ziyuzhou02 commited on
Commit
2e7296a
·
verified ·
1 Parent(s): be3bf2a

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-29T02:34:30.170237+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": "2026-07-29T02:48:10.213133+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": "2026-07-29T02:34:28.032024+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": "2026-07-29T02:48:08.314805+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,Moving-Average,1.0214140625,0.6370328425821091,1,1,1,1.0
39
- Hydrology,TabPFN-TS,0.999726629540324,0.6371976997142226,2,1,1,1.0
40
- Hydrology,Chronos-Bolt,0.9985341234579681,0.6392717717863047,3,1,1,1.0
41
- Hydrology,Chronos-2,1.001236886292696,0.6392940292272022,4,1,1,1.0
42
- Hydrology,TimesFM-2.5,0.9991976121589539,0.6429353154529154,5,1,1,1.0
43
- Hydrology,Sundial,1.12480897089839,0.6844293199066155,6,1,1,1.0
44
- Hydrology,Moirai-2.0,1.0619692907109857,0.7372901890583003,7,1,1,1.0
45
- Hydrology,TiRex,1.0007208641320466,0.7887214842091093,8,1,1,1.0
46
- Hydrology,Toto-1.0,1.033309433609247,0.8128151639806623,9,1,1,1.0
47
- Hydrology,ETS,0.8679554287684873,0.9135102558601378,10,1,1,1.0
48
- Hydrology,Seasonal-Naive,1.0,1.0,11,1,1,1.0
49
- Hydrology,ARIMA,2.8471547283782317,3.1754261339537115,12,1,1,1.0
50
  Ocean,ETS,0.09518516095471151,0.2761720625285491,1,2,2,1.0
51
  Ocean,TimesFM-2.5,0.07281852879570394,0.2570119454529022,2,2,2,1.0
52
  Ocean,Chronos-2,0.05541782384319625,0.2784674272092755,3,2,2,1.0
 
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,ETS,0.09518516095471151,0.2761720625285491,1,2,2,1.0
39
  Ocean,TimesFM-2.5,0.07281852879570394,0.2570119454529022,2,2,2,1.0
40
  Ocean,Chronos-2,0.05541782384319625,0.2784674272092755,3,2,2,1.0
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,Moving-Average,1.0214140625,0.6370328425821091,1,1,1,1.0
15
- 15min,TabPFN-TS,0.999726629540324,0.6371976997142226,2,1,1,1.0
16
- 15min,Chronos-Bolt,0.9985341234579681,0.6392717717863047,3,1,1,1.0
17
- 15min,Chronos-2,1.001236886292696,0.6392940292272022,4,1,1,1.0
18
- 15min,TimesFM-2.5,0.9991976121589539,0.6429353154529154,5,1,1,1.0
19
- 15min,Sundial,1.12480897089839,0.6844293199066155,6,1,1,1.0
20
- 15min,Moirai-2.0,1.0619692907109857,0.7372901890583003,7,1,1,1.0
21
- 15min,TiRex,1.0007208641320466,0.7887214842091093,8,1,1,1.0
22
- 15min,Toto-1.0,1.033309433609247,0.8128151639806623,9,1,1,1.0
23
- 15min,ETS,0.8679554287684873,0.9135102558601378,10,1,1,1.0
24
- 15min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
25
- 15min,ARIMA,2.8471547283782317,3.1754261339537115,12,1,1,1.0
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-1.0,255690.8555968103,13030.420401776826,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
- 24,Chronos-2,0.33112343830775287,0.6408591087639055,1,7,7,1.0
27
- 24,Chronos-Bolt,0.44303153510032106,0.6530382053012764,2,7,7,1.0
28
- 24,TiRex,0.2907103671635409,0.6572440134253928,3,7,7,1.0
29
- 24,Sundial,0.5403622341038394,0.6078867021056567,4,7,7,1.0
30
- 24,Moirai-2.0,0.3567187274513251,0.6919534774596541,5,7,7,1.0
31
- 24,TimesFM-2.5,0.3059580583366679,0.622723097736219,6,7,7,1.0
32
- 24,Toto-1.0,1.1680858370126643,0.6735050933105378,7,7,7,1.0
33
- 24,TabPFN-TS,0.49750143180707923,0.7055098464842646,8,7,7,1.0
34
- 24,Moving-Average,1.5163338622973692,1.2480242202276746,9,7,7,1.0
35
- 24,Seasonal-Naive,1.0,1.0,10,7,7,1.0
36
- 24,ARIMA,1.6111643626474184,1.5559883799961705,11,7,7,1.0
37
- 24,ETS,4.232993404975467,2.235937000348479,12,7,7,1.0
38
  36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
39
  36,Moving-Average,4301413138.721198,1.0,2,1,1,1.0
40
  36,ETS,4301412560.972201,123967.05458766423,3,1,1,1.0
 
23
  12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
24
  12,Toto-1.0,255690.8555968103,13030.420401776826,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
+ 24,TiRex,0.23658386029479467,0.637568913552396,1,6,6,1.0
27
+ 24,Chronos-2,0.27535867933395397,0.641120327610135,2,6,6,1.0
28
+ 24,Sundial,0.4782107758197922,0.5959890984516459,3,6,6,1.0
29
+ 24,Chronos-Bolt,0.3869129467061027,0.6553612620801093,4,6,6,1.0
30
+ 24,Toto-1.0,1.1921991800605538,0.6527282343390408,5,6,6,1.0
31
+ 24,Moirai-2.0,0.29741411006123314,0.6846731596793509,6,6,6,1.0
32
+ 24,TimesFM-2.5,0.2511868969740782,0.6194167190839796,7,6,6,1.0
33
+ 24,TabPFN-TS,0.4428736560186536,0.7175869951826023,8,6,6,1.0
34
+ 24,ARIMA,1.465304815202299,1.3815726858440398,9,6,6,1.0
35
+ 24,Seasonal-Naive,1.0,1.0,10,6,6,1.0
36
+ 24,Moving-Average,1.6195474144088537,1.3960464827885333,11,6,6,1.0
37
+ 24,ETS,5.51238175363501,2.595676619701423,12,6,6,1.0
38
  36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
39
  36,Moving-Average,4301413138.721198,1.0,2,1,1,1.0
40
  36,ETS,4301412560.972201,123967.05458766423,3,1,1,1.0
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,0.8017260142696447,5.60310165565298,1,13,13,1.0
3
- Overall,Chronos-2,1.0990823535166132,6.922901496899398,2,13,13,1.0
4
- Overall,Sundial,2.336405644992367,7.308038988236886,3,13,13,1.0
5
- Overall,TimesFM-2.5,0.7678796232570124,3.0811081667098477,4,13,13,1.0
6
- Overall,Moirai-2.0,1.1656250122658105,8.650226658565176,5,13,13,1.0
7
- Overall,Chronos-Bolt,1.6865390808253753,11.552018828811239,6,13,13,1.0
8
- Overall,Moving-Average,6.300088763429552,2.7326347968300655,7,13,13,1.0
9
- Overall,Toto-1.0,50.696070929765014,15.5992336705747,8,13,13,1.0
10
- Overall,ARIMA,5.582983997675871,18.10276290637925,9,13,13,1.0
11
- Overall,TabPFN-TS,1.9088862726566063,4.025370192511457,10,13,13,1.0
12
- Overall,ETS,7.646102057230824,7.590098954379924,11,13,13,1.0
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,0.7870495244413689,6.5976190835324715,1,12,12,1.0
3
+ Overall,Chronos-2,1.1076554394122438,8.443135859020373,2,12,12,1.0
4
+ Overall,Sundial,2.4831561845443395,8.902395336265226,3,12,12,1.0
5
+ Overall,Moirai-2.0,1.174706665535206,10.620457857208972,4,12,12,1.0
6
+ Overall,TimesFM-2.5,0.7512133364392474,3.5109010023776324,5,12,12,1.0
7
+ Overall,Toto-1.0,70.12447572941844,19.95396560223523,6,12,12,1.0
8
+ Overall,Chronos-Bolt,1.761837572480876,14.70298739069732,7,12,12,1.0
9
+ Overall,ARIMA,5.90524144580455,20.928596302908005,8,12,12,1.0
10
+ Overall,Moving-Average,7.331487042370404,3.0851994256541686,9,12,12,1.0
11
+ Overall,ETS,9.166115233130736,9.054725150573324,10,12,12,1.0
12
+ Overall,Seasonal-Naive,1.0,1.0,11,12,12,1.0
13
+ Overall,TabPFN-TS,2.014597486146719,4.693715857687908,12,12,12,1.0
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": "2026-07-29T02:31:17.528395+00:00",
6
- "finished_at": "2026-07-29T02:34:30.180926+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 3,
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": "2026-07-29T02:34:25.596308+00:00",
23
- "resolved_tasks": [
24
- {
25
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
26
- "task_id": "future-c056385aaaf66931e9d4",
27
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
28
- "resolved_at": "2026-07-29T02:31:22.783151+00:00",
29
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.624948+00:00",
42
- "resolved_tasks": [
43
- {
44
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
45
- "task_id": "future-c056385aaaf66931e9d4",
46
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
47
- "resolved_at": "2026-07-29T02:31:23.239323+00:00",
48
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.634421+00:00",
61
- "resolved_tasks": [
62
- {
63
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
64
- "task_id": "future-c056385aaaf66931e9d4",
65
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
66
- "resolved_at": "2026-07-29T02:31:23.196597+00:00",
67
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.642155+00:00",
80
- "resolved_tasks": [
81
- {
82
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
83
- "task_id": "future-c056385aaaf66931e9d4",
84
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
85
- "resolved_at": "2026-07-29T02:31:23.267028+00:00",
86
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.651854+00:00",
99
- "resolved_tasks": [
100
- {
101
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
102
- "task_id": "future-c056385aaaf66931e9d4",
103
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
104
- "resolved_at": "2026-07-29T02:31:22.938113+00:00",
105
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.654828+00:00",
118
- "resolved_tasks": [
119
- {
120
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
121
- "task_id": "future-c056385aaaf66931e9d4",
122
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
123
- "resolved_at": "2026-07-29T02:31:22.830152+00:00",
124
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.661364+00:00",
137
- "resolved_tasks": [
138
- {
139
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
140
- "task_id": "future-c056385aaaf66931e9d4",
141
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
142
- "resolved_at": "2026-07-29T02:31:23.166139+00:00",
143
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.685937+00:00",
156
- "resolved_tasks": [
157
- {
158
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
159
- "task_id": "future-c056385aaaf66931e9d4",
160
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
161
- "resolved_at": "2026-07-29T02:31:23.126081+00:00",
162
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.687760+00:00",
175
- "resolved_tasks": [
176
- {
177
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
178
- "task_id": "future-c056385aaaf66931e9d4",
179
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
180
- "resolved_at": "2026-07-29T02:31:23.003115+00:00",
181
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.693113+00:00",
194
- "resolved_tasks": [
195
- {
196
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
197
- "task_id": "future-c056385aaaf66931e9d4",
198
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
199
- "resolved_at": "2026-07-29T02:31:22.864048+00:00",
200
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.696398+00:00",
213
- "resolved_tasks": [
214
- {
215
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
216
- "task_id": "future-c056385aaaf66931e9d4",
217
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
218
- "resolved_at": "2026-07-29T02:31:22.692674+00:00",
219
- "target_end": "2026-07-27T17:35:00+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": "2026-07-29T02:34:25.720777+00:00",
232
- "resolved_tasks": [
233
- {
234
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
235
- "task_id": "future-c056385aaaf66931e9d4",
236
- "issued_at": "2026-07-28T19:38:05.211084+00:00",
237
- "resolved_at": "2026-07-29T02:31:23.038085+00:00",
238
- "target_end": "2026-07-27T17:35:00+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": "ok",
266
- "pushed_at": "2026-07-29T02:35:31.675395+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": "2026-07-29T02:48:01.381934+00:00",
6
+ "finished_at": "2026-07-29T02:48:10.224006+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 3,
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": "2026-07-29T02:48:06.653850+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": "2026-07-29T02:48:06.653857+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": "2026-07-29T02:48:06.653859+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": "2026-07-29T02:48:06.653860+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": "2026-07-29T02:48:06.653860+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": "2026-07-29T02:48:06.653862+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": "2026-07-29T02:48:06.653863+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": "2026-07-29T02:48:06.653864+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": "2026-07-29T02:48:06.653865+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": "2026-07-29T02:48:06.653865+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": "2026-07-29T02:48:06.653866+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": "2026-07-29T02:48:06.653867+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
  }