ziyuzhou02 commited on
Commit
4fb8bf7
·
verified ·
1 Parent(s): 5257910

Update leaderboard results from local eval

Browse files
results/aggregates/live_metadata.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "generated_at": "2026-07-27T23:40:55.846725+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": "2026-07-28T01:02:51.013205+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": "2026-07-27T23:40:53.793207+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": "2026-07-28T01:02:49.053656+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,Moirai-2.0,1.4824060116514644,14.748371632894651,9,5,5,1.0
11
  Climate,ARIMA,7.768114077941136,34.84406300542313,10,5,5,1.0
12
  Climate,Moving-Average,4.448829912179885,27.760038786622744,11,5,5,1.0
13
  Climate,ETS,41.67150566777602,91.51964639360355,12,5,5,1.0
14
- Finance,Sundial,0.19445980585053715,0.4743818504842995,1,3,3,1.0
15
- Finance,Toto-1.0,0.9947021774741156,0.5950506929520395,2,3,3,1.0
16
- Finance,Chronos-Bolt,0.4199809081352074,0.6752307614065016,3,3,3,1.0
17
- Finance,Moirai-2.0,0.5671540412820155,0.6826931781544368,4,3,3,1.0
18
- Finance,TiRex,0.4809226366262122,0.659726851800773,5,3,3,1.0
19
- Finance,TimesFM-2.5,0.47441744573781885,0.6306218519694167,6,3,3,1.0
20
- Finance,Chronos-2,0.6332301204356406,0.7064421109615494,7,3,3,1.0
21
- Finance,Moving-Average,0.487799996024218,0.6635190074539776,8,3,3,1.0
22
- Finance,TabPFN-TS,0.4489120413494622,0.7033657254188453,9,3,3,1.0
23
- Finance,ETS,1.1616593432036997,1.0465162529631655,10,3,3,1.0
24
- Finance,ARIMA,1.0573085089666414,1.5807217993353238,11,3,3,1.0
25
- Finance,Seasonal-Naive,1.0,1.0,12,3,3,1.0
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-1.0,50341153.673178256,277943555.25179964,12,1,1,1.0
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,7.768114077941136,34.84406300542313,10,5,5,1.0
12
  Climate,Moving-Average,4.448829912179885,27.760038786622744,11,5,5,1.0
13
  Climate,ETS,41.67150566777602,91.51964639360355,12,5,5,1.0
14
+ Finance,Sundial,0.09952901750099762,0.368263120192457,1,2,2,1.0
15
+ Finance,TimesFM-2.5,0.36989863532881,0.5604116791822299,2,2,2,1.0
16
+ Finance,Toto-1.0,1.2481366622293906,0.5744141563175763,3,2,2,1.0
17
+ Finance,TiRex,0.39338522835316736,0.6627981567759068,4,2,2,1.0
18
+ Finance,TabPFN-TS,0.32911000269320434,0.6243785441568039,5,2,2,1.0
19
+ Finance,Chronos-Bolt,0.33195408280557637,0.6970978498460929,6,2,2,1.0
20
+ Finance,Moving-Average,0.35423580404413224,0.5733245263298223,7,2,2,1.0
21
+ Finance,Moirai-2.0,0.5656424724531764,0.7463752724135839,8,2,2,1.0
22
+ Finance,Chronos-2,0.6075099051917358,0.7400319231159583,9,2,2,1.0
23
+ Finance,Seasonal-Naive,1.0,1.0,10,2,2,1.0
24
+ Finance,ETS,1.438062507760955,1.2197892953489888,11,2,2,1.0
25
+ Finance,ARIMA,1.2583538765342204,2.2658873562028767,12,2,2,1.0
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-1.0,50341153.673178256,277943555.25179964,12,1,1,1.0
 
 
 
 
 
 
 
 
 
 
 
 
results/aggregates/results_by_frequency.csv CHANGED
@@ -23,18 +23,6 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
23
  15min,TabPFN-TS,1.7823948120487276,1.6723544394535688,10,1,1,1.0
24
  15min,ETS,2.3101830377998778,1.8643116894683234,11,1,1,1.0
25
  15min,ARIMA,1.7969075767873166,2.166778271475671,12,1,1,1.0
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,Toto-1.0,3.631265561890252,0.7862624882593825,1,7,7,1.0
39
  1h,TiRex,0.7550528102997923,0.886617366686293,2,7,7,1.0
40
  1h,Sundial,0.8504551179293129,0.823347513995428,3,7,7,1.0
@@ -47,18 +35,6 @@ frequency,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
47
  1h,Moving-Average,2.089917990633689,1.4725595797214652,10,7,7,1.0
48
  1h,ARIMA,4.428904238820278,2.541255453576966,11,7,7,1.0
49
  1h,ETS,15.453136887947402,4.288675039942574,12,7,7,1.0
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
53
- 1mo,Chronos-2,0.6879834115815433,0.6437671766189335,4,1,1,1.0
54
- 1mo,TiRex,0.7187693708563099,0.6536268717700132,5,1,1,1.0
55
- 1mo,ARIMA,0.7464480695996939,0.7692893066778397,6,1,1,1.0
56
- 1mo,ETS,0.7580203095992263,0.7703148978390245,7,1,1,1.0
57
- 1mo,Sundial,0.7423182015400501,0.7871685560956725,8,1,1,1.0
58
- 1mo,TimesFM-2.5,0.7803986235065251,0.7985326751147283,9,1,1,1.0
59
- 1mo,Moving-Average,0.9249973049108767,0.8887079460534169,10,1,1,1.0
60
- 1mo,TabPFN-TS,0.8352213750339312,0.8925810519947165,11,1,1,1.0
61
- 1mo,Seasonal-Naive,1.0,1.0,12,1,1,1.0
62
  5min,Seasonal-Naive,1.0,1.0,1,2,2,1.0
63
  5min,TabPFN-TS,1.0,1.0,2,2,2,1.0
64
  5min,TimesFM-2.5,1.0,1.0,3,2,2,1.0
 
23
  15min,TabPFN-TS,1.7823948120487276,1.6723544394535688,10,1,1,1.0
24
  15min,ETS,2.3101830377998778,1.8643116894683234,11,1,1,1.0
25
  15min,ARIMA,1.7969075767873166,2.166778271475671,12,1,1,1.0
 
 
 
 
 
 
 
 
 
 
 
 
26
  1h,Toto-1.0,3.631265561890252,0.7862624882593825,1,7,7,1.0
27
  1h,TiRex,0.7550528102997923,0.886617366686293,2,7,7,1.0
28
  1h,Sundial,0.8504551179293129,0.823347513995428,3,7,7,1.0
 
35
  1h,Moving-Average,2.089917990633689,1.4725595797214652,10,7,7,1.0
36
  1h,ARIMA,4.428904238820278,2.541255453576966,11,7,7,1.0
37
  1h,ETS,15.453136887947402,4.288675039942574,12,7,7,1.0
 
 
 
 
 
 
 
 
 
 
 
 
38
  5min,Seasonal-Naive,1.0,1.0,1,2,2,1.0
39
  5min,TabPFN-TS,1.0,1.0,2,2,2,1.0
40
  5min,TimesFM-2.5,1.0,1.0,3,2,2,1.0
results/aggregates/results_by_prediction_length.csv CHANGED
@@ -1,28 +1,16 @@
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
17
- 12,TimesFM-2.5,0.883401733927733,0.8936065549864372,4,2,2,1.0
18
- 12,Chronos-Bolt,0.8576213668056174,1427.1372538860771,5,2,2,1.0
19
- 12,TabPFN-TS,0.9139044671265871,0.9447650776752475,6,2,2,1.0
20
- 12,Sundial,0.8615789003568101,128.99937631337272,7,2,2,1.0
21
- 12,ARIMA,0.8639722620545719,438.7361038019728,8,2,2,1.0
22
- 12,Seasonal-Naive,1.0,1.0,9,2,2,1.0
23
- 12,ETS,0.8706436180201554,439.02846065451104,10,2,2,1.0
24
- 12,Toto-1.0,5639.479792962678,13322.450572675643,11,2,2,1.0
25
- 12,Moving-Average,0.9617678019724286,471.56119324419365,12,2,2,1.0
26
  24,TiRex,0.8393124614051559,0.9225291259963043,1,8,8,1.0
27
  24,Toto-1.0,3.221488937183407,0.8424427873415189,2,8,8,1.0
28
  24,Moirai-2.0,1.0996765234197958,0.9902855253418892,3,8,8,1.0
 
1
  prediction_length,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
+ 12,Seasonal-Naive,1.0,1.0,1,1,1,1.0
3
+ 12,TabPFN-TS,1.0,1.0,2,1,1,1.0
4
+ 12,TimesFM-2.5,1.0,1.0,3,1,1,1.0
5
+ 12,TiRex,1.0,1397.7486927145103,4,1,1,1.0
6
+ 12,Chronos-2,1.0,2356.162747109683,5,1,1,1.0
7
+ 12,Sundial,1.0,21140.1217190091,6,1,1,1.0
8
+ 12,ARIMA,1.0,250217.138218906,7,1,1,1.0
9
+ 12,ETS,1.0,250217.138218906,8,1,1,1.0
10
+ 12,Moving-Average,1.0,250217.138218906,9,1,1,1.0
11
+ 12,Moirai-2.0,1.0,410051.5180343537,10,1,1,1.0
12
+ 12,Chronos-Bolt,1.094103907762285,3214861.8499168884,11,1,1,1.0
13
+ 12,Toto-1.0,50341153.673178256,277943555.25179964,12,1,1,1.0
 
 
 
 
 
 
 
 
 
 
 
 
14
  24,TiRex,0.8393124614051559,0.9225291259963043,1,8,8,1.0
15
  24,Toto-1.0,3.221488937183407,0.8424427873415189,2,8,8,1.0
16
  24,Moirai-2.0,1.0996765234197958,0.9902855253418892,3,8,8,1.0
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,0.703393241439027,2.487920264306921,1,14,14,1.0
3
- Overall,Sundial,0.7317203685052369,3.4971862653133186,2,14,14,1.0
4
- Overall,Chronos-2,0.7609184058549149,2.383744211554301,3,14,14,1.0
5
- Overall,TimesFM-2.5,0.7658651758591832,0.8853652606290402,4,14,14,1.0
6
- Overall,Moirai-2.0,1.034855488960128,5.861708922220037,5,14,14,1.0
7
- Overall,Toto-1.0,48.273768089052126,13.15836737780422,6,14,14,1.0
8
- Overall,Seasonal-Naive,1.0,1.0,7,14,14,1.0
9
- Overall,TabPFN-TS,0.8204778598140972,0.9550955125482756,8,14,14,1.0
10
- Overall,Chronos-Bolt,0.983158788785599,5.880150827877197,9,14,14,1.0
11
- Overall,Moving-Average,1.2654153157880021,6.624155488526724,10,14,14,1.0
12
- Overall,ARIMA,2.2049738892736177,9.601367184262196,11,14,14,1.0
13
- Overall,ETS,4.400531481318116,12.73349124682922,12,14,14,1.0
 
1
  overall,model,MSE,CRPS,Rank,n_configs,n_group_configs,coverage
2
+ Overall,TiRex,0.7274124589463101,3.133231764528986,1,12,12,1.0
3
+ Overall,Sundial,0.786396301241797,4.635469062321733,2,12,12,1.0
4
+ Overall,Chronos-2,0.8016861795629415,2.993414992250487,3,12,12,1.0
5
+ Overall,TimesFM-2.5,0.8215330246701777,0.9189556267630763,4,12,12,1.0
6
+ Overall,Seasonal-Naive,1.0,1.0,5,12,12,1.0
7
+ Overall,TabPFN-TS,0.8158200209107423,0.9565070855775092,6,12,12,1.0
8
+ Overall,Toto-1.0,94.37845208105712,21.618942395242758,7,12,12,1.0
9
+ Overall,Moving-Average,1.419222942029952,9.638787245937582,8,12,12,1.0
10
+ Overall,Chronos-Bolt,1.0949882640042732,8.514267128835796,9,12,12,1.0
11
+ Overall,Moirai-2.0,1.1753009673612107,8.720370995044656,10,12,12,1.0
12
+ Overall,ARIMA,2.8127465532292644,15.210837874073626,11,12,12,1.0
13
+ Overall,ETS,6.191598473811765,20.918024408446165,12,12,12,1.0
results/dataset_properties.csv CHANGED
@@ -1,7 +1,6 @@
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
7
  nasa_power_shanghai_hourly_t2m,Weather,1h,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
  coingecko_bitcoin_7d_price_usd,Finance,1h,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
6
  nasa_power_shanghai_hourly_t2m,Weather,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
 
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": "2026-07-27T23:40:47.118767+00:00",
6
- "finished_at": "2026-07-27T23:40:55.875758+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 4,
@@ -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": "2026-07-27T23:40:51.541579+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": "2026-07-27T23:40:51.541586+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": "2026-07-27T23:40:51.541587+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": "2026-07-27T23:40:51.541588+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": "2026-07-27T23:40:51.541589+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": "2026-07-27T23:40:51.541590+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": "2026-07-27T23:40:51.541591+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": "2026-07-27T23:40:51.541592+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": "2026-07-27T23:40:51.541594+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": "2026-07-27T23:40:51.541594+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": "2026-07-27T23:40:51.541595+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": "2026-07-27T23:40:51.541596+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": "2026-07-28T00:51:18.371820+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": "2026-07-28T01:02:45.223130+00:00",
6
+ "finished_at": "2026-07-28T01:02:51.024032+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
  "task_count": 4,
 
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": "2026-07-28T01:02:47.761732+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": "2026-07-28T01:02:47.761740+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": "2026-07-28T01:02:47.761741+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": "2026-07-28T01:02:47.761742+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": "2026-07-28T01:02:47.761743+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": "2026-07-28T01:02:47.761744+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": "2026-07-28T01:02:47.761745+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": "2026-07-28T01:02:47.761746+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": "2026-07-28T01:02:47.761746+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": "2026-07-28T01:02:47.761747+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": "2026-07-28T01:02:47.761748+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": "2026-07-28T01:02:47.761749+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
  }