ziyuzhou02 commited on
Commit
db10537
·
verified ·
1 Parent(s): e9d1608

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-28T09:49:07.653023+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": "2026-07-28T10:00:48.136476+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": "2026-07-28T09:49:05.595748+00:00",
3
  "baseline_model": "Seasonal-Naive",
4
  "normalization": "Per-config metric / Seasonal-Naive metric",
5
  "metric_aggregation": "Geometric mean over dataset configurations",
 
1
  {
2
+ "generated_at": "2026-07-28T10:00:46.080970+00:00",
3
  "baseline_model": "Seasonal-Naive",
4
  "normalization": "Per-config metric / Seasonal-Naive metric",
5
  "metric_aggregation": "Geometric mean over dataset configurations",
results/online_status.json CHANGED
@@ -1,17 +1,23 @@
1
  {
2
- "status": "ok",
3
  "evaluation_protocol": "issue-now-score-later",
4
  "metric_version": "livehouse-canonical-v1",
5
- "started_at": "2026-07-28T09:48:59.885423+00:00",
6
- "finished_at": "2026-07-28T09:49:07.664790+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,
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": "2026-07-28T09:49:03.429804+00:00",
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": "2026-07-28T09:49:03.429812+00:00",
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": "2026-07-28T09:49:03.429814+00:00",
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": "2026-07-28T09:49:03.429815+00:00",
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": "2026-07-28T09:49:03.429816+00:00",
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": "2026-07-28T09:49:03.429817+00:00",
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": "2026-07-28T09:49:03.429818+00:00",
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": "2026-07-28T09:49:03.429819+00:00",
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": "2026-07-28T09:49:03.429820+00:00",
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": "2026-07-28T09:49:03.429821+00:00",
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": "2026-07-28T09:49:03.429822+00:00",
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": "2026-07-28T09:49:03.429822+00:00",
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": "ok",
146
- "pushed_at": "2026-07-28T09:50:01.784553+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": "2026-07-28T10:00:40.639569+00:00",
6
+ "finished_at": "2026-07-28T10:00:48.147906+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": "2026-07-28T10:00:45.041206+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": "2026-07-28T10:00:45.041214+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": "2026-07-28T10:00:45.041215+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": "2026-07-28T10:00:45.041216+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": "2026-07-28T10:00:45.041218+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": "2026-07-28T10:00:45.041219+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": "2026-07-28T10:00:45.041220+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": "2026-07-28T10:00:45.041221+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": "2026-07-28T10:00:45.041222+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": "2026-07-28T10:00:45.041223+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": "2026-07-28T10:00:45.041224+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": "2026-07-28T10:00:45.041225+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
  }