasks": [
138
- {
139
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
140
- "task_id": "future-11a4cfc38ecb272f5f2d",
141
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
142
- "resolved_at": "2026-07-28T17:42:39.695463+00:00",
143
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.239806+00:00",
156
- "resolved_tasks": [
157
- {
158
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
159
- "task_id": "future-11a4cfc38ecb272f5f2d",
160
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
161
- "resolved_at": "2026-07-28T17:42:39.642247+00:00",
162
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.253942+00:00",
175
- "resolved_tasks": [
176
- {
177
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
178
- "task_id": "future-11a4cfc38ecb272f5f2d",
179
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
180
- "resolved_at": "2026-07-28T17:42:39.536254+00:00",
181
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.281851+00:00",
194
- "resolved_tasks": [
195
- {
196
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
197
- "task_id": "future-11a4cfc38ecb272f5f2d",
198
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
199
- "resolved_at": "2026-07-28T17:42:39.455925+00:00",
200
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.290619+00:00",
213
- "resolved_tasks": [
214
- {
215
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
216
- "task_id": "future-11a4cfc38ecb272f5f2d",
217
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
218
- "resolved_at": "2026-07-28T17:42:39.297471+00:00",
219
- "target_end": "2026-07-27T14:30:00+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": "2026-07-28T17:46:10.323503+00:00",
232
- "resolved_tasks": [
233
- {
234
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
235
- "task_id": "future-11a4cfc38ecb272f5f2d",
236
- "issued_at": "2026-07-28T14:22:27.338912+00:00",
237
- "resolved_at": "2026-07-28T17:42:39.603257+00:00",
238
- "target_end": "2026-07-27T14:30:00+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": "ok",
266
- "pushed_at": "2026-07-28T17:47:24.036162+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": "2026-07-28T17:58:57.354453+00:00",
6
+ "finished_at": "2026-07-28T17:59:02.804053+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,
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": "2026-07-28T17:58:59.675069+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": "2026-07-28T17:58:59.675091+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": "2026-07-28T17:58:59.675095+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": "2026-07-28T17:58:59.675098+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": "2026-07-28T17:58:59.675101+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": "2026-07-28T17:58:59.675104+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": "2026-07-28T17:58:59.675106+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": "2026-07-28T17:58:59.675108+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": "2026-07-28T17:58:59.675111+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": "2026-07-28T17:58:59.675113+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": "2026-07-28T17:58:59.675115+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": "2026-07-28T17:58:59.675118+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
  }