ziyuzhou02 commited on
Commit
dd77ed2
·
verified ·
1 Parent(s): 3876e7b

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-30T03:22:16.992219+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": "2026-07-30T03:34:11.474730+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": "2026-07-30T03:22:14.923100+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": "2026-07-30T03:34:09.465221+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
@@ -2,8 +2,8 @@
2
  "status": "ok",
3
  "evaluation_protocol": "issue-now-score-later",
4
  "metric_version": "livehouse-canonical-v1",
5
- "started_at": "2026-07-30T03:22:08.463503+00:00",
6
- "finished_at": "2026-07-30T03:22:17.003707+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 4,
@@ -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": "2026-07-30T03:22:13.261178+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": "2026-07-30T03:22:13.261197+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": "2026-07-30T03:22:13.261200+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": "2026-07-30T03:22:13.261202+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": "2026-07-30T03:22:13.261205+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": "2026-07-30T03:22:13.261207+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": "2026-07-30T03:22:13.261209+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": "2026-07-30T03:22:13.261212+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": "2026-07-30T03:22:13.261214+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": "2026-07-30T03:22:13.261216+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": "2026-07-30T03:22:13.261219+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": "2026-07-30T03:22:13.261221+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": "2026-07-30T03:23:18.299158+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": "2026-07-30T03:34:06.583555+00:00",
6
+ "finished_at": "2026-07-30T03:34:11.486869+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 4,
 
19
  "admitted_at": "2026-06-01T00:00:00Z",
20
  "evaluation_protocol": "issue-now-score-later",
21
  "metric_version": "livehouse-canonical-v1",
22
+ "evaluated_at": "2026-07-30T03:34:09.057378+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": "2026-07-30T03:34:09.057397+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": "2026-07-30T03:34:09.057401+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": "2026-07-30T03:34:09.057404+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": "2026-07-30T03:34:09.057406+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": "2026-07-30T03:34:09.057408+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": "2026-07-30T03:34:09.057411+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": "2026-07-30T03:34:09.057413+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": "2026-07-30T03:34:09.057415+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": "2026-07-30T03:34:09.057417+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": "2026-07-30T03:34:09.057419+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": "2026-07-30T03:34:09.057421+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
  }