ziyuzhou02 commited on
Commit
ce023b1
·
verified ·
1 Parent(s): a621f5f

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-27T10:39:50.934572+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": "2026-07-27T10:51:33.114175+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": "2026-07-27T10:39:48.222374+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": 14,
14
  "num_models": 12,
15
  "num_rows_missing_prediction_length": 0
16
  }
 
1
  {
2
+ "generated_at": "2026-07-27T10:51:30.937614+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
@@ -11,18 +11,18 @@ Climate,Chronos-Bolt,47.4655458843892,96.98926440492649,9,5,5,1.0
11
  Climate,ARIMA,498.03148316002745,9.29051171563987,10,5,5,1.0
12
  Climate,TimesFM-2.5,19.702239675462305,97.57289238633813,11,5,5,1.0
13
  Climate,ETS,2730.709743546208,63.60664425761785,12,5,5,1.0
14
- Finance,TiRex,0.511127609443142,0.6365436647590029,1,3,3,1.0
15
- Finance,Chronos-2,0.6756273588989797,0.7474684518753827,2,3,3,1.0
16
- Finance,Moirai-2.0,0.8939506322509885,0.8084053655303516,3,3,3,1.0
17
- Finance,Chronos-Bolt,0.7502482432292896,0.8303214097324793,4,3,3,1.0
18
- Finance,Toto-1.0,0.8948723732629463,0.8783617899756722,5,3,3,1.0
19
- Finance,Sundial,0.6307937874132711,0.8016412757672429,6,3,3,1.0
20
- Finance,ARIMA,1.090517359648809,1.1187187338654994,7,3,3,1.0
21
- Finance,TimesFM-2.5,0.7139757250034728,0.8742752788997603,8,3,3,1.0
22
- Finance,Seasonal-Naive,1.0,1.0,9,3,3,1.0
23
- Finance,TabPFN-TS,0.7471649627495729,0.9604369019880863,10,3,3,1.0
24
- Finance,ETS,1.1311048184754804,1.0949766947182327,11,3,3,1.0
25
- Finance,Moving-Average,1.0978870037380029,1.1315175601021201,12,3,3,1.0
26
  Hazards,ARIMA,0.7462605338771628,0.6602389941338824,1,1,1,1.0
27
  Hazards,Moirai-2.0,0.7281972824447458,0.7036277604367918,2,1,1,1.0
28
  Hazards,Moving-Average,0.7963258085146442,0.7048427412162565,3,1,1,1.0
@@ -71,15 +71,3 @@ Transportation,Moving-Average,1.0,250217.138218906,9,1,1,1.0
71
  Transportation,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
72
  Transportation,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
73
  Transportation,Toto-1.0,139539233137.999,281471356.81470025,12,1,1,1.0
74
- Web,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
75
- Web,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
76
- Web,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
77
- Web,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
78
- Web,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
79
- Web,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
80
- Web,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
81
- Web,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
82
- Web,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
83
- Web,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
84
- Web,Seasonal-Naive,1.0,1.0,11,1,1,1.0
85
- Web,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
 
11
  Climate,ARIMA,498.03148316002745,9.29051171563987,10,5,5,1.0
12
  Climate,TimesFM-2.5,19.702239675462305,97.57289238633813,11,5,5,1.0
13
  Climate,ETS,2730.709743546208,63.60664425761785,12,5,5,1.0
14
+ Finance,TiRex,0.3931124718915428,0.5540640832588316,1,2,2,1.0
15
+ Finance,Chronos-Bolt,0.4094997273505915,0.5971475845353197,2,2,2,1.0
16
+ Finance,Chronos-2,0.4792565171069634,0.5968336898677795,3,2,2,1.0
17
+ Finance,Moirai-2.0,0.6022456428440649,0.6277441482199546,4,2,2,1.0
18
+ Finance,Sundial,0.3850621616392369,0.5665205003918359,5,2,2,1.0
19
+ Finance,Toto-1.0,0.5732008210305747,0.6524422824227847,6,2,2,1.0
20
+ Finance,TimesFM-2.5,0.5243224958692184,0.6419690325196108,7,2,2,1.0
21
+ Finance,ETS,1.017222403089634,0.9244745823211508,8,2,2,1.0
22
+ Finance,ARIMA,1.0429819994006044,1.3044306584906822,9,2,2,1.0
23
+ Finance,TabPFN-TS,0.647027083008818,0.7923082880130374,10,2,2,1.0
24
+ Finance,Seasonal-Naive,1.0,1.0,11,2,2,1.0
25
+ Finance,Moving-Average,1.047028420685017,1.0104050688948565,12,2,2,1.0
26
  Hazards,ARIMA,0.7462605338771628,0.6602389941338824,1,1,1,1.0
27
  Hazards,Moirai-2.0,0.7281972824447458,0.7036277604367918,2,1,1,1.0
28
  Hazards,Moving-Average,0.7963258085146442,0.7048427412162565,3,1,1,1.0
 
71
  Transportation,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
72
  Transportation,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
73
  Transportation,Toto-1.0,139539233137.999,281471356.81470025,12,1,1,1.0
 
 
 
 
 
 
 
 
 
 
 
 
results/aggregates/results_by_frequency.csv CHANGED
@@ -23,30 +23,18 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
23
  15min,Toto-1.0,108543418950.29202,0.44809729258219655,10,1,1,1.0
24
  15min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
25
  15min,ARIMA,10837674801930.557,5.106079303459772,12,1,1,1.0
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
29
- 1D,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
30
- 1D,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
31
- 1D,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
32
- 1D,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
33
- 1D,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
34
- 1D,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
35
- 1D,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
36
- 1D,Seasonal-Naive,1.0,1.0,11,1,1,1.0
37
- 1D,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
38
- 1h,TiRex,0.7750233887785511,0.8731280991152257,1,7,7,1.0
39
- 1h,Toto-1.0,3.470346837824563,0.9290676306090473,2,7,7,1.0
40
- 1h,Seasonal-Naive,1.0,1.0,3,7,7,1.0
41
- 1h,Chronos-2,1.0557222332934295,0.9420539527408869,4,7,7,1.0
42
- 1h,Moirai-2.0,1.3074632480924078,1.0409721294042618,5,7,7,1.0
43
- 1h,TabPFN-TS,0.7872457845933027,0.9836899995672891,6,7,7,1.0
44
- 1h,Sundial,1.4082380266832522,1.0309415375783566,7,7,7,1.0
45
- 1h,ARIMA,4.487995071217601,2.1913157129268295,8,7,7,1.0
46
- 1h,Chronos-Bolt,1.2952350198445803,1.0117775807505975,9,7,7,1.0
47
- 1h,TimesFM-2.5,0.9561943420818555,1.08048274208185,10,7,7,1.0
48
- 1h,Moving-Average,2.958841847567672,1.851054181454787,11,7,7,1.0
49
- 1h,ETS,15.27761409327684,4.372686909715655,12,7,7,1.0
50
  1mo,Moirai-2.0,0.5701893078499076,0.5711658118752873,1,1,1,1.0
51
  1mo,Chronos-Bolt,0.6722527938921684,0.6335328970612374,2,1,1,1.0
52
  1mo,Toto-1.0,0.6317640740160342,0.6385745807295035,3,1,1,1.0
 
23
  15min,Toto-1.0,108543418950.29202,0.44809729258219655,10,1,1,1.0
24
  15min,Seasonal-Naive,1.0,1.0,11,1,1,1.0
25
  15min,ARIMA,10837674801930.557,5.106079303459772,12,1,1,1.0
26
+ 1h,TiRex,0.7610996943071011,0.878746331824924,1,6,6,1.0
27
+ 1h,Toto-1.0,3.7496443706833267,0.8493092732352021,2,6,6,1.0
28
+ 1h,Chronos-2,1.014246865952099,0.9083287947663047,3,6,6,1.0
29
+ 1h,Seasonal-Naive,1.0,1.0,4,6,6,1.0
30
+ 1h,Moirai-2.0,1.2211495654602278,0.9979878400623481,5,6,6,1.0
31
+ 1h,TabPFN-TS,0.7569397375884535,0.926257234094127,6,6,6,1.0
32
+ 1h,Sundial,1.3657000431154327,0.9576090002677531,7,6,6,1.0
33
+ 1h,Chronos-Bolt,1.159369986330377,0.9368498734192843,8,6,6,1.0
34
+ 1h,TimesFM-2.5,0.905722114763785,1.00979852986364,9,6,6,1.0
35
+ 1h,ARIMA,5.5976242951061925,2.579896730748346,10,6,6,1.0
36
+ 1h,Moving-Average,3.4357064155293853,1.9348925056984916,11,6,6,1.0
37
+ 1h,ETS,22.757191857667504,5.205578498615606,12,6,6,1.0
 
 
 
 
 
 
 
 
 
 
 
 
38
  1mo,Moirai-2.0,0.5701893078499076,0.5711658118752873,1,1,1,1.0
39
  1mo,Chronos-Bolt,0.6722527938921684,0.6335328970612374,2,1,1,1.0
40
  1mo,Toto-1.0,0.6317640740160342,0.6385745807295035,3,1,1,1.0
results/aggregates/results_by_prediction_length.csv CHANGED
@@ -1,16 +1,4 @@
1
  prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
- 7,ARIMA,0.35081770342317864,0.47944164778388026,1,1,1,1.0
3
- 7,Moirai-2.0,0.40785680526551005,0.5118677129116019,2,1,1,1.0
4
- 7,Sundial,0.303769640015456,0.5282879649026628,3,1,1,1.0
5
- 7,ETS,0.4243826259793997,0.5449399343905824,4,1,1,1.0
6
- 7,Moving-Average,0.4370340438348723,0.54802384805273,5,1,1,1.0
7
- 7,Chronos-2,0.4498860462918392,0.5739884284864399,6,1,1,1.0
8
- 7,TiRex,0.46006192226374054,0.5949360110321206,7,1,1,1.0
9
- 7,TimesFM-2.5,0.32382897462809757,0.6278956823267848,8,1,1,1.0
10
- 7,Chronos-Bolt,0.3947163650820193,0.6425428458659833,9,1,1,1.0
11
- 7,Toto-1.0,1.1828445386062165,0.7008146109363338,10,1,1,1.0
12
- 7,Seasonal-Naive,1.0,1.0,11,1,1,1.0
13
- 7,TabPFN-TS,0.8629829581417852,1.004036040514957,12,1,1,1.0
14
  12,Chronos-2,0.8294476545156683,38.946376459967496,1,2,2,1.0
15
  12,TiRex,0.847802672121473,30.22591777828443,2,2,2,1.0
16
  12,Moirai-2.0,0.7551088053055054,483.94979926515697,3,2,2,1.0
@@ -23,18 +11,18 @@ 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-1.0,296910.5495133771,13406.731654855768,11,2,2,1.0
25
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
- 24,TiRex,5.224871811883289,0.7823730949914425,1,8,8,1.0
27
- 24,Chronos-2,6.0695511895599426,0.42944714703078707,2,8,8,1.0
28
- 24,TabPFN-TS,2.548332405401998,0.29130116026903996,3,8,8,1.0
29
- 24,Moirai-2.0,11.76921551477689,0.6135853025712298,4,8,8,1.0
30
- 24,Toto-1.0,71.16668043850568,0.8481310305890166,5,8,8,1.0
31
- 24,Seasonal-Naive,1.0,1.0,6,8,8,1.0
32
- 24,Sundial,22.22111134675419,0.6698504650169589,7,8,8,1.0
33
- 24,Chronos-Bolt,13.420985696012036,0.5948015273581341,8,8,8,1.0
34
- 24,TimesFM-2.5,6.290754398626646,0.494206717769758,9,8,8,1.0
35
- 24,Moving-Average,46.15004583660541,0.05419905815213889,10,8,8,1.0
36
- 24,ARIMA,158.4575144359654,2.4357223332839517,11,8,8,1.0
37
- 24,ETS,274.4663647782223,3.0878543129477825,12,8,8,1.0
38
  36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
39
  36,Moving-Average,1208318634.7525988,1.0,2,1,1,1.0
40
  36,ARIMA,1083193423.3268,342.79755336616876,3,1,1,1.0
 
1
  prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
 
 
 
 
 
 
 
 
 
 
 
 
2
  12,Chronos-2,0.8294476545156683,38.946376459967496,1,2,2,1.0
3
  12,TiRex,0.847802672121473,30.22591777828443,2,2,2,1.0
4
  12,Moirai-2.0,0.7551088053055054,483.94979926515697,3,2,2,1.0
 
11
  12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
12
  12,Toto-1.0,296910.5495133771,13406.731654855768,11,2,2,1.0
13
  12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
14
+ 24,TiRex,6.756496163289516,0.7744482076348079,1,7,7,1.0
15
+ 24,Chronos-2,7.5292623256725335,0.37204959265128773,2,7,7,1.0
16
+ 24,Toto-1.0,117.08635389952524,0.7751671490693114,3,7,7,1.0
17
+ 24,TabPFN-TS,2.9142082085464702,0.23251215265324596,4,7,7,1.0
18
+ 24,Moirai-2.0,15.193410236369886,0.5487600429428899,5,7,7,1.0
19
+ 24,Sundial,32.09989910427459,0.591233639652137,6,7,7,1.0
20
+ 24,Seasonal-Naive,1.0,1.0,7,7,7,1.0
21
+ 24,Chronos-Bolt,17.044935754093814,0.5161448606395037,8,7,7,1.0
22
+ 24,TimesFM-2.5,7.859510485853854,0.41705491671244116,9,7,7,1.0
23
+ 24,Moving-Average,77.66611580503375,0.03399539961874934,10,7,7,1.0
24
+ 24,ARIMA,318.62496343381406,2.8441818163453627,11,7,7,1.0
25
+ 24,ETS,583.4904598160068,3.4117380320294015,12,7,7,1.0
26
  36,Seasonal-Naive,1.0,1.0,1,1,1,1.0
27
  36,Moving-Average,1208318634.7525988,1.0,2,1,1,1.0
28
  36,ARIMA,1083193423.3268,342.79755336616876,3,1,1,1.0
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,5.774975006020239,5.646181090823145,1,14,14,1.0
3
- Overall,Chronos-2,7.145030886581356,4.44572064522782,2,14,14,1.0
4
- Overall,Moirai-2.0,11.238482524527065,7.976714576170561,3,14,14,1.0
5
- Overall,Moving-Average,35.35372366234358,0.4217764566963194,4,14,14,1.0
6
- Overall,Seasonal-Naive,1.0,1.0,5,14,14,1.0
7
- Overall,ARIMA,73.34125083823173,5.749266231793158,6,14,14,1.0
8
- Overall,Toto-1.0,439.2371205401317,15.505646734653837,7,14,14,1.0
9
- Overall,Sundial,24.74388106301975,7.864794822974638,8,14,14,1.0
10
- Overall,TabPFN-TS,5.019807509828724,2.306438364864622,9,14,14,1.0
11
- Overall,TimesFM-2.5,6.716812811069544,2.9647404539042026,10,14,14,1.0
12
- Overall,Chronos-Bolt,15.624470605913055,10.848082782604182,11,14,14,1.0
13
- Overall,ETS,105.26199831669565,9.475730029675217,12,14,14,1.0
 
1
  overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
+ Overall,TiRex,8.353354354823885,7.982599955499262,1,12,12,1.0
3
+ Overall,Chronos-2,10.341434437439744,5.892070589574432,2,12,12,1.0
4
+ Overall,Toto-1.0,1119.0489777773864,24.26293090185123,3,12,12,1.0
5
+ Overall,Moirai-2.0,17.129730806331033,11.634687735117273,4,12,12,1.0
6
+ Overall,Seasonal-Naive,1.0,1.0,5,12,12,1.0
7
+ Overall,Moving-Average,67.55410612788627,0.37298957745710887,6,12,12,1.0
8
+ Overall,TabPFN-TS,6.651725853133647,2.575242972556257,7,12,12,1.0
9
+ Overall,TimesFM-2.5,9.900938534912244,3.5481404126522627,8,12,12,1.0
10
+ Overall,Sundial,44.64611919685413,11.244418242242466,9,12,12,1.0
11
+ Overall,ARIMA,161.35690780763707,8.315271787203065,10,12,12,1.0
12
+ Overall,Chronos-Bolt,24.71667942750833,16.098621969410704,11,12,12,1.0
13
+ Overall,ETS,238.88965993603242,13.98997749855162,12,12,12,1.0
results/dataset_eval_intervals.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
  "binance_btcusdt_1h_close": 300,
 
3
  "data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd": 2592000,
4
  "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total": 900,
5
  "data_gov_sg_singapore_taxi_availability_available_taxi_count": 300,
 
1
  {
2
  "binance_btcusdt_1h_close": 300,
3
+ "coingecko_bitcoin_7d_price_usd": 300,
4
  "data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd": 2592000,
5
  "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total": 900,
6
  "data_gov_sg_singapore_taxi_availability_available_taxi_count": 300,
results/dataset_properties.csv CHANGED
@@ -1,6 +1,5 @@
1
  dataset,domain,frequency,num_variates
2
  binance_btcusdt_1h_close,Finance,1h,1
3
- coingecko_bitcoin_7d_price_usd,Finance,1h,1
4
  data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd,Finance,M,1
5
  data_gov_sg_singapore_rainfall_5min_rainfall_5min_total,Climate,5min,1
6
  data_gov_sg_singapore_taxi_availability_available_taxi_count,Transportation,5min,1
@@ -12,4 +11,3 @@ open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
12
  open_meteo_shanghai_hourly_temperature_2m,Weather,1h,1
13
  usgs_earthquake_all_week_hourly_earthquake_count,Hazards,1h,1
14
  usgs_potomac_iv_usgs_00060,Hydrology,15min,1
15
- wikimedia_time_series_hourly_pageviews,Web,1D,1
 
1
  dataset,domain,frequency,num_variates
2
  binance_btcusdt_1h_close,Finance,1h,1
 
3
  data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd,Finance,M,1
4
  data_gov_sg_singapore_rainfall_5min_rainfall_5min_total,Climate,5min,1
5
  data_gov_sg_singapore_taxi_availability_available_taxi_count,Transportation,5min,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
 
results/online_status.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "status": "ok",
3
  "evaluation_protocol": "issue-now-score-later",
4
  "metric_version": "livehouse-canonical-v1",
5
- "started_at": "2026-07-27T10:39:45.214847+00:00",
6
- "finished_at": "2026-07-27T10:39:50.946321+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 3,
@@ -11,7 +11,13 @@
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": "2026-07-27T10:39:47.133617+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": "2026-07-27T10:39:47.133626+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": "2026-07-27T10:39:47.133627+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": "2026-07-27T10:39:47.133628+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": "2026-07-27T10:39:47.133630+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": "2026-07-27T10:39:47.133630+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": "2026-07-27T10:39:47.133632+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": "2026-07-27T10:39:47.133632+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": "2026-07-27T10:39:47.133633+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": "2026-07-27T10:39:47.133634+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": "2026-07-27T10:39:47.133635+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": "2026-07-27T10:39:47.133636+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": "2026-07-27T10:40:37.393174+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": "2026-07-27T10:51:25.986558+00:00",
6
+ "finished_at": "2026-07-27T10:51:33.126731+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 3,
 
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": "2026-07-27T10:51:29.050595+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": "2026-07-27T10:51:29.050603+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": "2026-07-27T10:51:29.050605+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": "2026-07-27T10:51:29.050606+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": "2026-07-27T10:51:29.050607+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": "2026-07-27T10:51:29.050608+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": "2026-07-27T10:51:29.050609+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": "2026-07-27T10:51:29.050610+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": "2026-07-27T10:51:29.050611+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": "2026-07-27T10:51:29.050612+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": "2026-07-27T10:51:29.050613+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": "2026-07-27T10:51:29.050614+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
  }