ziyuzhou02 commited on
Commit
c852145
·
verified ·
1 Parent(s): 83acce6

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-28T12:26:01.466941+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": "2026-07-28T12:40:11.489228+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": "2026-07-28T12:25:37.451335+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": "2026-07-28T12:40:09.513780+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": "2026-07-28T12:22:46.850740+00:00",
6
- "finished_at": "2026-07-28T12:26:01.477346+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
- "task_count": 2,
10
- "issued_tasks": 1,
11
- "issued_forecasts": 12,
12
- "resolved_forecasts": 12,
13
  "pending_tasks": 13,
14
- "failed_forecasts": [],
 
 
 
 
 
 
15
  "models": {
16
  "Chronos-2": {
17
  "model": "Chronos-2",
@@ -19,18 +25,8 @@
19
  "admitted_at": "2026-06-01T00:00:00Z",
20
  "evaluation_protocol": "issue-now-score-later",
21
  "metric_version": "livehouse-canonical-v1",
22
- "evaluated_at": "2026-07-28T12:25:35.163834+00:00",
23
- "resolved_tasks": [
24
- {
25
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
26
- "task_id": "future-915c3cd2da3f0a7f5bda",
27
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
28
- "resolved_at": "2026-07-28T12:22:51.537982+00:00",
29
- "target_end": "2026-07-27T09:05:00+00:00",
30
- "prediction_length": 12,
31
- "metric_version": "livehouse-canonical-v1"
32
- }
33
- ]
34
  },
35
  "TiRex": {
36
  "model": "TiRex",
@@ -38,18 +34,8 @@
38
  "admitted_at": "2026-06-01T00:00:00Z",
39
  "evaluation_protocol": "issue-now-score-later",
40
  "metric_version": "livehouse-canonical-v1",
41
- "evaluated_at": "2026-07-28T12:25:35.189225+00:00",
42
- "resolved_tasks": [
43
- {
44
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
45
- "task_id": "future-915c3cd2da3f0a7f5bda",
46
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
47
- "resolved_at": "2026-07-28T12:22:51.966847+00:00",
48
- "target_end": "2026-07-27T09:05:00+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 +43,8 @@
57
  "admitted_at": "2026-06-01T00:00:00Z",
58
  "evaluation_protocol": "issue-now-score-later",
59
  "metric_version": "livehouse-canonical-v1",
60
- "evaluated_at": "2026-07-28T12:25:35.206125+00:00",
61
- "resolved_tasks": [
62
- {
63
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
64
- "task_id": "future-915c3cd2da3f0a7f5bda",
65
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
66
- "resolved_at": "2026-07-28T12:22:51.872515+00:00",
67
- "target_end": "2026-07-27T09:05:00+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 +52,8 @@
76
  "admitted_at": "2026-06-01T00:00:00Z",
77
  "evaluation_protocol": "issue-now-score-later",
78
  "metric_version": "livehouse-canonical-v1",
79
- "evaluated_at": "2026-07-28T12:25:35.208881+00:00",
80
- "resolved_tasks": [
81
- {
82
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
83
- "task_id": "future-915c3cd2da3f0a7f5bda",
84
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
85
- "resolved_at": "2026-07-28T12:22:52.008060+00:00",
86
- "target_end": "2026-07-27T09:05:00+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 +61,8 @@
95
  "admitted_at": "2026-06-01T00:00:00Z",
96
  "evaluation_protocol": "issue-now-score-later",
97
  "metric_version": "livehouse-canonical-v1",
98
- "evaluated_at": "2026-07-28T12:25:35.215484+00:00",
99
- "resolved_tasks": [
100
- {
101
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
102
- "task_id": "future-915c3cd2da3f0a7f5bda",
103
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
104
- "resolved_at": "2026-07-28T12:22:51.647830+00:00",
105
- "target_end": "2026-07-27T09:05:00+00:00",
106
- "prediction_length": 12,
107
- "metric_version": "livehouse-canonical-v1"
108
- }
109
- ]
110
  },
111
  "Chronos-Bolt": {
112
  "model": "Chronos-Bolt",
@@ -114,18 +70,8 @@
114
  "admitted_at": "2026-06-01T00:00:00Z",
115
  "evaluation_protocol": "issue-now-score-later",
116
  "metric_version": "livehouse-canonical-v1",
117
- "evaluated_at": "2026-07-28T12:25:35.224737+00:00",
118
- "resolved_tasks": [
119
- {
120
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
121
- "task_id": "future-915c3cd2da3f0a7f5bda",
122
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
123
- "resolved_at": "2026-07-28T12:22:51.562834+00:00",
124
- "target_end": "2026-07-27T09:05:00+00:00",
125
- "prediction_length": 12,
126
- "metric_version": "livehouse-canonical-v1"
127
- }
128
- ]
129
  },
130
  "TabPFN-TS": {
131
  "model": "TabPFN-TS",
@@ -133,18 +79,8 @@
133
  "admitted_at": "2026-06-01T00:00:00Z",
134
  "evaluation_protocol": "issue-now-score-later",
135
  "metric_version": "livehouse-canonical-v1",
136
- "evaluated_at": "2026-07-28T12:25:35.232581+00:00",
137
- "resolved_tasks": [
138
- {
139
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
140
- "task_id": "future-915c3cd2da3f0a7f5bda",
141
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
142
- "resolved_at": "2026-07-28T12:22:51.841833+00:00",
143
- "target_end": "2026-07-27T09:05:00+00:00",
144
- "prediction_length": 12,
145
- "metric_version": "livehouse-canonical-v1"
146
- }
147
- ]
148
  },
149
  "Sundial": {
150
  "model": "Sundial",
@@ -152,18 +88,8 @@
152
  "admitted_at": "2026-06-01T00:00:00Z",
153
  "evaluation_protocol": "issue-now-score-later",
154
  "metric_version": "livehouse-canonical-v1",
155
- "evaluated_at": "2026-07-28T12:25:35.252370+00:00",
156
- "resolved_tasks": [
157
- {
158
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
159
- "task_id": "future-915c3cd2da3f0a7f5bda",
160
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
161
- "resolved_at": "2026-07-28T12:22:51.809922+00:00",
162
- "target_end": "2026-07-27T09:05:00+00:00",
163
- "prediction_length": 12,
164
- "metric_version": "livehouse-canonical-v1"
165
- }
166
- ]
167
  },
168
  "Moving-Average": {
169
  "model": "Moving-Average",
@@ -171,18 +97,8 @@
171
  "admitted_at": "2026-06-01T00:00:00Z",
172
  "evaluation_protocol": "issue-now-score-later",
173
  "metric_version": "livehouse-canonical-v1",
174
- "evaluated_at": "2026-07-28T12:25:35.263355+00:00",
175
- "resolved_tasks": [
176
- {
177
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
178
- "task_id": "future-915c3cd2da3f0a7f5bda",
179
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
180
- "resolved_at": "2026-07-28T12:22:51.690818+00:00",
181
- "target_end": "2026-07-27T09:05:00+00:00",
182
- "prediction_length": 12,
183
- "metric_version": "livehouse-canonical-v1"
184
- }
185
- ]
186
  },
187
  "ETS": {
188
  "model": "ETS",
@@ -190,18 +106,8 @@
190
  "admitted_at": "2026-06-01T00:00:00Z",
191
  "evaluation_protocol": "issue-now-score-later",
192
  "metric_version": "livehouse-canonical-v1",
193
- "evaluated_at": "2026-07-28T12:25:35.265949+00:00",
194
- "resolved_tasks": [
195
- {
196
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
197
- "task_id": "future-915c3cd2da3f0a7f5bda",
198
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
199
- "resolved_at": "2026-07-28T12:22:51.618875+00:00",
200
- "target_end": "2026-07-27T09:05:00+00:00",
201
- "prediction_length": 12,
202
- "metric_version": "livehouse-canonical-v1"
203
- }
204
- ]
205
  },
206
  "ARIMA": {
207
  "model": "ARIMA",
@@ -209,18 +115,8 @@
209
  "admitted_at": "2026-06-01T00:00:00Z",
210
  "evaluation_protocol": "issue-now-score-later",
211
  "metric_version": "livehouse-canonical-v1",
212
- "evaluated_at": "2026-07-28T12:25:35.267990+00:00",
213
- "resolved_tasks": [
214
- {
215
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
216
- "task_id": "future-915c3cd2da3f0a7f5bda",
217
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
218
- "resolved_at": "2026-07-28T12:22:51.455146+00:00",
219
- "target_end": "2026-07-27T09:05:00+00:00",
220
- "prediction_length": 12,
221
- "metric_version": "livehouse-canonical-v1"
222
- }
223
- ]
224
  },
225
  "Seasonal-Naive": {
226
  "model": "Seasonal-Naive",
@@ -228,18 +124,8 @@
228
  "admitted_at": "2026-06-01T00:00:00Z",
229
  "evaluation_protocol": "issue-now-score-later",
230
  "metric_version": "livehouse-canonical-v1",
231
- "evaluated_at": "2026-07-28T12:25:35.269866+00:00",
232
- "resolved_tasks": [
233
- {
234
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
235
- "task_id": "future-915c3cd2da3f0a7f5bda",
236
- "issued_at": "2026-07-28T11:48:19.276268+00:00",
237
- "resolved_at": "2026-07-28T12:22:51.743842+00:00",
238
- "target_end": "2026-07-27T09:05:00+00:00",
239
- "prediction_length": 12,
240
- "metric_version": "livehouse-canonical-v1"
241
- }
242
- ]
243
  }
244
  },
245
  "skipped_models": [],
@@ -262,7 +148,5 @@
262
  "live_overall_30d": "aggregates/live_overall_30d.csv",
263
  "live_metadata": "aggregates/live_metadata.json"
264
  },
265
- "push_status": "ok",
266
- "pushed_at": "2026-07-28T12:27:04.899450+00:00",
267
- "push_detail": "HF Hub API"
268
  }
 
1
  {
2
+ "status": "partial",
3
  "evaluation_protocol": "issue-now-score-later",
4
  "metric_version": "livehouse-canonical-v1",
5
+ "started_at": "2026-07-28T12:40:06.026240+00:00",
6
+ "finished_at": "2026-07-28T12:40:11.500648+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": "2026-07-28T12:40:08.537782+00:00",
29
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
30
  },
31
  "TiRex": {
32
  "model": "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": "2026-07-28T12:40:08.537789+00:00",
38
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
39
  },
40
  "TimesFM-2.5": {
41
  "model": "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": "2026-07-28T12:40:08.537791+00:00",
47
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
48
  },
49
  "Toto-1.0": {
50
  "model": "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": "2026-07-28T12:40:08.537792+00:00",
56
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
57
  },
58
  "Moirai-2.0": {
59
  "model": "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": "2026-07-28T12:40:08.537793+00:00",
65
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
66
  },
67
  "Chronos-Bolt": {
68
  "model": "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": "2026-07-28T12:40:08.537794+00:00",
74
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
75
  },
76
  "TabPFN-TS": {
77
  "model": "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": "2026-07-28T12:40:08.537795+00:00",
83
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
84
  },
85
  "Sundial": {
86
  "model": "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": "2026-07-28T12:40:08.537796+00:00",
92
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
93
  },
94
  "Moving-Average": {
95
  "model": "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": "2026-07-28T12:40:08.537797+00:00",
101
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
102
  },
103
  "ETS": {
104
  "model": "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": "2026-07-28T12:40:08.537798+00:00",
110
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
111
  },
112
  "ARIMA": {
113
  "model": "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": "2026-07-28T12:40:08.537799+00:00",
119
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
120
  },
121
  "Seasonal-Naive": {
122
  "model": "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": "2026-07-28T12:40:08.537800+00:00",
128
+ "resolved_tasks": []
 
 
 
 
 
 
 
 
 
 
129
  }
130
  },
131
  "skipped_models": [],
 
148
  "live_overall_30d": "aggregates/live_overall_30d.csv",
149
  "live_metadata": "aggregates/live_metadata.json"
150
  },
151
+ "push_status": "pending"
 
 
152
  }