ziyuzhou02 commited on
Commit
669c821
·
verified ·
1 Parent(s): 7966714

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-27T06:11:56.597009+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": "2026-07-27T06:24:14.796193+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": "2026-07-27T06:11:42.683822+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": "2026-07-27T06:24:12.526650+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,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
- 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
 
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
results/aggregates/results_by_frequency.csv CHANGED
@@ -11,18 +11,6 @@ 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
- 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
 
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
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-1.0,384873.0188877535,13327.175525195342,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
- 24,TiRex,0.5552979038192593,0.7990291671062807,1,7,7,1.0
27
- 24,Chronos-Bolt,0.5411696387233879,0.753262799562506,2,7,7,1.0
28
- 24,Chronos-2,0.646772721096046,0.7759612519697378,3,7,7,1.0
29
- 24,Sundial,0.7606410771099004,0.7759108715416382,4,7,7,1.0
30
- 24,Moirai-2.0,1.086973992115207,0.9879234439289957,5,7,7,1.0
31
- 24,Toto-1.0,2.4026463060317997,0.7934624094526244,6,7,7,1.0
32
- 24,Seasonal-Naive,1.0,1.0,7,7,7,1.0
33
- 24,TimesFM-2.5,0.7291521736846612,0.8745414822798746,8,7,7,1.0
34
- 24,TabPFN-TS,0.8341215929670431,0.936206061555175,9,7,7,1.0
35
- 24,ARIMA,2.685967783733017,1.722254335979107,10,7,7,1.0
36
- 24,Moving-Average,2.160327931644515,1.4793737311349737,11,7,7,1.0
37
- 24,ETS,7.626747289429526,2.906911936576978,12,7,7,1.0
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
 
23
  12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
24
  12,Toto-1.0,384873.0188877535,13327.175525195342,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
+ 24,TiRex,0.5071542842230036,0.723439594864657,1,6,6,1.0
27
+ 24,Chronos-Bolt,0.48852747529436374,0.6988591950632111,2,6,6,1.0
28
+ 24,Chronos-2,0.6014649305639767,0.7234893089563668,3,6,6,1.0
29
+ 24,Sundial,0.7267355482332052,0.7234345067080555,4,6,6,1.0
30
+ 24,Toto-1.0,2.5248803785195295,0.7251088253778802,5,6,6,1.0
31
+ 24,Moirai-2.0,1.1021880000629,0.9589501069018305,6,6,6,1.0
32
+ 24,TimesFM-2.5,0.6917585526136719,0.8318197486696985,7,6,6,1.0
33
+ 24,TabPFN-TS,0.8092839448074433,0.9006418024016122,8,6,6,1.0
34
+ 24,Seasonal-Naive,1.0,1.0,9,6,6,1.0
35
+ 24,ARIMA,3.1667778537892444,1.8339982286146068,10,6,6,1.0
36
+ 24,Moving-Average,2.456252223684873,1.535947237458775,11,6,6,1.0
37
+ 24,ETS,10.700299056579944,3.377711856811074,12,6,6,1.0
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
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,1.8009625980837958,7.141509977586904,1,13,13,1.0
3
- Overall,Moirai-2.0,2.830777584704455,12.19724488295978,2,13,13,1.0
4
- Overall,Chronos-2,2.4185318862600336,7.6715198903030135,3,13,13,1.0
5
- Overall,Sundial,4.598007319995878,10.938846202143933,4,13,13,1.0
6
- Overall,ARIMA,8.437513750216919,13.077656698045622,5,13,13,1.0
7
- Overall,Seasonal-Naive,1.0,1.0,6,13,13,1.0
8
- Overall,Moving-Average,7.265578725970994,2.930251717327456,7,13,13,1.0
9
- Overall,Toto-1.0,98.81328332684205,18.27146951818796,8,13,13,1.0
10
- Overall,TimesFM-2.5,1.6063164081521566,4.653090350063608,9,13,13,1.0
11
- Overall,Chronos-Bolt,2.4412844028600023,14.835614615809819,10,13,13,1.0
12
- Overall,ETS,15.489332161425226,12.025992799326682,11,13,13,1.0
13
- Overall,TabPFN-TS,3.65947910842757,5.186430370928792,12,13,13,1.0
 
1
  overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
+ Overall,TiRex,1.8984242849621829,8.156030091938922,1,12,12,1.0
3
+ Overall,Chronos-2,2.603241559941208,8.965975996216969,2,12,12,1.0
4
+ Overall,Sundial,5.221361908428266,13.16826368742788,3,12,12,1.0
5
+ Overall,Moirai-2.0,3.08719854126262,14.816978168553948,4,12,12,1.0
6
+ Overall,Toto-1.0,138.0706182555135,22.68467117172149,5,12,12,1.0
7
+ Overall,ARIMA,10.078572742335263,15.979019699554899,6,12,12,1.0
8
+ Overall,TimesFM-2.5,1.6710278454815868,5.216301045932894,7,12,12,1.0
9
+ Overall,Moving-Average,8.571221741121528,3.1607468359607087,8,12,12,1.0
10
+ Overall,Chronos-Bolt,2.6297829651856603,18.318519743429334,9,12,12,1.0
11
+ Overall,Seasonal-Naive,1.0,1.0,10,12,12,1.0
12
+ Overall,TabPFN-TS,4.07728320414509,5.867011906432972,11,12,12,1.0
13
+ Overall,ETS,19.462654994055878,14.591739117114606,12,12,12,1.0
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
@@ -2,11 +2,11 @@
2
  "status": "ok",
3
  "evaluation_protocol": "issue-now-score-later",
4
  "metric_version": "livehouse-canonical-v1",
5
- "started_at": "2026-07-27T06:11:35.484991+00:00",
6
- "finished_at": "2026-07-27T06:11:56.607029+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,
@@ -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": "2026-07-27T06:11:39.842521+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": "2026-07-27T06:11:39.842526+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": "2026-07-27T06:11:39.842527+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": "2026-07-27T06:11:39.842528+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": "2026-07-27T06:11:39.842533+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": "2026-07-27T06:11:39.842534+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": "2026-07-27T06:11:39.842535+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": "2026-07-27T06:11:39.842536+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": "2026-07-27T06:11:39.842536+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": "2026-07-27T06:11:39.842537+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": "2026-07-27T06:11:39.842538+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": "2026-07-27T06:11:39.842539+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": "2026-07-27T06:12:57.077321+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": "2026-07-27T06:24:07.495879+00:00",
6
+ "finished_at": "2026-07-27T06:24:14.808573+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,
 
19
  "admitted_at": "2026-06-01T00:00:00Z",
20
  "evaluation_protocol": "issue-now-score-later",
21
  "metric_version": "livehouse-canonical-v1",
22
+ "evaluated_at": "2026-07-27T06:24:10.703653+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": "2026-07-27T06:24:10.703660+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": "2026-07-27T06:24:10.703661+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": "2026-07-27T06:24:10.703662+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": "2026-07-27T06:24:10.703663+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": "2026-07-27T06:24:10.703663+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": "2026-07-27T06:24:10.703664+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": "2026-07-27T06:24:10.703666+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": "2026-07-27T06:24:10.703667+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": "2026-07-27T06:24:10.703667+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": "2026-07-27T06:24:10.703668+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": "2026-07-27T06:24:10.703669+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
  }