Website data through 2026-11-04

site/index.json

@@ -1 +1 @@
-{"generated_at":"2026-11-04T01:40:52+00:00","results":"Chennzi/agentic-forecasting-results","github":"https://github.com/rowingchenn/agentic-forecasting-tasks","taxonomy":{"version":1,"domains":[{"id":"energy","name":"Energy","leaves":[{"id":"electricity-demand","name":"Electricity demand","examples":["ERCOT daily peak load","PJM daily load","CAISO daily load"]},{"id":"gas-demand","name":"Gas demand","examples":["GB NTS gas demand","AEMO Victoria gas demand"]},{"id":"renewable-generation","name":"Renewable generation","examples":["ERCOT daily wind output","CAISO daily solar output"]},{"id":"fuel-inventories","name":"Fuel inventories","examples":["EIA weekly natural gas storage","EIA weekly crude oil inventories"]},{"id":"energy-prices","name":"Energy prices","examples":["Henry Hub natural gas spot","US retail gasoline price"]}]},{"id":"health","name":"Public health","leaves":[{"id":"respiratory-illness","name":"Respiratory illness","examples":["CDC ILINet","influenza hospital admissions","COVID-19 hospital admissions"]},{"id":"other-infectious-disease","name":"Other infectious disease","examples":["Dengue cases","norovirus outbreaks"]},{"id":"health-care-use","name":"Health-care use","examples":["Emergency department visits"]}]},{"id":"economy","name":"Economy and labor","leaves":[{"id":"labor-market","name":"Labor market","examples":["US initial jobless claims"]},{"id":"consumer-prices","name":"Consumer prices","examples":["Food price indices","used car prices"]},{"id":"economic-activity","name":"Economic activity","examples":["Retail foot traffic","freight volumes"]},{"id":"bank-liquidity","name":"Bank liquidity","examples":["Norges Bank structural liquidity","ECB excess liquidity"]}]},{"id":"markets","name":"Financial markets","leaves":[{"id":"commodities","name":"Commodities","examples":["Corn futures","crude oil futures"]},{"id":"currencies","name":"Currencies","examples":["USD/JPY"]},{"id":"equities","name":"Equities and volatility","examples":["S&P 500 index","VIX"]}]},{"id":"environment","name":"Environment","leaves":[{"id":"weather","name":"Weather","examples":["Daily maximum air temperature","daily precipitation"]},{"id":"air-quality","name":"Air quality","examples":["PM2.5 concentration","ozone"]},{"id":"hydrology","name":"Hydrology","examples":["River discharge","reservoir storage"]},{"id":"natural-hazards","name":"Natural hazards","examples":["Wildfire burned area"]}]},{"id":"space","name":"Space","leaves":[{"id":"space-weather","name":"Space weather","examples":["Planetary Kp index","solar wind speed"]}]},{"id":"mobility","name":"Transport and mobility","leaves":[{"id":"air-travel","name":"Air travel","examples":["TSA checkpoint throughput"]},{"id":"ground-transport","name":"Ground transport","examples":["Transit ridership","road traffic counts"]}]},{"id":"attention","name":"Online attention","leaves":[{"id":"search-and-page-views","name":"Search and page views","examples":["Wikipedia page views","Google Trends interest"]},{"id":"media-and-social","name":"Media and social activity","examples":["News article volume","GitHub stars"]}]}],"facets":{"driver":{"weather":"Weather and climate","epidemic":"Disease transmission","economic":"Economic conditions and policy","behavioral":"Human behavior and events","market":"Market expectations","solar":"Solar activity"},"tradable":{"true":"Tradable price (control)","false":"Not tradable"}}},"systems":[{"id":"claude-code-claude-sonnet-5","kind":"agent","label":"Claude Code \u00b7 Sonnet 5","description":"Anthropic Claude Code 2.1.227 running claude-sonnet-5 with its default tools in bypassPermissions mode. Live runs add the open internet; the agent receives no data.","sort":0},{"id":"claude-code-claude-sonnet-5-continual","kind":"agent","label":"Claude Code \u00b7 Sonnet 5 \u00b7 continual","description":"The same Claude Code agent, continuing on every run day from a snapshot of the sandbox and native session of its previous run day (ALE --continue-from). Its earlier submissions are in /home/user/history/, and it is asked to compare them with the values published since and improve how it forecasts.","sort":0},{"id":"codex-cli-gpt-6.1-sol","kind":"agent","label":"Codex \u00b7 GPT-6.1 Sol","description":"OpenAI Codex CLI 0.146.0 running gpt-6.1-sol with its default settings: no approval prompts, no command sandbox, and its built-in web search. Live runs add the open internet; the agent receives no data.","sort":0},{"id":"codex-cli-gpt-6.1-sol-continual","kind":"agent","label":"Codex \u00b7 GPT-6.1 Sol \u00b7 continual","description":"The same Codex agent, continuing on every run day from a snapshot of the sandbox and native session of its previous run day (ALE --continue-from). Its earlier submissions are in /home/user/history/, and it is asked to compare them with the values published since and improve how it forecasts.","sort":0},{"id":"eccc-official","kind":"expert","label":"ECCC official","description":"ECCC's 06:00 AQHI forecast for the community on the run date, the first issue after the cutoff, which the agents cannot see. Its \"Today\" period gives the run date and its \"Tomorrow\" period the day after; each is ECCC's forecast maximum for 06:00 to 18:00, a whole number, with 10+ counted as 11. It is recorded the next day.","sort":1},{"id":"ercot-official","kind":"expert","label":"ERCOT official","description":"The forecast model ERCOT flags as in use, first version posted after the cutoff (the 09:30 version), which the agents cannot see; it is recorded the next day; the daily maximum of its hourly system total.","sort":1},{"id":"nws-official","kind":"expert","label":"NWS official","description":"The first river forecast the NWS issues for the gauge after the cutoff, normally its evening forecast of the run date, which the agents cannot see; the mean of its four six-hourly stage values on each date. It is recorded the next day.","sort":1},{"id":"chronos-2","kind":"tsfm","label":"Chronos-2 \u00b7 curated","description":"Curated TSFM: Amazon Chronos-2, zero-shot, given the run day's curated input: the target history plus the covariates the task's author chose, for the past and the forecast window, without the earlier expert forecast.","sort":2},{"id":"chronos-2-expert","kind":"tsfm","label":"Chronos-2 \u00b7 curated + expert","description":"Chronos-2 \u00b7 curated, plus the expert forecast's latest version before each snapshot as one more covariate. The version the run is compared with comes after the cutoff and is not included. The pair isolates what the earlier expert forecast adds.","sort":2},{"id":"chronos-2-univariate","kind":"tsfm","label":"Chronos-2 \u00b7 history only","description":"Amazon Chronos-2, zero-shot, given only the target history.","sort":2},{"id":"timesfm-3","kind":"tsfm","label":"TimesFM-3 \u00b7 curated","description":"Curated TSFM: Google TimesFM 3.0 (331M), zero-shot, given the run day's curated input with every known covariate for the past and the forecast window, without the earlier expert forecast. Weights under Google's non-commercial license.","sort":2},{"id":"timesfm-3-expert","kind":"tsfm","label":"TimesFM-3 \u00b7 curated + expert","description":"TimesFM-3 \u00b7 curated, plus the expert forecast's latest version before each snapshot as one more covariate. The version the run is compared with comes after the cutoff and is not included. The pair isolates what the earlier expert forecast adds.","sort":2},{"id":"seasonal-naive","kind":"reference","label":"Seasonal naive","description":"The value on the same weekday in the latest observed week. It is the denominator of every scaled score, so its own scaled score is 1.","sort":3}],"tasks":[{"id":"ercot_peak_load","title":"ERCOT daily peak load","question":"How high will electricity demand on the Texas grid peak on each of the next seven days?","summary":"The highest hourly electricity demand of each day on the ERCOT grid, which serves about 90% of Texas load. Weather drives it, and grid notices and news add information that history alone does not contain.","taxonomy":"energy/electricity-demand","driver":"weather","tradable":false,"domain":"Electricity demand","region":"Texas (ERCOT grid)","unit":"MW","schedule":{"snapshot":"07:05","every_days":1,"first_run":"2026-10-16","timezone":"America/Chicago","cutoff":"09:25"},"horizons":[1,2,3,4,5,6,7],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"baseline":"ERCOT official","baseline_visible":false,"live_since":"2026-10-24","latest_run":"2026-11-03","run_days":10,"next_run":"2026-11-04T07:05:00-06:00","last_observed":"2026-11-02","leaderboard":[{"system":"chronos-2","n":33,"scaled_crps":0.5111289225290981,"scaled_mae":0.6609930257929812,"crps":1986.7392255892266,"mae":2569.255454545456,"coverage80":0.6060606060606061},{"system":"chronos-2-expert","n":33,"scaled_crps":0.33551974076304925,"scaled_mae":0.4208059762790583,"crps":1304.1528282828294,"mae":1635.657272727274,"coverage80":0.48484848484848486},{"system":"chronos-2-univariate","n":33,"scaled_crps":0.6260526576615838,"scaled_mae":0.8267282441741152,"crps":2433.443535353536,"mae":3213.462121212123,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5","n":33,"scaled_crps":0.33078061462853287,"scaled_mae":0.43025730612463853,"crps":1285.7320202020212,"mae":1672.3942424242439,"coverage80":0.8484848484848485},{"system":"codex-cli-gpt-6.1-sol","n":33,"scaled_crps":0.28581102007555237,"scaled_mae":0.35019448852255014,"crps":1110.9368686868695,"mae":1361.1930303030315,"coverage80":0.9696969696969697},{"system":"ercot-official","n":33,"scaled_crps":0.35215496588518375,"scaled_mae":0.35215496588518375,"crps":1368.8133333333344,"mae":1368.8133333333344,"coverage80":null},{"system":"seasonal-naive","n":33,"scaled_crps":1.0,"scaled_mae":1.0,"crps":3886.9630303030312,"mae":3886.9630303030312,"coverage80":null},{"system":"timesfm-3","n":33,"scaled_crps":0.4243866932474492,"scaled_mae":0.561005483910552,"crps":1649.575387205388,"mae":2180.6075757575777,"coverage80":0.6666666666666666},{"system":"timesfm-3-expert","n":33,"scaled_crps":0.2640867725993001,"scaled_mae":0.3547525379711419,"crps":1026.495521885523,"mae":1378.9100000000008,"coverage80":0.7575757575757576}],"truth":[{"date":"2026-09-07","value":86412.36},{"date":"2026-09-08","value":86278.55},{"date":"2026-09-09","value":85931.94},{"date":"2026-09-10","value":84538.73},{"date":"2026-09-11","value":85799.88},{"date":"2026-09-12","value":86491.57},{"date":"2026-09-13","value":86049.84},{"date":"2026-09-14","value":86157.25},{"date":"2026-09-15","value":86129.24},{"date":"2026-09-16","value":86167.87},{"date":"2026-09-17","value":82811.92},{"date":"2026-09-18","value":83098.65},{"date":"2026-09-19","value":82789.85},{"date":"2026-09-20","value":83005.03},{"date":"2026-09-21","value":85925.71},{"date":"2026-09-22","value":85311.93},{"date":"2026-09-23","value":85059.79},{"date":"2026-09-24","value":83426.9},{"date":"2026-09-25","value":81227.32},{"date":"2026-09-26","value":78487.51},{"date":"2026-09-27","value":81585.99},{"date":"2026-09-28","value":82504.9},{"date":"2026-09-29","value":80912.32},{"date":"2026-09-30","value":77838.24},{"date":"2026-10-01","value":66732.03},{"date":"2026-10-02","value":66602.18},{"date":"2026-10-03","value":62432.53},{"date":"2026-10-04","value":60263.42},{"date":"2026-10-05","value":69952.07},{"date":"2026-10-06","value":72381.47},{"date":"2026-10-07","value":73189.81},{"date":"2026-10-08","value":75120.38},{"date":"2026-10-09","value":73917.77},{"date":"2026-10-10","value":71643.27},{"date":"2026-10-11","value":73217.47},{"date":"2026-10-12","value":76145.36},{"date":"2026-10-13","value":81169.2},{"date":"2026-10-14","value":79009.83},{"date":"2026-10-15","value":74982.12},{"date":"2026-10-16","value":54532.28},{"date":"2026-10-17","value":49594.28},{"date":"2026-10-18","value":52374.04},{"date":"2026-10-19","value":56965.61},{"date":"2026-10-20","value":60239.11},{"date":"2026-10-21","value":63001.08},{"date":"2026-10-22","value":63381.26},{"date":"2026-10-23","value":63943.77},{"date":"2026-10-24","value":62087.1},{"date":"2026-10-25","value":58287.79},{"date":"2026-10-26","value":60005.82},{"date":"2026-10-27","value":61064.31},{"date":"2026-10-28","value":63406.9},{"date":"2026-10-29","value":59702.77},{"date":"2026-10-31","value":59794.65},{"date":"2026-11-01","value":62940.51},{"date":"2026-11-02","value":65881.05}]},{"id":"mississippi_st_louis_stage","title":"Mississippi River stage at St. Louis","question":"How high will the Mississippi River be at St. Louis, on average, on each of the next 13 days?","summary":"The daily mean water level of the Mississippi at the St. Louis gauge, just below the mouth of the Missouri River. Barge traffic depends on it: below about 1 ft, barges may have to carry lighter loads. Rain and snowmelt across the upper Mississippi and Missouri basins drive it days to weeks later, and river forecasts, reservoir releases and navigation notices add information that history alone does not contain.","taxonomy":"environment/hydrology","driver":"weather","tradable":false,"domain":"Hydrology","region":"St. Louis, Missouri (Mississippi River)","unit":"ft","schedule":{"snapshot":"16:50","every_days":1,"first_run":"2026-10-29","timezone":"America/Chicago","cutoff":"18:40"},"horizons":[1,2,3,4,5,6,7,8,9,10,11,12,13],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"baseline":"NWS official","baseline_visible":false,"live_since":"2026-10-29","latest_run":"2026-11-03","run_days":6,"next_run":"2026-11-04T16:50:00-06:00","last_observed":"2026-11-02","leaderboard":[{"system":"chronos-2","n":8,"scaled_crps":0.2730185147113129,"scaled_mae":0.37521992714487307,"crps":1.0252418873648492,"mae":1.4090296648550724,"coverage80":0.75},{"system":"chronos-2-expert","n":8,"scaled_crps":0.09872081289329346,"scaled_mae":0.13293353510613765,"crps":0.37071739489878064,"mae":0.4991933553312628,"coverage80":0.625},{"system":"chronos-2-univariate","n":8,"scaled_crps":0.3568379056819871,"scaled_mae":0.4291885958479616,"crps":1.3400013119680239,"mae":1.611693355331263,"coverage80":0.75},{"system":"claude-code-claude-sonnet-5","n":8,"scaled_crps":0.0876654037608079,"scaled_mae":0.10288832230203276,"crps":0.3292020107257877,"mae":0.38636726837474095,"coverage80":0.375},{"system":"codex-cli-gpt-6.1-sol","n":8,"scaled_crps":0.0867518218196759,"scaled_mae":0.10240650380029709,"crps":0.3257713185817805,"mae":0.3845579386645961,"coverage80":1.0},{"system":"nws-official","n":8,"scaled_crps":0.09627415085088606,"scaled_mae":0.09627415085088606,"crps":0.3615296648550725,"mae":0.3615296648550725,"coverage80":null},{"system":"seasonal-naive","n":8,"scaled_crps":1.0,"scaled_mae":1.0,"crps":3.7552101125776396,"mae":3.7552101125776396,"coverage80":null},{"system":"timesfm-3","n":8,"scaled_crps":0.20382206687866122,"scaled_mae":0.23279479153596588,"crps":0.7653946867092246,"mae":0.8741933553312626,"coverage80":0.875},{"system":"timesfm-3-expert","n":8,"scaled_crps":0.0715751544853244,"scaled_mae":0.10754851426875808,"crps":0.26877974393259696,"mae":0.4038672683747409,"coverage80":1.0}],"truth":[{"date":"2026-09-08","value":-0.9465853658536586},{"date":"2026-09-09","value":-1.166111111111111},{"date":"2026-09-10","value":-0.8307499999999999},{"date":"2026-09-11","value":-0.2272916666666666},{"date":"2026-09-12","value":0.5810416666666667},{"date":"2026-09-13","value":2.426875},{"date":"2026-09-14","value":3.0060416666666665},{"date":"2026-09-15","value":1.3766666666666667},{"date":"2026-09-16","value":0.7833333333333333},{"date":"2026-09-17","value":1.8091666666666668},{"date":"2026-09-18","value":3.7385416666666655},{"date":"2026-09-19","value":5.570625},{"date":"2026-09-20","value":7.413958333333333},{"date":"2026-09-21","value":9.941666666666666},{"date":"2026-09-22","value":12.197083333333332},{"date":"2026-09-23","value":14.26304347826087},{"date":"2026-09-24","value":14.531063829787234},{"date":"2026-09-25","value":15.239574468085106},{"date":"2026-09-26","value":15.83608695652174},{"date":"2026-09-27","value":16.145652173913046},{"date":"2026-09-28","value":15.769565217391303},{"date":"2026-09-29","value":14.377916666666666},{"date":"2026-09-30","value":12.940833333333332},{"date":"2026-10-01","value":11.278541666666667},{"date":"2026-10-02","value":10.331458333333334},{"date":"2026-10-03","value":12.21875},{"date":"2026-10-04","value":16.39875},{"date":"2026-10-05","value":21.80458333333333},{"date":"2026-10-06","value":23.74895833333333},{"date":"2026-10-07","value":22.921458333333334},{"date":"2026-10-08","value":20.898125},{"date":"2026-10-09","value":18.805208333333333},{"date":"2026-10-10","value":16.673125000000002},{"date":"2026-10-11","value":15.039791666666666},{"date":"2026-10-12","value":13.71468085106383},{"date":"2026-10-13","value":12.589166666666666},{"date":"2026-10-14","value":12.990652173913045},{"date":"2026-10-15","value":11.280851063829788},{"date":"2026-10-16","value":11.069767441860463},{"date":"2026-10-17","value":9.949574468085109},{"date":"2026-10-18","value":9.380208333333334},{"date":"2026-10-19","value":9.475},{"date":"2026-10-20","value":8.028863636363637},{"date":"2026-10-21","value":7.666744186046512},{"date":"2026-10-22","value":8.357234042553191},{"date":"2026-10-23","value":8.49159090909091},{"date":"2026-10-24","value":7.717826086956522},{"date":"2026-10-25","value":6.5806818181818185},{"date":"2026-10-26","value":6.381555555555556},{"date":"2026-10-27","value":4.63375},{"date":"2026-10-28","value":4.232083333333333},{"date":"2026-10-29","value":5.173333333333333},{"date":"2026-10-30","value":4.4035416666666665},{"date":"2026-10-31","value":3.3229166666666665},{"date":"2026-11-01","value":2.816428571428572},{"date":"2026-11-02","value":3.1686956521739127}]},{"id":"toronto_aqhi","title":"Toronto daytime AQHI","question":"How high will Toronto's Air Quality Health Index get during the day today and tomorrow?","summary":"The highest hourly Air Quality Health Index of the day in Toronto, as observed by Environment and Climate Change Canada (ECCC). The index combines ozone, nitrogen dioxide and fine particulate matter into a health-risk scale from 1 to 10+. Weather drives it, and wildfire smoke, ECCC's forecasts and air quality statements add information that history alone does not contain.","taxonomy":"environment/air-quality","driver":"weather","tradable":false,"domain":"Air quality","region":"Toronto, Ontario","unit":"AQHI","schedule":{"snapshot":"04:05","every_days":1,"first_run":"2026-10-29","timezone":"America/Toronto","cutoff":"05:50"},"horizons":[0,1],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"baseline":"ECCC official","baseline_visible":false,"live_since":"2026-10-29","latest_run":"2026-11-03","run_days":6,"next_run":"2026-11-04T04:05:00-05:00","last_observed":"2026-11-02","leaderboard":[{"system":"chronos-2","n":9,"scaled_crps":1.1345891345891344,"scaled_mae":1.5380835380835378,"crps":0.5130864197530864,"mae":0.6955555555555555,"coverage80":0.6666666666666666},{"system":"chronos-2-expert","n":9,"scaled_crps":0.5787605787605787,"scaled_mae":0.7616707616707614,"crps":0.2617283950617284,"mae":0.34444444444444433,"coverage80":0.7777777777777778},{"system":"chronos-2-univariate","n":9,"scaled_crps":1.4447174447174447,"scaled_mae":1.9066339066339064,"crps":0.6533333333333333,"mae":0.8622222222222222,"coverage80":0.4444444444444444},{"system":"claude-code-claude-sonnet-5","n":9,"scaled_crps":0.5426153426153426,"scaled_mae":0.4471744471744472,"crps":0.24538271604938272,"mae":0.20222222222222225,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","n":9,"scaled_crps":0.3187005187005187,"scaled_mae":0.32186732186732187,"crps":0.14412345679012345,"mae":0.14555555555555555,"coverage80":1.0},{"system":"eccc-official","n":9,"scaled_crps":0.6928746928746929,"scaled_mae":0.6928746928746929,"crps":0.31333333333333335,"mae":0.31333333333333335,"coverage80":null},{"system":"seasonal-naive","n":9,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.45222222222222225,"mae":0.45222222222222225,"coverage80":null},{"system":"timesfm-3","n":9,"scaled_crps":0.8375648375648375,"scaled_mae":1.2186732186732183,"crps":0.37876543209876545,"mae":0.551111111111111,"coverage80":0.7777777777777778},{"system":"timesfm-3-expert","n":9,"scaled_crps":0.6082446082446081,"scaled_mae":0.7764127764127764,"crps":0.2750617283950617,"mae":0.35111111111111115,"coverage80":0.7777777777777778}],"truth":[{"date":"2026-09-08","value":10.0},{"date":"2026-09-09","value":2.58},{"date":"2026-09-10","value":2.31},{"date":"2026-09-11","value":3.43},{"date":"2026-09-12","value":2.84},{"date":"2026-09-13","value":2.41},{"date":"2026-09-14","value":2.2},{"date":"2026-09-15","value":2.38},{"date":"2026-09-16","value":2.72},{"date":"2026-09-17","value":2.84},{"date":"2026-09-18","value":2.06},{"date":"2026-09-19","value":1.44},{"date":"2026-09-20","value":1.81},{"date":"2026-09-21","value":1.74},{"date":"2026-09-22","value":1.98},{"date":"2026-09-23","value":2.0},{"date":"2026-09-24","value":2.05},{"date":"2026-09-25","value":2.64},{"date":"2026-09-26","value":2.13},{"date":"2026-09-27","value":3.0},{"date":"2026-09-28","value":2.32},{"date":"2026-09-29","value":2.21},{"date":"2026-09-30","value":3.07},{"date":"2026-10-01","value":3.02},{"date":"2026-10-02","value":2.29},{"date":"2026-10-03","value":1.5},{"date":"2026-10-04","value":2.21},{"date":"2026-10-05","value":1.96},{"date":"2026-10-06","value":2.49},{"date":"2026-10-07","value":3.51},{"date":"2026-10-08","value":2.43},{"date":"2026-10-09","value":2.51},{"date":"2026-10-10","value":1.65},{"date":"2026-10-11","value":2.29},{"date":"2026-10-12","value":2.75},{"date":"2026-10-13","value":3.7},{"date":"2026-10-14","value":1.55},{"date":"2026-10-15","value":1.81},{"date":"2026-10-16","value":2.0},{"date":"2026-10-17","value":1.98},{"date":"2026-10-18","value":2.38},{"date":"2026-10-19","value":3.03},{"date":"2026-10-20","value":2.34},{"date":"2026-10-21","value":2.96},{"date":"2026-10-22","value":3.55},{"date":"2026-10-23","value":2.12},{"date":"2026-10-24","value":2.39},{"date":"2026-10-25","value":3.17},{"date":"2026-10-26","value":4.56},{"date":"2026-10-27","value":2.02},{"date":"2026-10-28","value":2.15},{"date":"2026-10-29","value":4.0},{"date":"2026-10-30","value":1.69},{"date":"2026-10-31","value":2.17},{"date":"2026-11-01","value":2.9},{"date":"2026-11-02","value":3.67}]}],"continual_note":"You may have forecast this target on earlier run days in this same environment and session; if so, your earlier submissions are under `/home/user/history/<run date>/`. Compare them with the values published since, and use what you learn to improve how you forecast."}
+{"generated_at":"2026-11-04T09:22:10+00:00","results":"Chennzi/agentic-forecasting-results","github":"https://github.com/rowingchenn/agentic-forecasting-tasks","taxonomy":{"version":1,"domains":[{"id":"energy","name":"Energy","leaves":[{"id":"electricity-demand","name":"Electricity demand","examples":["ERCOT daily peak load","PJM daily load","CAISO daily load"]},{"id":"gas-demand","name":"Gas demand","examples":["GB NTS gas demand","AEMO Victoria gas demand"]},{"id":"renewable-generation","name":"Renewable generation","examples":["ERCOT daily wind output","CAISO daily solar output"]},{"id":"fuel-inventories","name":"Fuel inventories","examples":["EIA weekly natural gas storage","EIA weekly crude oil inventories"]},{"id":"energy-prices","name":"Energy prices","examples":["Henry Hub natural gas spot","US retail gasoline price"]}]},{"id":"health","name":"Public health","leaves":[{"id":"respiratory-illness","name":"Respiratory illness","examples":["CDC ILINet","influenza hospital admissions","COVID-19 hospital admissions"]},{"id":"other-infectious-disease","name":"Other infectious disease","examples":["Dengue cases","norovirus outbreaks"]},{"id":"health-care-use","name":"Health-care use","examples":["Emergency department visits"]}]},{"id":"economy","name":"Economy and labor","leaves":[{"id":"labor-market","name":"Labor market","examples":["US initial jobless claims"]},{"id":"consumer-prices","name":"Consumer prices","examples":["Food price indices","used car prices"]},{"id":"economic-activity","name":"Economic activity","examples":["Retail foot traffic","freight volumes"]},{"id":"bank-liquidity","name":"Bank liquidity","examples":["Norges Bank structural liquidity","ECB excess liquidity"]},{"id":"technology-adoption","name":"Technology adoption","examples":["Vercel AI Gateway spend shares by lab"]}]},{"id":"markets","name":"Financial markets","leaves":[{"id":"commodities","name":"Commodities","examples":["Corn futures","crude oil futures"]},{"id":"currencies","name":"Currencies","examples":["USD/JPY"]},{"id":"equities","name":"Equities and volatility","examples":["S&P 500 index","VIX"]}]},{"id":"environment","name":"Environment","leaves":[{"id":"weather","name":"Weather","examples":["Daily maximum air temperature","daily precipitation"]},{"id":"air-quality","name":"Air quality","examples":["PM2.5 concentration","ozone"]},{"id":"hydrology","name":"Hydrology","examples":["River discharge","reservoir storage"]},{"id":"natural-hazards","name":"Natural hazards","examples":["Wildfire burned area"]}]},{"id":"space","name":"Space","leaves":[{"id":"space-weather","name":"Space weather","examples":["Planetary Kp index","solar wind speed"]}]},{"id":"mobility","name":"Transport and mobility","leaves":[{"id":"air-travel","name":"Air travel","examples":["TSA checkpoint throughput"]},{"id":"ground-transport","name":"Ground transport","examples":["Transit ridership","road traffic counts"]}]},{"id":"attention","name":"Online attention","leaves":[{"id":"search-and-page-views","name":"Search and page views","examples":["Wikipedia page views","Google Trends interest"]},{"id":"media-and-social","name":"Media and social activity","examples":["News article volume","GitHub stars"]}]}],"facets":{"driver":{"weather":"Weather and climate","epidemic":"Disease transmission","economic":"Economic conditions and policy","behavioral":"Human behavior and events","market":"Market expectations","solar":"Solar activity"},"tradable":{"true":"Tradable price (control)","false":"Not tradable"}}},"systems":[{"id":"claude-code-claude-sonnet-5","kind":"agent","label":"Claude Code \u00b7 Sonnet 5","description":"Anthropic Claude Code 2.1.227 running claude-sonnet-5 with its default tools in bypassPermissions mode. Live runs add the open internet; the agent receives no data.","sort":0},{"id":"claude-code-claude-sonnet-5-continual","kind":"agent","label":"Claude Code \u00b7 Sonnet 5 \u00b7 continual","description":"The same Claude Code agent, continuing on every run day from a snapshot of the sandbox and native session of its previous run day (ALE --continue-from). Its earlier submissions are in /home/user/history/, and it is asked to compare them with the values published since and improve how it forecasts.","sort":0},{"id":"codex-cli-gpt-6.1-sol","kind":"agent","label":"Codex \u00b7 GPT-6.1 Sol","description":"OpenAI Codex CLI 0.146.0 running gpt-6.1-sol with its default settings: no approval prompts, no command sandbox, and its built-in web search. Live runs add the open internet; the agent receives no data.","sort":0},{"id":"codex-cli-gpt-6.1-sol-continual","kind":"agent","label":"Codex \u00b7 GPT-6.1 Sol \u00b7 continual","description":"The same Codex agent, continuing on every run day from a snapshot of the sandbox and native session of its previous run day (ALE --continue-from). Its earlier submissions are in /home/user/history/, and it is asked to compare them with the values published since and improve how it forecasts.","sort":0},{"id":"eccc-official","kind":"expert","label":"ECCC official","description":"ECCC's 06:00 AQHI forecast for the community on the run date, the first issue after the cutoff, which the agents cannot see. Its \"Today\" period gives the run date and its \"Tomorrow\" period the day after; each is ECCC's forecast maximum for 06:00 to 18:00, a whole number, with 10+ counted as 11. It is recorded the next day.","sort":1},{"id":"ercot-official","kind":"expert","label":"ERCOT official","description":"The forecast model ERCOT flags as in use, first version posted after the cutoff (the 09:30 version), which the agents cannot see; it is recorded the next day; the daily maximum of its hourly system total.","sort":1},{"id":"nws-official","kind":"expert","label":"NWS official","description":"The first river forecast the NWS issues for the gauge after the cutoff, normally its evening forecast of the run date, which the agents cannot see; the mean of its four six-hourly stage values on each date. It is recorded the next day.","sort":1},{"id":"chronos-2","kind":"tsfm","label":"Chronos-2 \u00b7 curated","description":"Curated TSFM: Amazon Chronos-2, zero-shot, given the run day's curated input: the target history plus the covariates the task's author chose, for the past and the forecast window, without the earlier expert forecast.","sort":2},{"id":"chronos-2-expert","kind":"tsfm","label":"Chronos-2 \u00b7 curated + expert","description":"Chronos-2 \u00b7 curated, plus the expert forecast's latest version before each snapshot as one more covariate. The version the run is compared with comes after the cutoff and is not included. The pair isolates what the earlier expert forecast adds.","sort":2},{"id":"chronos-2-univariate","kind":"tsfm","label":"Chronos-2 \u00b7 history only","description":"Amazon Chronos-2, zero-shot, given only the target history.","sort":2},{"id":"timesfm-3","kind":"tsfm","label":"TimesFM-3 \u00b7 curated","description":"Curated TSFM: Google TimesFM 3.0 (331M), zero-shot, given the run day's curated input with every known covariate for the past and the forecast window, without the earlier expert forecast. Weights under Google's non-commercial license.","sort":2},{"id":"timesfm-3-expert","kind":"tsfm","label":"TimesFM-3 \u00b7 curated + expert","description":"TimesFM-3 \u00b7 curated, plus the expert forecast's latest version before each snapshot as one more covariate. The version the run is compared with comes after the cutoff and is not included. The pair isolates what the earlier expert forecast adds.","sort":2},{"id":"seasonal-naive","kind":"reference","label":"Seasonal naive","description":"The value on the same weekday in the latest observed week. It is the denominator of every scaled score, so its own scaled score is 1.","sort":3}],"tasks":[{"id":"ercot_peak_load","title":"ERCOT daily peak load","question":"How high will electricity demand on the Texas grid peak on each of the next seven days?","summary":"The highest hourly electricity demand of each day on the ERCOT grid, which serves about 90% of Texas load. Weather drives it, and grid notices and news add information that history alone does not contain.","taxonomy":"energy/electricity-demand","driver":"weather","tradable":false,"domain":"Electricity demand","region":"Texas (ERCOT grid)","unit":"MW","schedule":{"snapshot":"07:05","every_days":1,"first_run":"2026-10-16","timezone":"America/Chicago","cutoff":"09:25"},"horizons":[1,2,3,4,5,6,7],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"baseline":"ERCOT official","baseline_visible":false,"live_since":"2026-10-24","latest_run":"2026-11-03","run_days":10,"next_run":"2026-11-04T07:05:00-06:00","last_observed":"2026-11-02","leaderboard":[{"system":"chronos-2","n":33,"scaled_crps":0.5111289225290981,"scaled_mae":0.6609930257929812,"crps":1986.7392255892266,"mae":2569.255454545456,"coverage80":0.6060606060606061},{"system":"chronos-2-expert","n":33,"scaled_crps":0.33551974076304925,"scaled_mae":0.4208059762790583,"crps":1304.1528282828294,"mae":1635.657272727274,"coverage80":0.48484848484848486},{"system":"chronos-2-univariate","n":33,"scaled_crps":0.6260526576615838,"scaled_mae":0.8267282441741152,"crps":2433.443535353536,"mae":3213.462121212123,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5","n":33,"scaled_crps":0.33078061462853287,"scaled_mae":0.43025730612463853,"crps":1285.7320202020212,"mae":1672.3942424242439,"coverage80":0.8484848484848485},{"system":"codex-cli-gpt-6.1-sol","n":33,"scaled_crps":0.28581102007555237,"scaled_mae":0.35019448852255014,"crps":1110.9368686868695,"mae":1361.1930303030315,"coverage80":0.9696969696969697},{"system":"ercot-official","n":33,"scaled_crps":0.35215496588518375,"scaled_mae":0.35215496588518375,"crps":1368.8133333333344,"mae":1368.8133333333344,"coverage80":null},{"system":"seasonal-naive","n":33,"scaled_crps":1.0,"scaled_mae":1.0,"crps":3886.9630303030312,"mae":3886.9630303030312,"coverage80":null},{"system":"timesfm-3","n":33,"scaled_crps":0.4243866932474492,"scaled_mae":0.561005483910552,"crps":1649.575387205388,"mae":2180.6075757575777,"coverage80":0.6666666666666666},{"system":"timesfm-3-expert","n":33,"scaled_crps":0.2640867725993001,"scaled_mae":0.3547525379711419,"crps":1026.495521885523,"mae":1378.9100000000008,"coverage80":0.7575757575757576}],"truth":[{"date":"2026-09-07","value":86412.36},{"date":"2026-09-08","value":86278.55},{"date":"2026-09-09","value":85931.94},{"date":"2026-09-10","value":84538.73},{"date":"2026-09-11","value":85799.88},{"date":"2026-09-12","value":86491.57},{"date":"2026-09-13","value":86049.84},{"date":"2026-09-14","value":86157.25},{"date":"2026-09-15","value":86129.24},{"date":"2026-09-16","value":86167.87},{"date":"2026-09-17","value":82811.92},{"date":"2026-09-18","value":83098.65},{"date":"2026-09-19","value":82789.85},{"date":"2026-09-20","value":83005.03},{"date":"2026-09-21","value":85925.71},{"date":"2026-09-22","value":85311.93},{"date":"2026-09-23","value":85059.79},{"date":"2026-09-24","value":83426.9},{"date":"2026-09-25","value":81227.32},{"date":"2026-09-26","value":78487.51},{"date":"2026-09-27","value":81585.99},{"date":"2026-09-28","value":82504.9},{"date":"2026-09-29","value":80912.32},{"date":"2026-09-30","value":77838.24},{"date":"2026-10-01","value":66732.03},{"date":"2026-10-02","value":66602.18},{"date":"2026-10-03","value":62432.53},{"date":"2026-10-04","value":60263.42},{"date":"2026-10-05","value":69952.07},{"date":"2026-10-06","value":72381.47},{"date":"2026-10-07","value":73189.81},{"date":"2026-10-08","value":75120.38},{"date":"2026-10-09","value":73917.77},{"date":"2026-10-10","value":71643.27},{"date":"2026-10-11","value":73217.47},{"date":"2026-10-12","value":76145.36},{"date":"2026-10-13","value":81169.2},{"date":"2026-10-14","value":79009.83},{"date":"2026-10-15","value":74982.12},{"date":"2026-10-16","value":54532.28},{"date":"2026-10-17","value":49594.28},{"date":"2026-10-18","value":52374.04},{"date":"2026-10-19","value":56965.61},{"date":"2026-10-20","value":60239.11},{"date":"2026-10-21","value":63001.08},{"date":"2026-10-22","value":63381.26},{"date":"2026-10-23","value":63943.77},{"date":"2026-10-24","value":62087.1},{"date":"2026-10-25","value":58287.79},{"date":"2026-10-26","value":60005.82},{"date":"2026-10-27","value":61064.31},{"date":"2026-10-28","value":63406.9},{"date":"2026-10-29","value":59702.77},{"date":"2026-10-31","value":59794.65},{"date":"2026-11-01","value":62940.51},{"date":"2026-11-02","value":65881.05}]},{"id":"mississippi_st_louis_stage","title":"Mississippi River stage at St. Louis","question":"How high will the Mississippi River be at St. Louis, on average, on each of the next 13 days?","summary":"The daily mean water level of the Mississippi at the St. Louis gauge, just below the mouth of the Missouri River. Barge traffic depends on it: below about 1 ft, barges may have to carry lighter loads. Rain and snowmelt across the upper Mississippi and Missouri basins drive it days to weeks later, and river forecasts, reservoir releases and navigation notices add information that history alone does not contain.","taxonomy":"environment/hydrology","driver":"weather","tradable":false,"domain":"Hydrology","region":"St. Louis, Missouri (Mississippi River)","unit":"ft","schedule":{"snapshot":"16:50","every_days":1,"first_run":"2026-10-29","timezone":"America/Chicago","cutoff":"18:40"},"horizons":[1,2,3,4,5,6,7,8,9,10,11,12,13],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"baseline":"NWS official","baseline_visible":false,"live_since":"2026-10-29","latest_run":"2026-11-03","run_days":6,"next_run":"2026-11-04T16:50:00-06:00","last_observed":"2026-11-02","leaderboard":[{"system":"chronos-2","n":8,"scaled_crps":0.2730185147113129,"scaled_mae":0.37521992714487307,"crps":1.0252418873648492,"mae":1.4090296648550724,"coverage80":0.75},{"system":"chronos-2-expert","n":8,"scaled_crps":0.09872081289329346,"scaled_mae":0.13293353510613765,"crps":0.37071739489878064,"mae":0.4991933553312628,"coverage80":0.625},{"system":"chronos-2-univariate","n":8,"scaled_crps":0.3568379056819871,"scaled_mae":0.4291885958479616,"crps":1.3400013119680239,"mae":1.611693355331263,"coverage80":0.75},{"system":"claude-code-claude-sonnet-5","n":8,"scaled_crps":0.0876654037608079,"scaled_mae":0.10288832230203276,"crps":0.3292020107257877,"mae":0.38636726837474095,"coverage80":0.375},{"system":"codex-cli-gpt-6.1-sol","n":8,"scaled_crps":0.0867518218196759,"scaled_mae":0.10240650380029709,"crps":0.3257713185817805,"mae":0.3845579386645961,"coverage80":1.0},{"system":"nws-official","n":8,"scaled_crps":0.09627415085088606,"scaled_mae":0.09627415085088606,"crps":0.3615296648550725,"mae":0.3615296648550725,"coverage80":null},{"system":"seasonal-naive","n":8,"scaled_crps":1.0,"scaled_mae":1.0,"crps":3.7552101125776396,"mae":3.7552101125776396,"coverage80":null},{"system":"timesfm-3","n":8,"scaled_crps":0.20382206687866122,"scaled_mae":0.23279479153596588,"crps":0.7653946867092246,"mae":0.8741933553312626,"coverage80":0.875},{"system":"timesfm-3-expert","n":8,"scaled_crps":0.0715751544853244,"scaled_mae":0.10754851426875808,"crps":0.26877974393259696,"mae":0.4038672683747409,"coverage80":1.0}],"truth":[{"date":"2026-09-08","value":-0.9465853658536586},{"date":"2026-09-09","value":-1.166111111111111},{"date":"2026-09-10","value":-0.8307499999999999},{"date":"2026-09-11","value":-0.2272916666666666},{"date":"2026-09-12","value":0.5810416666666667},{"date":"2026-09-13","value":2.426875},{"date":"2026-09-14","value":3.0060416666666665},{"date":"2026-09-15","value":1.3766666666666667},{"date":"2026-09-16","value":0.7833333333333333},{"date":"2026-09-17","value":1.8091666666666668},{"date":"2026-09-18","value":3.7385416666666655},{"date":"2026-09-19","value":5.570625},{"date":"2026-09-20","value":7.413958333333333},{"date":"2026-09-21","value":9.941666666666666},{"date":"2026-09-22","value":12.197083333333332},{"date":"2026-09-23","value":14.26304347826087},{"date":"2026-09-24","value":14.531063829787234},{"date":"2026-09-25","value":15.239574468085106},{"date":"2026-09-26","value":15.83608695652174},{"date":"2026-09-27","value":16.145652173913046},{"date":"2026-09-28","value":15.769565217391303},{"date":"2026-09-29","value":14.377916666666666},{"date":"2026-09-30","value":12.940833333333332},{"date":"2026-10-01","value":11.278541666666667},{"date":"2026-10-02","value":10.331458333333334},{"date":"2026-10-03","value":12.21875},{"date":"2026-10-04","value":16.39875},{"date":"2026-10-05","value":21.80458333333333},{"date":"2026-10-06","value":23.74895833333333},{"date":"2026-10-07","value":22.921458333333334},{"date":"2026-10-08","value":20.898125},{"date":"2026-10-09","value":18.805208333333333},{"date":"2026-10-10","value":16.673125000000002},{"date":"2026-10-11","value":15.039791666666666},{"date":"2026-10-12","value":13.71468085106383},{"date":"2026-10-13","value":12.589166666666666},{"date":"2026-10-14","value":12.990652173913045},{"date":"2026-10-15","value":11.280851063829788},{"date":"2026-10-16","value":11.069767441860463},{"date":"2026-10-17","value":9.949574468085109},{"date":"2026-10-18","value":9.380208333333334},{"date":"2026-10-19","value":9.475},{"date":"2026-10-20","value":8.028863636363637},{"date":"2026-10-21","value":7.666744186046512},{"date":"2026-10-22","value":8.357234042553191},{"date":"2026-10-23","value":8.49159090909091},{"date":"2026-10-24","value":7.717826086956522},{"date":"2026-10-25","value":6.5806818181818185},{"date":"2026-10-26","value":6.381555555555556},{"date":"2026-10-27","value":4.63375},{"date":"2026-10-28","value":4.232083333333333},{"date":"2026-10-29","value":5.173333333333333},{"date":"2026-10-30","value":4.4035416666666665},{"date":"2026-10-31","value":3.3229166666666665},{"date":"2026-11-01","value":2.816428571428572},{"date":"2026-11-02","value":3.1686956521739127}]},{"id":"toronto_aqhi","title":"Toronto daytime AQHI","question":"How high will Toronto's Air Quality Health Index get during the day today and tomorrow?","summary":"The highest hourly Air Quality Health Index of the day in Toronto, as observed by Environment and Climate Change Canada (ECCC). The index combines ozone, nitrogen dioxide and fine particulate matter into a health-risk scale from 1 to 10+. Weather drives it, and wildfire smoke, ECCC's forecasts and air quality statements add information that history alone does not contain.","taxonomy":"environment/air-quality","driver":"weather","tradable":false,"domain":"Air quality","region":"Toronto, Ontario","unit":"AQHI","schedule":{"snapshot":"04:05","every_days":1,"first_run":"2026-10-29","timezone":"America/Toronto","cutoff":"05:50"},"horizons":[0,1],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"baseline":"ECCC official","baseline_visible":false,"live_since":"2026-10-29","latest_run":"2026-11-04","run_days":7,"next_run":"2026-11-05T04:05:00-05:00","last_observed":"2026-11-03","leaderboard":[{"system":"chronos-2","n":10,"scaled_crps":1.0327212806026365,"scaled_mae":1.3961864406779658,"crps":0.48744444444444446,"mae":0.659,"coverage80":0.7},{"system":"chronos-2-expert","n":10,"scaled_crps":0.6664312617702447,"scaled_mae":0.8749999999999997,"crps":0.3145555555555556,"mae":0.4129999999999999,"coverage80":0.7},{"system":"chronos-2-univariate","n":10,"scaled_crps":1.2850753295668547,"scaled_mae":1.6800847457627115,"crps":0.6065555555555555,"mae":0.7929999999999999,"coverage80":0.5},{"system":"claude-code-claude-sonnet-5","n":10,"scaled_crps":0.6686911487758944,"scaled_mae":0.6673728813559322,"crps":0.3156222222222222,"mae":0.31500000000000006,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","n":10,"scaled_crps":0.36162900188323915,"scaled_mae":0.39194915254237284,"crps":0.17068888888888892,"mae":0.185,"coverage80":0.9},{"system":"eccc-official","n":10,"scaled_crps":0.8792372881355932,"scaled_mae":0.8792372881355932,"crps":0.41500000000000004,"mae":0.41500000000000004,"coverage80":null},{"system":"seasonal-naive","n":10,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.4720000000000001,"mae":0.4720000000000001,"coverage80":null},{"system":"timesfm-3","n":10,"scaled_crps":0.7991996233521655,"scaled_mae":1.1631355932203389,"crps":0.37722222222222224,"mae":0.549,"coverage80":0.8},{"system":"timesfm-3-expert","n":10,"scaled_crps":0.6692561205273069,"scaled_mae":0.8665254237288134,"crps":0.3158888888888889,"mae":0.409,"coverage80":0.7}],"truth":[{"date":"2026-09-09","value":2.58},{"date":"2026-09-10","value":2.31},{"date":"2026-09-11","value":3.43},{"date":"2026-09-12","value":2.84},{"date":"2026-09-13","value":2.41},{"date":"2026-09-14","value":2.2},{"date":"2026-09-15","value":2.38},{"date":"2026-09-16","value":2.72},{"date":"2026-09-17","value":2.84},{"date":"2026-09-18","value":2.06},{"date":"2026-09-19","value":1.44},{"date":"2026-09-20","value":1.81},{"date":"2026-09-21","value":1.74},{"date":"2026-09-22","value":1.98},{"date":"2026-09-23","value":2.0},{"date":"2026-09-24","value":2.05},{"date":"2026-09-25","value":2.64},{"date":"2026-09-26","value":2.13},{"date":"2026-09-27","value":3.0},{"date":"2026-09-28","value":2.32},{"date":"2026-09-29","value":2.21},{"date":"2026-09-30","value":3.07},{"date":"2026-10-01","value":3.02},{"date":"2026-10-02","value":2.29},{"date":"2026-10-03","value":1.5},{"date":"2026-10-04","value":2.21},{"date":"2026-10-05","value":1.96},{"date":"2026-10-06","value":2.49},{"date":"2026-10-07","value":3.51},{"date":"2026-10-08","value":2.43},{"date":"2026-10-09","value":2.51},{"date":"2026-10-10","value":1.65},{"date":"2026-10-11","value":2.29},{"date":"2026-10-12","value":2.75},{"date":"2026-10-13","value":3.7},{"date":"2026-10-14","value":1.55},{"date":"2026-10-15","value":1.81},{"date":"2026-10-16","value":2.0},{"date":"2026-10-17","value":1.98},{"date":"2026-10-18","value":2.38},{"date":"2026-10-19","value":3.03},{"date":"2026-10-20","value":2.34},{"date":"2026-10-21","value":2.96},{"date":"2026-10-22","value":3.55},{"date":"2026-10-23","value":2.12},{"date":"2026-10-24","value":2.39},{"date":"2026-10-25","value":3.17},{"date":"2026-10-26","value":4.56},{"date":"2026-10-27","value":2.02},{"date":"2026-10-28","value":2.15},{"date":"2026-10-29","value":4.0},{"date":"2026-10-30","value":1.69},{"date":"2026-10-31","value":2.17},{"date":"2026-11-01","value":2.9},{"date":"2026-11-02","value":3.67},{"date":"2026-11-03","value":2.67}]}],"continual_note":"You may have forecast this target on earlier run days in this same environment and session; if so, your earlier submissions are under `/home/user/history/<run date>/`. Compare them with the values published since, and use what you learn to improve how you forecast."}

site/tasks/toronto_aqhi.json

@@ -1 +1 @@
-{"id":"toronto_aqhi","spec":{"target":"toronto_aqhi","title":"Toronto daytime AQHI","question":"How high will Toronto's Air Quality Health Index get during the day today and tomorrow?","taxonomy":"environment/air-quality","driver":"weather","domain":"Air quality","region":"Toronto, Ontario","unit":"AQHI","tradable":false,"summary":"The highest hourly Air Quality Health Index of the day in Toronto, as observed by Environment and Climate Change Canada (ECCC). The index combines ozone, nitrogen dioxide and fine particulate matter into a health-risk scale from 1 to 10+. Weather drives it, and wildfire smoke, ECCC's forecasts and air quality statements add information that history alone does not contain.","y":{"definition":"Maximum of ECCC's hourly observed AQHI for the community Toronto (FEUZB) over the hours stamped 07:00 to 18:00 local time (America/Toronto), ECCC's daytime forecast period of 06:00 to 18:00; values as published, with two decimals, and \"10+\" counted as 11. A day counts once at least 9 of its 12 hours have values.","settlement":"First published value: the hourly observations as posted in ECCC's realtime file the day after; ECCC's later backfill revisions are not used.","source":{"name":"ECCC MSC Datamart, AQHI observations for Toronto (FEUZB)","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"}},"schedule":{"snapshot":"04:05","every_days":1,"first_run":"2026-10-29","timezone":"America/Toronto","cutoff":"05:50"},"x":{"history_start":"2024-01-01","frequency":"daily, with the hourly observations it is derived from","given_to":"TSFMs only; agents find their own information","raw":["Hourly AQHI observations for the community (ECCC MSC Datamart)","Every ECCC AQHI forecast issue for the community since history_start","Daily weather forecast at the community (ECMWF IFS via Open-Meteo)"],"groups":[{"name":"AQHI history","columns":["target"],"what":"The target itself, every day up to the day before the run date; the rare day with too few hours is filled in linearly from its neighbours.","why":"Air quality persists for a day or two with the weather pattern behind it, and the history carries the season's level.","source":"ECCC MSC Datamart","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"},{"name":"Earlier ECCC AQHI forecast","columns":["eccc"],"expert":true,"what":"ECCC's forecast of each day's daytime maximum as a run could see it, normally from the evening issue of the day before: for past days, its \"Tomorrow\" period; for the forecast window, its \"Tomorrow\" and \"Day 3\" periods. The 06:00 forecast the run is compared with comes out after the cutoff and is not included.","why":"ECCC's forecasters combine air quality models, smoke forecasts and the weather pattern, which the history and local weather alone cannot see.","source":"ECCC MSC Datamart, AQHI forecasts for Toronto (FEUZB)","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"},{"name":"Weather at the community","columns":["tmax","precip","wind_u","wind_v","radiation"],"what":"Daily maximum temperature, precipitation, the day's strongest wind as eastward and northward components (from its speed and dominant direction) and solar radiation at the community: reanalysis for past days, the ECMWF forecast issued before the run for the forecast window.","why":"Heat and sunshine make ozone, calm air lets pollution build up, rain washes particles out, and the wind decides whose pollution and smoke arrive.","source":"Open-Meteo (ERA5 reanalysis, ECMWF IFS 0.25\u00b0 forecast)","url":"https://open-meteo.com/en/docs/ecmwf-api"},{"name":"Calendar","columns":["dow"],"what":"Day of week.","why":"Traffic, a source of nitrogen dioxide, is lighter on weekends.","source":"computed"}]},"baseline":{"system":"eccc-official","label":"ECCC official","name":"ECCC AQHI forecast","kind":"point","visible_to_agents":false,"method":"ECCC's 06:00 AQHI forecast for the community on the run date, the first issue after the cutoff, which the agents cannot see. Its \"Today\" period gives the run date and its \"Tomorrow\" period the day after; each is ECCC's forecast maximum for 06:00 to 18:00, a whole number, with 10+ counted as 11. It is recorded the next day.","source":{"name":"ECCC MSC Datamart, AQHI forecasts for Toronto (FEUZB)","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"}},"horizons":[0,1],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]},"status":{"live_since":"2026-10-29","latest_run":"2026-11-03","run_days":6,"next_run":"2026-11-04T04:05:00-05:00","last_observed":"2026-11-02"},"leaderboard":{"live":[{"system":"chronos-2","n":9,"scaled_crps":1.1345891345891344,"scaled_mae":1.5380835380835378,"crps":0.5130864197530864,"mae":0.6955555555555555,"coverage80":0.6666666666666666},{"system":"chronos-2-expert","n":9,"scaled_crps":0.5787605787605787,"scaled_mae":0.7616707616707614,"crps":0.2617283950617284,"mae":0.34444444444444433,"coverage80":0.7777777777777778},{"system":"chronos-2-univariate","n":9,"scaled_crps":1.4447174447174447,"scaled_mae":1.9066339066339064,"crps":0.6533333333333333,"mae":0.8622222222222222,"coverage80":0.4444444444444444},{"system":"claude-code-claude-sonnet-5","n":9,"scaled_crps":0.5426153426153426,"scaled_mae":0.4471744471744472,"crps":0.24538271604938272,"mae":0.20222222222222225,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","n":9,"scaled_crps":0.3187005187005187,"scaled_mae":0.32186732186732187,"crps":0.14412345679012345,"mae":0.14555555555555555,"coverage80":1.0},{"system":"eccc-official","n":9,"scaled_crps":0.6928746928746929,"scaled_mae":0.6928746928746929,"crps":0.31333333333333335,"mae":0.31333333333333335,"coverage80":null},{"system":"seasonal-naive","n":9,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.45222222222222225,"mae":0.45222222222222225,"coverage80":null},{"system":"timesfm-3","n":9,"scaled_crps":0.8375648375648375,"scaled_mae":1.2186732186732183,"crps":0.37876543209876545,"mae":0.551111111111111,"coverage80":0.7777777777777778},{"system":"timesfm-3-expert","n":9,"scaled_crps":0.6082446082446081,"scaled_mae":0.7764127764127764,"crps":0.2750617283950617,"mae":0.35111111111111115,"coverage80":0.7777777777777778}],"mock":[{"system":"chronos-2","n":8,"scaled_crps":1.294549266247379,"scaled_mae":1.7264150943396221,"crps":0.5145833333333333,"mae":0.6862499999999999,"coverage80":0.625},{"system":"chronos-2-expert","n":8,"scaled_crps":0.6802935010482178,"scaled_mae":0.8899371069182386,"crps":0.27041666666666664,"mae":0.3537499999999999,"coverage80":0.75},{"system":"chronos-2-univariate","n":8,"scaled_crps":1.5929419986023756,"scaled_mae":2.072327044025157,"crps":0.6331944444444444,"mae":0.82375,"coverage80":0.5},{"system":"claude-code-claude-sonnet-5","n":8,"scaled_crps":0.3431167016072676,"scaled_mae":0.3584905660377359,"crps":0.1363888888888889,"mae":0.14250000000000004,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","n":8,"scaled_crps":0.3503843466107616,"scaled_mae":0.3490566037735848,"crps":0.13927777777777778,"mae":0.13874999999999998,"coverage80":1.0},{"system":"eccc-official","n":8,"scaled_crps":0.7830188679245282,"scaled_mae":0.7830188679245282,"crps":0.31125,"mae":0.31125,"coverage80":null},{"system":"seasonal-naive","n":8,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.3975000000000001,"mae":0.3975000000000001,"coverage80":null},{"system":"timesfm-3","n":8,"scaled_crps":0.9283717679944092,"scaled_mae":1.3176100628930814,"crps":0.36902777777777773,"mae":0.5237499999999999,"coverage80":0.75},{"system":"timesfm-3-expert","n":8,"scaled_crps":0.687980433263452,"scaled_mae":0.8773584905660375,"crps":0.2734722222222222,"mae":0.34875,"coverage80":0.75}]},"continual":[{"continual":"claude-code-claude-sonnet-5-continual","fresh":"claude-code-claude-sonnet-5","rows":[{"system":"claude-code-claude-sonnet-5","n":9,"scaled_crps":0.5426153426153426,"scaled_mae":0.4471744471744472,"crps":0.24538271604938272,"mae":0.20222222222222225,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5-continual","n":9,"scaled_crps":0.6535626535626534,"scaled_mae":0.5356265356265356,"crps":0.2955555555555555,"mae":0.24222222222222223,"coverage80":1.0}]},{"continual":"codex-cli-gpt-6.1-sol-continual","fresh":"codex-cli-gpt-6.1-sol","rows":[{"system":"codex-cli-gpt-6.1-sol","n":9,"scaled_crps":0.3187005187005187,"scaled_mae":0.32186732186732187,"crps":0.14412345679012345,"mae":0.14555555555555555,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol-continual","n":9,"scaled_crps":0.3093093093093093,"scaled_mae":0.30221130221130227,"crps":0.13987654320987655,"mae":0.13666666666666671,"coverage80":1.0}]}],"by_horizon":{"live":[{"system":"chronos-2","horizon":0,"n":5,"scaled_crps":1.2876106194690262,"scaled_mae":1.7035398230088492,"crps":0.582,"mae":0.7699999999999999,"coverage80":0.6},{"system":"chronos-2","horizon":1,"n":4,"scaled_crps":0.9435236341313689,"scaled_mae":1.3314917127071821,"crps":0.4269444444444444,"mae":0.6024999999999999,"coverage80":0.75},{"system":"chronos-2-expert","horizon":0,"n":5,"scaled_crps":0.6317600786627334,"scaled_mae":0.8628318584070794,"crps":0.2855555555555555,"mae":0.38999999999999996,"coverage80":0.8},{"system":"chronos-2-expert","horizon":1,"n":4,"scaled_crps":0.5125844076120318,"scaled_mae":0.6353591160220992,"crps":0.23194444444444443,"mae":0.28749999999999987,"coverage80":0.75},{"system":"chronos-2-univariate","horizon":0,"n":5,"scaled_crps":1.5884955752212386,"scaled_mae":2.057522123893805,"crps":0.718,"mae":0.9299999999999999,"coverage80":0.4},{"system":"chronos-2-univariate","horizon":1,"n":4,"scaled_crps":1.2651933701657458,"scaled_mae":1.718232044198895,"crps":0.5725,"mae":0.7775,"coverage80":0.5},{"system":"claude-code-claude-sonnet-5","horizon":0,"n":5,"scaled_crps":0.5132743362831859,"scaled_mae":0.4469026548672567,"crps":0.23200000000000004,"mae":0.20200000000000004,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5","horizon":1,"n":4,"scaled_crps":0.5792510742786986,"scaled_mae":0.44751381215469616,"crps":0.26211111111111113,"mae":0.2025,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":0,"n":5,"scaled_crps":0.38869223205506387,"scaled_mae":0.4557522123893806,"crps":0.1756888888888889,"mae":0.20600000000000004,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":1,"n":4,"scaled_crps":0.23130755064456723,"scaled_mae":0.15469613259668497,"crps":0.10466666666666667,"mae":0.06999999999999995,"coverage80":1.0},{"system":"eccc-official","horizon":0,"n":5,"scaled_crps":0.4026548672566372,"scaled_mae":0.4026548672566372,"crps":0.18200000000000002,"mae":0.18200000000000002,"coverage80":null},{"system":"eccc-official","horizon":1,"n":4,"scaled_crps":1.0552486187845305,"scaled_mae":1.0552486187845305,"crps":0.47750000000000004,"mae":0.47750000000000004,"coverage80":null},{"system":"seasonal-naive","horizon":0,"n":5,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.45200000000000007,"mae":0.45200000000000007,"coverage80":null},{"system":"seasonal-naive","horizon":1,"n":4,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.4525,"mae":0.4525,"coverage80":null},{"system":"timesfm-3","horizon":0,"n":5,"scaled_crps":0.8205506391347098,"scaled_mae":1.2168141592920352,"crps":0.3708888888888889,"mae":0.5499999999999999,"coverage80":0.8},{"system":"timesfm-3","horizon":1,"n":4,"scaled_crps":0.8588090853284223,"scaled_mae":1.2209944751381214,"crps":0.3886111111111111,"mae":0.5525,"coverage80":0.75},{"system":"timesfm-3-expert","horizon":0,"n":5,"scaled_crps":0.5668633235004916,"scaled_mae":0.7300884955752212,"crps":0.25622222222222224,"mae":0.32999999999999996,"coverage80":0.8},{"system":"timesfm-3-expert","horizon":1,"n":4,"scaled_crps":0.6599140577041129,"scaled_mae":0.8342541436464089,"crps":0.2986111111111111,"mae":0.37750000000000006,"coverage80":0.75}],"mock":[{"system":"chronos-2","horizon":0,"n":4,"scaled_crps":1.7583130575831298,"scaled_mae":2.248175182481751,"crps":0.6022222222222222,"mae":0.77,"coverage80":0.5},{"system":"chronos-2","horizon":1,"n":4,"scaled_crps":0.9435236341313689,"scaled_mae":1.3314917127071821,"crps":0.4269444444444444,"mae":0.6024999999999999,"coverage80":0.75},{"system":"chronos-2-expert","horizon":0,"n":4,"scaled_crps":0.9018653690186533,"scaled_mae":1.2262773722627731,"crps":0.3088888888888889,"mae":0.41999999999999993,"coverage80":0.75},{"system":"chronos-2-expert","horizon":1,"n":4,"scaled_crps":0.5125844076120318,"scaled_mae":0.6353591160220992,"crps":0.23194444444444443,"mae":0.28749999999999987,"coverage80":0.75},{"system":"chronos-2-univariate","horizon":0,"n":4,"scaled_crps":2.025952960259529,"scaled_mae":2.5401459854014585,"crps":0.6938888888888889,"mae":0.8699999999999999,"coverage80":0.5},{"system":"chronos-2-univariate","horizon":1,"n":4,"scaled_crps":1.2651933701657458,"scaled_mae":1.718232044198895,"crps":0.5725,"mae":0.7775,"coverage80":0.5},{"system":"claude-code-claude-sonnet-5","horizon":0,"n":4,"scaled_crps":0.46942416869424153,"scaled_mae":0.5401459854014597,"crps":0.1607777777777778,"mae":0.18500000000000005,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5","horizon":1,"n":4,"scaled_crps":0.2475138121546961,"scaled_mae":0.22099447513812162,"crps":0.11199999999999999,"mae":0.10000000000000003,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":0,"n":4,"scaled_crps":0.4512570965125708,"scaled_mae":0.4671532846715329,"crps":0.15455555555555556,"mae":0.1600000000000001,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":1,"n":4,"scaled_crps":0.2740331491712707,"scaled_mae":0.25966850828729254,"crps":0.12399999999999999,"mae":0.11749999999999988,"coverage80":1.0},{"system":"eccc-official","horizon":0,"n":4,"scaled_crps":0.4233576642335765,"scaled_mae":0.4233576642335765,"crps":0.14500000000000002,"mae":0.14500000000000002,"coverage80":null},{"system":"eccc-official","horizon":1,"n":4,"scaled_crps":1.0552486187845305,"scaled_mae":1.0552486187845305,"crps":0.47750000000000004,"mae":0.47750000000000004,"coverage80":null},{"system":"seasonal-naive","horizon":0,"n":4,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.34250000000000014,"mae":0.34250000000000014,"coverage80":null},{"system":"seasonal-naive","horizon":1,"n":4,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.4525,"mae":0.4525,"coverage80":null},{"system":"timesfm-3","horizon":0,"n":4,"scaled_crps":1.020275750202757,"scaled_mae":1.4452554744525539,"crps":0.34944444444444445,"mae":0.4949999999999999,"coverage80":0.75},{"system":"timesfm-3","horizon":1,"n":4,"scaled_crps":0.8588090853284223,"scaled_mae":1.2209944751381214,"crps":0.3886111111111111,"mae":0.5525,"coverage80":0.75},{"system":"timesfm-3-expert","horizon":0,"n":4,"scaled_crps":0.725060827250608,"scaled_mae":0.9343065693430652,"crps":0.24833333333333335,"mae":0.31999999999999995,"coverage80":0.75},{"system":"timesfm-3-expert","horizon":1,"n":4,"scaled_crps":0.6599140577041129,"scaled_mae":0.8342541436464089,"crps":0.2986111111111111,"mae":0.37750000000000006,"coverage80":0.75}]},"run_days":[{"run_date":"2026-11-03","resolved":0,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":[]},"scores":{"live":{},"mock":{}},"materials":{}},{"run_date":"2026-11-02","resolved":1,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":[]},"scores":{"live":{"chronos-2":{"scaled_crps":0.5630461922596756,"n":1},"chronos-2-expert":{"scaled_crps":0.21598002496878907,"n":1},"chronos-2-univariate":{"scaled_crps":0.9151061173533085,"n":1},"claude-code-claude-sonnet-5":{"scaled_crps":0.31585518102372045,"n":1},"claude-code-claude-sonnet-5-continual":{"scaled_crps":0.303370786516854,"n":1},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.21897627965043703,"n":1},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.2302122347066169,"n":1},"eccc-official":{"scaled_crps":0.3707865168539328,"n":1},"timesfm-3":{"scaled_crps":0.5131086142322099,"n":1},"timesfm-3-expert":{"scaled_crps":0.32334581772784027,"n":1}},"mock":{}},"materials":{"claude-code-claude-sonnet-5":{"files":3,"bytes":82344},"claude-code-claude-sonnet-5-continual":{"files":15,"bytes":310253},"codex-cli-gpt-6.1-sol":{"files":316,"bytes":11142764},"codex-cli-gpt-6.1-sol-continual":{"files":404,"bytes":13938218}}},{"run_date":"2026-11-01","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":0.774904214559387,"n":2},"chronos-2-expert":{"scaled_crps":0.29022988505747127,"n":2},"chronos-2-univariate":{"scaled_crps":1.2365900383141766,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.4291187739463603,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":0.4473180076628354,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.1877394636015326,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.19731800766283533,"n":2},"eccc-official":{"scaled_crps":0.37068965517241403,"n":2},"timesfm-3":{"scaled_crps":0.7480842911877396,"n":2},"timesfm-3-expert":{"scaled_crps":0.378352490421456,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.17030651340996175,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.20593869731800774,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":6,"bytes":183538},"claude-code-claude-sonnet-5-continual":{"files":15,"bytes":310154},"codex-cli-gpt-6.1-sol":{"files":310,"bytes":11050146},"codex-cli-gpt-6.1-sol-continual":{"files":394,"bytes":13720823}}},{"run_date":"2026-10-31","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":1.0770975056689336,"n":2},"chronos-2-expert":{"scaled_crps":0.7414965986394554,"n":2},"chronos-2-univariate":{"scaled_crps":1.3310657596371875,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.5410430839002265,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":1.136054421768707,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.3823129251700678,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.33378684807256226,"n":2},"eccc-official":{"scaled_crps":0.5510204081632651,"n":2},"timesfm-3":{"scaled_crps":0.9773242630385481,"n":2},"timesfm-3-expert":{"scaled_crps":0.8321995464852602,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.45351473922902485,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.4099773242630382,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":12,"bytes":94625},"claude-code-claude-sonnet-5-continual":{"files":14,"bytes":308909},"codex-cli-gpt-6.1-sol":{"files":484,"bytes":14447177},"codex-cli-gpt-6.1-sol-continual":{"files":384,"bytes":13356090}}},{"run_date":"2026-10-30","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":1.6410256410256405,"n":2},"chronos-2-expert":{"scaled_crps":0.8717948717948713,"n":2},"chronos-2-univariate":{"scaled_crps":1.7709401709401698,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.8632478632478627,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":1.0358974358974353,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.289230769230769,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.2427350427350426,"n":2},"eccc-official":{"scaled_crps":0.7384615384615381,"n":2},"timesfm-3":{"scaled_crps":0.902564102564102,"n":2},"timesfm-3-expert":{"scaled_crps":0.7350427350427348,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.36034188034188014,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.2994871794871793,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":4,"bytes":336358},"claude-code-claude-sonnet-5-continual":{"files":14,"bytes":309729},"codex-cli-gpt-6.1-sol":{"files":249,"bytes":9281012},"codex-cli-gpt-6.1-sol-continual":{"files":375,"bytes":13153620}}},{"run_date":"2026-10-29","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":1.8446969696969688,"n":2},"chronos-2-expert":{"scaled_crps":1.0189393939393936,"n":2},"chronos-2-univariate":{"scaled_crps":2.0770202020202015,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.6856060606060604,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":0.7285353535353534,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.5785353535353533,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.5724747474747474,"n":2},"eccc-official":{"scaled_crps":1.488636363636363,"n":2},"timesfm-3":{"scaled_crps":1.1578282828282824,"n":2},"timesfm-3-expert":{"scaled_crps":0.9810606060606056,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.49671717171717156,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.5452020202020201,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":4,"bytes":138418},"claude-code-claude-sonnet-5-continual":{"files":13,"bytes":278728},"codex-cli-gpt-6.1-sol":{"files":248,"bytes":10128151},"codex-cli-gpt-6.1-sol-continual":{"files":309,"bytes":10856900}}}],"truth":[{"date":"2026-07-06","value":2.62},{"date":"2026-07-07","value":2.61},{"date":"2026-07-08","value":3.37},{"date":"2026-07-09","value":3.77},{"date":"2026-07-10","value":2.47},{"date":"2026-07-11","value":2.76},{"date":"2026-07-12","value":4.09},{"date":"2026-07-13","value":4.32},{"date":"2026-07-14","value":3.69},{"date":"2026-07-15","value":11.0},{"date":"2026-07-16","value":11.0},{"date":"2026-07-17","value":11.0},{"date":"2026-07-18","value":11.0},{"date":"2026-07-19","value":4.0},{"date":"2026-07-20","value":3.68},{"date":"2026-07-21","value":4.0},{"date":"2026-07-22","value":2.24},{"date":"2026-07-23","value":2.63},{"date":"2026-07-24","value":3.22},{"date":"2026-07-25","value":3.69},{"date":"2026-07-26","value":4.12},{"date":"2026-07-27","value":3.79},{"date":"2026-07-28","value":3.4},{"date":"2026-07-29","value":1.74},{"date":"2026-07-30","value":2.36},{"date":"2026-07-31","value":3.08},{"date":"2026-08-01","value":3.61},{"date":"2026-08-02","value":2.0},{"date":"2026-08-03","value":1.69},{"date":"2026-08-04","value":2.85},{"date":"2026-08-05","value":4.05},{"date":"2026-08-06","value":4.1},{"date":"2026-08-07","value":3.53},{"date":"2026-08-08","value":2.92},{"date":"2026-08-09","value":2.34},{"date":"2026-08-10","value":3.52},{"date":"2026-08-11","value":2.65},{"date":"2026-08-12","value":3.3},{"date":"2026-08-13","value":2.29},{"date":"2026-08-14","value":3.4},{"date":"2026-08-15","value":1.64},{"date":"2026-08-16","value":2.58},{"date":"2026-08-17","value":1.67},{"date":"2026-08-18","value":2.59},{"date":"2026-08-19","value":3.27},{"date":"2026-08-20","value":2.81},{"date":"2026-08-21","value":2.98},{"date":"2026-08-22","value":3.11},{"date":"2026-08-23","value":2.0},{"date":"2026-08-24","value":1.61},{"date":"2026-08-25","value":2.34},{"date":"2026-08-26","value":4.0},{"date":"2026-08-27","value":3.01},{"date":"2026-08-28","value":2.48},{"date":"2026-08-29","value":11.0},{"date":"2026-08-30","value":2.65},{"date":"2026-08-31","value":2.55},{"date":"2026-09-01","value":2.92},{"date":"2026-09-02","value":2.9},{"date":"2026-09-03","value":3.22},{"date":"2026-09-04","value":2.45},{"date":"2026-09-05","value":2.12},{"date":"2026-09-06","value":1.8},{"date":"2026-09-07","value":2.23},{"date":"2026-09-08","value":10.0},{"date":"2026-09-09","value":2.58},{"date":"2026-09-10","value":2.31},{"date":"2026-09-11","value":3.43},{"date":"2026-09-12","value":2.84},{"date":"2026-09-13","value":2.41},{"date":"2026-09-14","value":2.2},{"date":"2026-09-15","value":2.38},{"date":"2026-09-16","value":2.72},{"date":"2026-09-17","value":2.84},{"date":"2026-09-18","value":2.06},{"date":"2026-09-19","value":1.44},{"date":"2026-09-20","value":1.81},{"date":"2026-09-21","value":1.74},{"date":"2026-09-22","value":1.98},{"date":"2026-09-23","value":2.0},{"date":"2026-09-24","value":2.05},{"date":"2026-09-25","value":2.64},{"date":"2026-09-26","value":2.13},{"date":"2026-09-27","value":3.0},{"date":"2026-09-28","value":2.32},{"date":"2026-09-29","value":2.21},{"date":"2026-09-30","value":3.07},{"date":"2026-10-01","value":3.02},{"date":"2026-10-02","value":2.29},{"date":"2026-10-03","value":1.5},{"date":"2026-10-04","value":2.21},{"date":"2026-10-05","value":1.96},{"date":"2026-10-06","value":2.49},{"date":"2026-10-07","value":3.51},{"date":"2026-10-08","value":2.43},{"date":"2026-10-09","value":2.51},{"date":"2026-10-10","value":1.65},{"date":"2026-10-11","value":2.29},{"date":"2026-10-12","value":2.75},{"date":"2026-10-13","value":3.7},{"date":"2026-10-14","value":1.55},{"date":"2026-10-15","value":1.81},{"date":"2026-10-16","value":2.0},{"date":"2026-10-17","value":1.98},{"date":"2026-10-18","value":2.38},{"date":"2026-10-19","value":3.03},{"date":"2026-10-20","value":2.34},{"date":"2026-10-21","value":2.96},{"date":"2026-10-22","value":3.55},{"date":"2026-10-23","value":2.12},{"date":"2026-10-24","value":2.39},{"date":"2026-10-25","value":3.17},{"date":"2026-10-26","value":4.56},{"date":"2026-10-27","value":2.02},{"date":"2026-10-28","value":2.15},{"date":"2026-10-29","value":4.0},{"date":"2026-10-30","value":1.69},{"date":"2026-10-31","value":2.17},{"date":"2026-11-01","value":2.9},{"date":"2026-11-02","value":3.67}],"latest_x":{"run_date":"2026-11-03","cutoff":"2026-11-03T05:50:00-05:00","target_dates":["2026-11-03","2026-11-04"],"quantile_levels":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"task":"toronto_aqhi","target":{"name":"Toronto daytime AQHI","unit":"AQHI","definition":"Maximum of ECCC's hourly observed AQHI for the community Toronto (FEUZB) over the hours stamped 07:00 to 18:00 local time (America/Toronto), ECCC's daytime forecast period of 06:00 to 18:00; values as published, with two decimals, and \"10+\" counted as 11. A day counts once at least 9 of its 12 hours have values. Source: ECCC MSC Datamart, AQHI observations for Toronto (FEUZB). First published value: the hourly observations as posted in ECCC's realtime file the day after; ECCC's later backfill revisions are not used."},"last_observed":"2026-11-02","known_covariates":["eccc","tmax","precip","wind_u","wind_v","radiation","dow"],"expert_covariates":["eccc"],"past_covariates":[],"covariate_notes":{"target":"daily maximum of the hourly AQHI stamped 07:00 to 18:00 local time, the run date's once its 18:00 hour is posted; a day with fewer than 9 observed hours is filled linearly from its neighbours","eccc":"ECCC's AQHI forecast of the day's daytime maximum, a whole number: from the latest issue before that day's snapshot up to run_date, normally the evening issue of the day before, and from the latest before this snapshot after it","tmax":"daily maximum 2 m temperature (deg C)","precip":"daily precipitation (mm)","wind_u, wind_v":"eastward and northward components (km/h) of the day's maximum 10 m wind speed, along its dominant direction","radiation":"daily shortwave radiation (MJ/m2)","weather":"at 43.7417, -79.3733; dates before run_date are ERA5 reanalysis, run_date onward is the ecmwf_ifs025 forecast issued before the snapshot","dow":"day of week, Monday = 0"}},"case_studies":[],"links":{"live_task":"https://github.com/rowingchenn/agentic-forecasting-tasks/tree/main/tasks/live/toronto_aqhi","mock_tasks":"https://github.com/rowingchenn/agentic-forecasting-tasks/tree/main/tasks/mock/toronto_aqhi","results":"https://huggingface.co/datasets/Chennzi/agentic-forecasting-results/tree/main/runs/toronto_aqhi"}}
+{"id":"toronto_aqhi","spec":{"target":"toronto_aqhi","title":"Toronto daytime AQHI","question":"How high will Toronto's Air Quality Health Index get during the day today and tomorrow?","taxonomy":"environment/air-quality","driver":"weather","domain":"Air quality","region":"Toronto, Ontario","unit":"AQHI","tradable":false,"summary":"The highest hourly Air Quality Health Index of the day in Toronto, as observed by Environment and Climate Change Canada (ECCC). The index combines ozone, nitrogen dioxide and fine particulate matter into a health-risk scale from 1 to 10+. Weather drives it, and wildfire smoke, ECCC's forecasts and air quality statements add information that history alone does not contain.","y":{"definition":"Maximum of ECCC's hourly observed AQHI for the community Toronto (FEUZB) over the hours stamped 07:00 to 18:00 local time (America/Toronto), ECCC's daytime forecast period of 06:00 to 18:00; values as published, with two decimals, and \"10+\" counted as 11. A day counts once at least 9 of its 12 hours have values.","settlement":"First published value: the hourly observations as posted in ECCC's realtime file the day after; ECCC's later backfill revisions are not used.","source":{"name":"ECCC MSC Datamart, AQHI observations for Toronto (FEUZB)","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"}},"schedule":{"snapshot":"04:05","every_days":1,"first_run":"2026-10-29","timezone":"America/Toronto","cutoff":"05:50"},"x":{"history_start":"2024-01-01","frequency":"daily, with the hourly observations it is derived from","given_to":"TSFMs only; agents find their own information","raw":["Hourly AQHI observations for the community (ECCC MSC Datamart)","Every ECCC AQHI forecast issue for the community since history_start","Daily weather forecast at the community (ECMWF IFS via Open-Meteo)"],"groups":[{"name":"AQHI history","columns":["target"],"what":"The target itself, every day up to the day before the run date; the rare day with too few hours is filled in linearly from its neighbours.","why":"Air quality persists for a day or two with the weather pattern behind it, and the history carries the season's level.","source":"ECCC MSC Datamart","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"},{"name":"Earlier ECCC AQHI forecast","columns":["eccc"],"expert":true,"what":"ECCC's forecast of each day's daytime maximum as a run could see it, normally from the evening issue of the day before: for past days, its \"Tomorrow\" period; for the forecast window, its \"Tomorrow\" and \"Day 3\" periods. The 06:00 forecast the run is compared with comes out after the cutoff and is not included.","why":"ECCC's forecasters combine air quality models, smoke forecasts and the weather pattern, which the history and local weather alone cannot see.","source":"ECCC MSC Datamart, AQHI forecasts for Toronto (FEUZB)","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"},{"name":"Weather at the community","columns":["tmax","precip","wind_u","wind_v","radiation"],"what":"Daily maximum temperature, precipitation, the day's strongest wind as eastward and northward components (from its speed and dominant direction) and solar radiation at the community: reanalysis for past days, the ECMWF forecast issued before the run for the forecast window.","why":"Heat and sunshine make ozone, calm air lets pollution build up, rain washes particles out, and the wind decides whose pollution and smoke arrive.","source":"Open-Meteo (ERA5 reanalysis, ECMWF IFS 0.25\u00b0 forecast)","url":"https://open-meteo.com/en/docs/ecmwf-api"},{"name":"Calendar","columns":["dow"],"what":"Day of week.","why":"Traffic, a source of nitrogen dioxide, is lighter on weekends.","source":"computed"}]},"baseline":{"system":"eccc-official","label":"ECCC official","name":"ECCC AQHI forecast","kind":"point","visible_to_agents":false,"method":"ECCC's 06:00 AQHI forecast for the community on the run date, the first issue after the cutoff, which the agents cannot see. Its \"Today\" period gives the run date and its \"Tomorrow\" period the day after; each is ECCC's forecast maximum for 06:00 to 18:00, a whole number, with 10+ counted as 11. It is recorded the next day.","source":{"name":"ECCC MSC Datamart, AQHI forecasts for Toronto (FEUZB)","url":"https://dd.weather.gc.ca/today/air_quality/aqhi/"}},"horizons":[0,1],"quantiles":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]},"status":{"live_since":"2026-10-29","latest_run":"2026-11-04","run_days":7,"next_run":"2026-11-05T04:05:00-05:00","last_observed":"2026-11-03"},"leaderboard":{"live":[{"system":"chronos-2","n":10,"scaled_crps":1.0327212806026365,"scaled_mae":1.3961864406779658,"crps":0.48744444444444446,"mae":0.659,"coverage80":0.7},{"system":"chronos-2-expert","n":10,"scaled_crps":0.6664312617702447,"scaled_mae":0.8749999999999997,"crps":0.3145555555555556,"mae":0.4129999999999999,"coverage80":0.7},{"system":"chronos-2-univariate","n":10,"scaled_crps":1.2850753295668547,"scaled_mae":1.6800847457627115,"crps":0.6065555555555555,"mae":0.7929999999999999,"coverage80":0.5},{"system":"claude-code-claude-sonnet-5","n":10,"scaled_crps":0.6686911487758944,"scaled_mae":0.6673728813559322,"crps":0.3156222222222222,"mae":0.31500000000000006,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","n":10,"scaled_crps":0.36162900188323915,"scaled_mae":0.39194915254237284,"crps":0.17068888888888892,"mae":0.185,"coverage80":0.9},{"system":"eccc-official","n":10,"scaled_crps":0.8792372881355932,"scaled_mae":0.8792372881355932,"crps":0.41500000000000004,"mae":0.41500000000000004,"coverage80":null},{"system":"seasonal-naive","n":10,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.4720000000000001,"mae":0.4720000000000001,"coverage80":null},{"system":"timesfm-3","n":10,"scaled_crps":0.7991996233521655,"scaled_mae":1.1631355932203389,"crps":0.37722222222222224,"mae":0.549,"coverage80":0.8},{"system":"timesfm-3-expert","n":10,"scaled_crps":0.6692561205273069,"scaled_mae":0.8665254237288134,"crps":0.3158888888888889,"mae":0.409,"coverage80":0.7}],"mock":[{"system":"chronos-2","n":8,"scaled_crps":1.294549266247379,"scaled_mae":1.7264150943396221,"crps":0.5145833333333333,"mae":0.6862499999999999,"coverage80":0.625},{"system":"chronos-2-expert","n":8,"scaled_crps":0.6802935010482178,"scaled_mae":0.8899371069182386,"crps":0.27041666666666664,"mae":0.3537499999999999,"coverage80":0.75},{"system":"chronos-2-univariate","n":8,"scaled_crps":1.5929419986023756,"scaled_mae":2.072327044025157,"crps":0.6331944444444444,"mae":0.82375,"coverage80":0.5},{"system":"claude-code-claude-sonnet-5","n":8,"scaled_crps":0.3431167016072676,"scaled_mae":0.3584905660377359,"crps":0.1363888888888889,"mae":0.14250000000000004,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","n":8,"scaled_crps":0.3503843466107616,"scaled_mae":0.3490566037735848,"crps":0.13927777777777778,"mae":0.13874999999999998,"coverage80":1.0},{"system":"eccc-official","n":8,"scaled_crps":0.7830188679245282,"scaled_mae":0.7830188679245282,"crps":0.31125,"mae":0.31125,"coverage80":null},{"system":"seasonal-naive","n":8,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.3975000000000001,"mae":0.3975000000000001,"coverage80":null},{"system":"timesfm-3","n":8,"scaled_crps":0.9283717679944092,"scaled_mae":1.3176100628930814,"crps":0.36902777777777773,"mae":0.5237499999999999,"coverage80":0.75},{"system":"timesfm-3-expert","n":8,"scaled_crps":0.687980433263452,"scaled_mae":0.8773584905660375,"crps":0.2734722222222222,"mae":0.34875,"coverage80":0.75}]},"continual":[{"continual":"claude-code-claude-sonnet-5-continual","fresh":"claude-code-claude-sonnet-5","rows":[{"system":"claude-code-claude-sonnet-5","n":10,"scaled_crps":0.6686911487758944,"scaled_mae":0.6673728813559322,"crps":0.3156222222222222,"mae":0.31500000000000006,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5-continual","n":10,"scaled_crps":0.7949623352165723,"scaled_mae":0.7648305084745761,"crps":0.37522222222222223,"mae":0.361,"coverage80":0.9}]},{"continual":"codex-cli-gpt-6.1-sol-continual","fresh":"codex-cli-gpt-6.1-sol","rows":[{"system":"codex-cli-gpt-6.1-sol","n":10,"scaled_crps":0.36162900188323915,"scaled_mae":0.39194915254237284,"crps":0.17068888888888892,"mae":0.185,"coverage80":0.9},{"system":"codex-cli-gpt-6.1-sol-continual","n":10,"scaled_crps":0.35739171374764594,"scaled_mae":0.37500000000000006,"crps":0.16868888888888892,"mae":0.17700000000000005,"coverage80":0.9}]}],"by_horizon":{"live":[{"system":"chronos-2","horizon":0,"n":5,"scaled_crps":1.2876106194690262,"scaled_mae":1.7035398230088492,"crps":0.582,"mae":0.7699999999999999,"coverage80":0.6},{"system":"chronos-2","horizon":1,"n":5,"scaled_crps":0.7985546522131888,"scaled_mae":1.113821138211382,"crps":0.3928888888888889,"mae":0.5479999999999999,"coverage80":0.8},{"system":"chronos-2-expert","horizon":0,"n":5,"scaled_crps":0.6317600786627334,"scaled_mae":0.8628318584070794,"crps":0.2855555555555555,"mae":0.38999999999999996,"coverage80":0.8},{"system":"chronos-2-expert","horizon":1,"n":5,"scaled_crps":0.6982836495031617,"scaled_mae":0.8861788617886178,"crps":0.34355555555555556,"mae":0.43599999999999994,"coverage80":0.6},{"system":"chronos-2-univariate","horizon":0,"n":5,"scaled_crps":1.5884955752212386,"scaled_mae":2.057522123893805,"crps":0.718,"mae":0.9299999999999999,"coverage80":0.4},{"system":"chronos-2-univariate","horizon":1,"n":5,"scaled_crps":1.0063233965672989,"scaled_mae":1.3333333333333333,"crps":0.49511111111111106,"mae":0.6559999999999999,"coverage80":0.6},{"system":"claude-code-claude-sonnet-5","horizon":0,"n":5,"scaled_crps":0.5132743362831859,"scaled_mae":0.4469026548672567,"crps":0.23200000000000004,"mae":0.20200000000000004,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5","horizon":1,"n":5,"scaled_crps":0.8114724480578139,"scaled_mae":0.8699186991869919,"crps":0.3992444444444444,"mae":0.42800000000000005,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":0,"n":5,"scaled_crps":0.38869223205506387,"scaled_mae":0.4557522123893806,"crps":0.1756888888888889,"mae":0.20600000000000004,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":1,"n":5,"scaled_crps":0.33676603432700997,"scaled_mae":0.33333333333333326,"crps":0.1656888888888889,"mae":0.16399999999999998,"coverage80":0.8},{"system":"eccc-official","horizon":0,"n":5,"scaled_crps":0.4026548672566372,"scaled_mae":0.4026548672566372,"crps":0.18200000000000002,"mae":0.18200000000000002,"coverage80":null},{"system":"eccc-official","horizon":1,"n":5,"scaled_crps":1.3170731707317074,"scaled_mae":1.3170731707317074,"crps":0.648,"mae":0.648,"coverage80":null},{"system":"seasonal-naive","horizon":0,"n":5,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.45200000000000007,"mae":0.45200000000000007,"coverage80":null},{"system":"seasonal-naive","horizon":1,"n":5,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.492,"mae":0.492,"coverage80":null},{"system":"timesfm-3","horizon":0,"n":5,"scaled_crps":0.8205506391347098,"scaled_mae":1.2168141592920352,"crps":0.3708888888888889,"mae":0.5499999999999999,"coverage80":0.8},{"system":"timesfm-3","horizon":1,"n":5,"scaled_crps":0.7795844625112918,"scaled_mae":1.1138211382113823,"crps":0.38355555555555554,"mae":0.548,"coverage80":0.8},{"system":"timesfm-3-expert","horizon":0,"n":5,"scaled_crps":0.5668633235004916,"scaled_mae":0.7300884955752212,"crps":0.25622222222222224,"mae":0.32999999999999996,"coverage80":0.8},{"system":"timesfm-3-expert","horizon":1,"n":5,"scaled_crps":0.7633242999096658,"scaled_mae":0.9918699186991872,"crps":0.37555555555555553,"mae":0.4880000000000001,"coverage80":0.6}],"mock":[{"system":"chronos-2","horizon":0,"n":4,"scaled_crps":1.7583130575831298,"scaled_mae":2.248175182481751,"crps":0.6022222222222222,"mae":0.77,"coverage80":0.5},{"system":"chronos-2","horizon":1,"n":4,"scaled_crps":0.9435236341313689,"scaled_mae":1.3314917127071821,"crps":0.4269444444444444,"mae":0.6024999999999999,"coverage80":0.75},{"system":"chronos-2-expert","horizon":0,"n":4,"scaled_crps":0.9018653690186533,"scaled_mae":1.2262773722627731,"crps":0.3088888888888889,"mae":0.41999999999999993,"coverage80":0.75},{"system":"chronos-2-expert","horizon":1,"n":4,"scaled_crps":0.5125844076120318,"scaled_mae":0.6353591160220992,"crps":0.23194444444444443,"mae":0.28749999999999987,"coverage80":0.75},{"system":"chronos-2-univariate","horizon":0,"n":4,"scaled_crps":2.025952960259529,"scaled_mae":2.5401459854014585,"crps":0.6938888888888889,"mae":0.8699999999999999,"coverage80":0.5},{"system":"chronos-2-univariate","horizon":1,"n":4,"scaled_crps":1.2651933701657458,"scaled_mae":1.718232044198895,"crps":0.5725,"mae":0.7775,"coverage80":0.5},{"system":"claude-code-claude-sonnet-5","horizon":0,"n":4,"scaled_crps":0.46942416869424153,"scaled_mae":0.5401459854014597,"crps":0.1607777777777778,"mae":0.18500000000000005,"coverage80":1.0},{"system":"claude-code-claude-sonnet-5","horizon":1,"n":4,"scaled_crps":0.2475138121546961,"scaled_mae":0.22099447513812162,"crps":0.11199999999999999,"mae":0.10000000000000003,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":0,"n":4,"scaled_crps":0.4512570965125708,"scaled_mae":0.4671532846715329,"crps":0.15455555555555556,"mae":0.1600000000000001,"coverage80":1.0},{"system":"codex-cli-gpt-6.1-sol","horizon":1,"n":4,"scaled_crps":0.2740331491712707,"scaled_mae":0.25966850828729254,"crps":0.12399999999999999,"mae":0.11749999999999988,"coverage80":1.0},{"system":"eccc-official","horizon":0,"n":4,"scaled_crps":0.4233576642335765,"scaled_mae":0.4233576642335765,"crps":0.14500000000000002,"mae":0.14500000000000002,"coverage80":null},{"system":"eccc-official","horizon":1,"n":4,"scaled_crps":1.0552486187845305,"scaled_mae":1.0552486187845305,"crps":0.47750000000000004,"mae":0.47750000000000004,"coverage80":null},{"system":"seasonal-naive","horizon":0,"n":4,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.34250000000000014,"mae":0.34250000000000014,"coverage80":null},{"system":"seasonal-naive","horizon":1,"n":4,"scaled_crps":1.0,"scaled_mae":1.0,"crps":0.4525,"mae":0.4525,"coverage80":null},{"system":"timesfm-3","horizon":0,"n":4,"scaled_crps":1.020275750202757,"scaled_mae":1.4452554744525539,"crps":0.34944444444444445,"mae":0.4949999999999999,"coverage80":0.75},{"system":"timesfm-3","horizon":1,"n":4,"scaled_crps":0.8588090853284223,"scaled_mae":1.2209944751381214,"crps":0.3886111111111111,"mae":0.5525,"coverage80":0.75},{"system":"timesfm-3-expert","horizon":0,"n":4,"scaled_crps":0.725060827250608,"scaled_mae":0.9343065693430652,"crps":0.24833333333333335,"mae":0.31999999999999995,"coverage80":0.75},{"system":"timesfm-3-expert","horizon":1,"n":4,"scaled_crps":0.6599140577041129,"scaled_mae":0.8342541436464089,"crps":0.2986111111111111,"mae":0.37750000000000006,"coverage80":0.75}]},"run_days":[{"run_date":"2026-11-04","resolved":0,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":[]},"scores":{"live":{},"mock":{}},"materials":{"claude-code-claude-sonnet-5":{"files":7,"bytes":354595},"claude-code-claude-sonnet-5-continual":{"files":13,"bytes":53693},"codex-cli-gpt-6.1-sol":{"files":187,"bytes":6667091},"codex-cli-gpt-6.1-sol-continual":{"files":171,"bytes":5195392}}},{"run_date":"2026-11-03","resolved":1,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":[]},"scores":{"live":{"chronos-2":{"scaled_crps":0.6034188034188035,"n":1},"chronos-2-expert":{"scaled_crps":0.4495726495726498,"n":1},"chronos-2-univariate":{"scaled_crps":0.2957264957264958,"n":1},"eccc-official":{"scaled_crps":2.0461538461538464,"n":1},"timesfm-3":{"scaled_crps":1.1059829059829063,"n":1},"timesfm-3-expert":{"scaled_crps":0.4837606837606839,"n":1}},"mock":{}},"materials":{}},{"run_date":"2026-11-02","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":[]},"scores":{"live":{"chronos-2":{"scaled_crps":0.4920634920634922,"n":2},"chronos-2-expert":{"scaled_crps":0.637806637806638,"n":2},"chronos-2-univariate":{"scaled_crps":0.6493506493506495,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.7979797979797981,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":0.8845598845598848,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.39264069264069285,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.4109668109668112,"n":2},"eccc-official":{"scaled_crps":1.0779220779220784,"n":2},"timesfm-3":{"scaled_crps":0.5324675324675325,"n":2},"timesfm-3-expert":{"scaled_crps":0.6305916305916307,"n":2}},"mock":{}},"materials":{"claude-code-claude-sonnet-5":{"files":3,"bytes":82344},"claude-code-claude-sonnet-5-continual":{"files":15,"bytes":310253},"codex-cli-gpt-6.1-sol":{"files":316,"bytes":11142764},"codex-cli-gpt-6.1-sol-continual":{"files":404,"bytes":13938218}}},{"run_date":"2026-11-01","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":0.774904214559387,"n":2},"chronos-2-expert":{"scaled_crps":0.29022988505747127,"n":2},"chronos-2-univariate":{"scaled_crps":1.2365900383141766,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.4291187739463603,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":0.4473180076628354,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.1877394636015326,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.19731800766283533,"n":2},"eccc-official":{"scaled_crps":0.37068965517241403,"n":2},"timesfm-3":{"scaled_crps":0.7480842911877396,"n":2},"timesfm-3-expert":{"scaled_crps":0.378352490421456,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.17030651340996175,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.20593869731800774,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":6,"bytes":183538},"claude-code-claude-sonnet-5-continual":{"files":15,"bytes":310154},"codex-cli-gpt-6.1-sol":{"files":310,"bytes":11050146},"codex-cli-gpt-6.1-sol-continual":{"files":394,"bytes":13720823}}},{"run_date":"2026-10-31","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":1.0770975056689336,"n":2},"chronos-2-expert":{"scaled_crps":0.7414965986394554,"n":2},"chronos-2-univariate":{"scaled_crps":1.3310657596371875,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.5410430839002265,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":1.136054421768707,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.3823129251700678,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.33378684807256226,"n":2},"eccc-official":{"scaled_crps":0.5510204081632651,"n":2},"timesfm-3":{"scaled_crps":0.9773242630385481,"n":2},"timesfm-3-expert":{"scaled_crps":0.8321995464852602,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.45351473922902485,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.4099773242630382,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":12,"bytes":94625},"claude-code-claude-sonnet-5-continual":{"files":14,"bytes":308909},"codex-cli-gpt-6.1-sol":{"files":484,"bytes":14447177},"codex-cli-gpt-6.1-sol-continual":{"files":384,"bytes":13356090}}},{"run_date":"2026-10-30","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":1.6410256410256405,"n":2},"chronos-2-expert":{"scaled_crps":0.8717948717948713,"n":2},"chronos-2-univariate":{"scaled_crps":1.7709401709401698,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.8632478632478627,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":1.0358974358974353,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.289230769230769,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.2427350427350426,"n":2},"eccc-official":{"scaled_crps":0.7384615384615381,"n":2},"timesfm-3":{"scaled_crps":0.902564102564102,"n":2},"timesfm-3-expert":{"scaled_crps":0.7350427350427348,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.36034188034188014,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.2994871794871793,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":4,"bytes":336358},"claude-code-claude-sonnet-5-continual":{"files":14,"bytes":309729},"codex-cli-gpt-6.1-sol":{"files":249,"bytes":9281012},"codex-cli-gpt-6.1-sol-continual":{"files":375,"bytes":13153620}}},{"run_date":"2026-10-29","resolved":2,"target_dates":2,"submitted":{"live":["chronos-2","chronos-2-expert","chronos-2-univariate","claude-code-claude-sonnet-5","claude-code-claude-sonnet-5-continual","codex-cli-gpt-6.1-sol","codex-cli-gpt-6.1-sol-continual","eccc-official","seasonal-naive","timesfm-3","timesfm-3-expert"],"mock":["claude-code-claude-sonnet-5","codex-cli-gpt-6.1-sol"]},"scores":{"live":{"chronos-2":{"scaled_crps":1.8446969696969688,"n":2},"chronos-2-expert":{"scaled_crps":1.0189393939393936,"n":2},"chronos-2-univariate":{"scaled_crps":2.0770202020202015,"n":2},"claude-code-claude-sonnet-5":{"scaled_crps":0.6856060606060604,"n":2},"claude-code-claude-sonnet-5-continual":{"scaled_crps":0.7285353535353534,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.5785353535353533,"n":2},"codex-cli-gpt-6.1-sol-continual":{"scaled_crps":0.5724747474747474,"n":2},"eccc-official":{"scaled_crps":1.488636363636363,"n":2},"timesfm-3":{"scaled_crps":1.1578282828282824,"n":2},"timesfm-3-expert":{"scaled_crps":0.9810606060606056,"n":2}},"mock":{"claude-code-claude-sonnet-5":{"scaled_crps":0.49671717171717156,"n":2},"codex-cli-gpt-6.1-sol":{"scaled_crps":0.5452020202020201,"n":2}}},"materials":{"claude-code-claude-sonnet-5":{"files":4,"bytes":138418},"claude-code-claude-sonnet-5-continual":{"files":13,"bytes":278728},"codex-cli-gpt-6.1-sol":{"files":248,"bytes":10128151},"codex-cli-gpt-6.1-sol-continual":{"files":309,"bytes":10856900}}}],"truth":[{"date":"2026-07-07","value":2.61},{"date":"2026-07-08","value":3.37},{"date":"2026-07-09","value":3.77},{"date":"2026-07-10","value":2.47},{"date":"2026-07-11","value":2.76},{"date":"2026-07-12","value":4.09},{"date":"2026-07-13","value":4.32},{"date":"2026-07-14","value":3.69},{"date":"2026-07-15","value":11.0},{"date":"2026-07-16","value":11.0},{"date":"2026-07-17","value":11.0},{"date":"2026-07-18","value":11.0},{"date":"2026-07-19","value":4.0},{"date":"2026-07-20","value":3.68},{"date":"2026-07-21","value":4.0},{"date":"2026-07-22","value":2.24},{"date":"2026-07-23","value":2.63},{"date":"2026-07-24","value":3.22},{"date":"2026-07-25","value":3.69},{"date":"2026-07-26","value":4.12},{"date":"2026-07-27","value":3.79},{"date":"2026-07-28","value":3.4},{"date":"2026-07-29","value":1.74},{"date":"2026-07-30","value":2.36},{"date":"2026-07-31","value":3.08},{"date":"2026-08-01","value":3.61},{"date":"2026-08-02","value":2.0},{"date":"2026-08-03","value":1.69},{"date":"2026-08-04","value":2.85},{"date":"2026-08-05","value":4.05},{"date":"2026-08-06","value":4.1},{"date":"2026-08-07","value":3.53},{"date":"2026-08-08","value":2.92},{"date":"2026-08-09","value":2.34},{"date":"2026-08-10","value":3.52},{"date":"2026-08-11","value":2.65},{"date":"2026-08-12","value":3.3},{"date":"2026-08-13","value":2.29},{"date":"2026-08-14","value":3.4},{"date":"2026-08-15","value":1.64},{"date":"2026-08-16","value":2.58},{"date":"2026-08-17","value":1.67},{"date":"2026-08-18","value":2.59},{"date":"2026-08-19","value":3.27},{"date":"2026-08-20","value":2.81},{"date":"2026-08-21","value":2.98},{"date":"2026-08-22","value":3.11},{"date":"2026-08-23","value":2.0},{"date":"2026-08-24","value":1.61},{"date":"2026-08-25","value":2.34},{"date":"2026-08-26","value":4.0},{"date":"2026-08-27","value":3.01},{"date":"2026-08-28","value":2.48},{"date":"2026-08-29","value":11.0},{"date":"2026-08-30","value":2.65},{"date":"2026-08-31","value":2.55},{"date":"2026-09-01","value":2.92},{"date":"2026-09-02","value":2.9},{"date":"2026-09-03","value":3.22},{"date":"2026-09-04","value":2.45},{"date":"2026-09-05","value":2.12},{"date":"2026-09-06","value":1.8},{"date":"2026-09-07","value":2.23},{"date":"2026-09-08","value":10.0},{"date":"2026-09-09","value":2.58},{"date":"2026-09-10","value":2.31},{"date":"2026-09-11","value":3.43},{"date":"2026-09-12","value":2.84},{"date":"2026-09-13","value":2.41},{"date":"2026-09-14","value":2.2},{"date":"2026-09-15","value":2.38},{"date":"2026-09-16","value":2.72},{"date":"2026-09-17","value":2.84},{"date":"2026-09-18","value":2.06},{"date":"2026-09-19","value":1.44},{"date":"2026-09-20","value":1.81},{"date":"2026-09-21","value":1.74},{"date":"2026-09-22","value":1.98},{"date":"2026-09-23","value":2.0},{"date":"2026-09-24","value":2.05},{"date":"2026-09-25","value":2.64},{"date":"2026-09-26","value":2.13},{"date":"2026-09-27","value":3.0},{"date":"2026-09-28","value":2.32},{"date":"2026-09-29","value":2.21},{"date":"2026-09-30","value":3.07},{"date":"2026-10-01","value":3.02},{"date":"2026-10-02","value":2.29},{"date":"2026-10-03","value":1.5},{"date":"2026-10-04","value":2.21},{"date":"2026-10-05","value":1.96},{"date":"2026-10-06","value":2.49},{"date":"2026-10-07","value":3.51},{"date":"2026-10-08","value":2.43},{"date":"2026-10-09","value":2.51},{"date":"2026-10-10","value":1.65},{"date":"2026-10-11","value":2.29},{"date":"2026-10-12","value":2.75},{"date":"2026-10-13","value":3.7},{"date":"2026-10-14","value":1.55},{"date":"2026-10-15","value":1.81},{"date":"2026-10-16","value":2.0},{"date":"2026-10-17","value":1.98},{"date":"2026-10-18","value":2.38},{"date":"2026-10-19","value":3.03},{"date":"2026-10-20","value":2.34},{"date":"2026-10-21","value":2.96},{"date":"2026-10-22","value":3.55},{"date":"2026-10-23","value":2.12},{"date":"2026-10-24","value":2.39},{"date":"2026-10-25","value":3.17},{"date":"2026-10-26","value":4.56},{"date":"2026-10-27","value":2.02},{"date":"2026-10-28","value":2.15},{"date":"2026-10-29","value":4.0},{"date":"2026-10-30","value":1.69},{"date":"2026-10-31","value":2.17},{"date":"2026-11-01","value":2.9},{"date":"2026-11-02","value":3.67},{"date":"2026-11-03","value":2.67}],"latest_x":{"run_date":"2026-11-04","cutoff":"2026-11-04T05:50:00-05:00","target_dates":["2026-11-04","2026-11-05"],"quantile_levels":[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9],"task":"toronto_aqhi","target":{"name":"Toronto daytime AQHI","unit":"AQHI","definition":"Maximum of ECCC's hourly observed AQHI for the community Toronto (FEUZB) over the hours stamped 07:00 to 18:00 local time (America/Toronto), ECCC's daytime forecast period of 06:00 to 18:00; values as published, with two decimals, and \"10+\" counted as 11. A day counts once at least 9 of its 12 hours have values. Source: ECCC MSC Datamart, AQHI observations for Toronto (FEUZB). First published value: the hourly observations as posted in ECCC's realtime file the day after; ECCC's later backfill revisions are not used."},"last_observed":"2026-11-03","known_covariates":["eccc","tmax","precip","wind_u","wind_v","radiation","dow"],"expert_covariates":["eccc"],"past_covariates":[],"covariate_notes":{"target":"daily maximum of the hourly AQHI stamped 07:00 to 18:00 local time, the run date's once its 18:00 hour is posted; a day with fewer than 9 observed hours is filled linearly from its neighbours","eccc":"ECCC's AQHI forecast of the day's daytime maximum, a whole number: from the latest issue before that day's snapshot up to run_date, normally the evening issue of the day before, and from the latest before this snapshot after it","tmax":"daily maximum 2 m temperature (deg C)","precip":"daily precipitation (mm)","wind_u, wind_v":"eastward and northward components (km/h) of the day's maximum 10 m wind speed, along its dominant direction","radiation":"daily shortwave radiation (MJ/m2)","weather":"at 43.7417, -79.3733; dates before run_date are ERA5 reanalysis, run_date onward is the ecmwf_ifs025 forecast issued before the snapshot","dow":"day of week, Monday = 0"}},"case_studies":[],"links":{"live_task":"https://github.com/rowingchenn/agentic-forecasting-tasks/tree/main/tasks/live/toronto_aqhi","mock_tasks":"https://github.com/rowingchenn/agentic-forecasting-tasks/tree/main/tasks/mock/toronto_aqhi","results":"https://huggingface.co/datasets/Chennzi/agentic-forecasting-results/tree/main/runs/toronto_aqhi"}}

site/tasks/toronto_aqhi/2026-11-03.json

@@ -1 +1 @@
-{"run_date":"2026-11-03","cutoff":"2026-11-03T05:50:00-05:00","snapshot_at":"2026-11-03T09:08:39+00:00","last_observed":"2026-11-02","target_dates":["2026-11-03","2026-11-04"],"forecasts":[{"system":"chronos-2","mode":"live","submitted_at":"2026-11-03T04:08:50-05:00","on_time":true,"source":{"model":"amazon/chronos-2","revision":"29ec3766d36d6f73f0696f85560a422f50e8498c","device":"cpu","covariates":6},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.3,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.9,"0.4":3.1,"0.5":3.3,"0.6":3.4,"0.7":3.6,"0.8":3.9,"0.9":4.4},"y":null,"crps":null,"ae":null},{"target_date":"2026-11-04","horizon":1,"point":3.2,"quantiles":{"0.1":2.4,"0.2":2.6,"0.3":2.8,"0.4":3.0,"0.5":3.2,"0.6":3.4,"0.7":3.6,"0.8":3.9,"0.9":4.5},"y":null,"crps":null,"ae":null}]},{"system":"chronos-2-expert","mode":"live","submitted_at":"2026-11-03T04:09:14-05:00","on_time":true,"source":{"model":"amazon/chronos-2","revision":"29ec3766d36d6f73f0696f85560a422f50e8498c","device":"cpu","covariates":7},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.1,"quantiles":{"0.1":2.6,"0.2":2.7,"0.3":2.9,"0.4":3.0,"0.5":3.1,"0.6":3.2,"0.7":3.4,"0.8":3.5,"0.9":3.8},"y":null,"crps":null,"ae":null},{"target_date":"2026-11-04","horizon":1,"point":3.1,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.9,"0.4":3.0,"0.5":3.1,"0.6":3.2,"0.7":3.3,"0.8":3.5,"0.9":3.8},"y":null,"crps":null,"ae":null}]},{"system":"chronos-2-univariate","mode":"live","submitted_at":"2026-11-03T04:08:57-05:00","on_time":true,"source":{"model":"amazon/chronos-2","revision":"29ec3766d36d6f73f0696f85560a422f50e8498c","device":"cpu","covariates":0},"values":[{"target_date":"2026-11-03","horizon":0,"point":2.8,"quantiles":{"0.1":2.1,"0.2":2.3,"0.3":2.5,"0.4":2.7,"0.5":2.8,"0.6":3.0,"0.7":3.2,"0.8":3.5,"0.9":4.1},"y":null,"crps":null,"ae":null},{"target_date":"2026-11-04","horizon":1,"point":2.6,"quantiles":{"0.1":1.9,"0.2":2.2,"0.3":2.3,"0.4":2.5,"0.5":2.6,"0.6":2.8,"0.7":3.0,"0.8":3.4,"0.9":3.9},"y":null,"crps":null,"ae":null}]},{"system":"seasonal-naive","mode":"live","submitted_at":null,"on_time":true,"source":{},"values":[{"target_date":"2026-11-03","horizon":0,"point":2.02,"quantiles":null,"y":null,"crps":null,"ae":null},{"target_date":"2026-11-04","horizon":1,"point":2.15,"quantiles":null,"y":null,"crps":null,"ae":null}]},{"system":"timesfm-3","mode":"live","submitted_at":"2026-11-03T04:09:08-05:00","on_time":true,"source":{"model":"google/timesfm-3.0-pytorch","revision":"43046b85ec22d584a13f8098c2ed39c889e129c2","device":"cpu","covariates":6},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.6,"quantiles":{"0.1":2.7,"0.2":3.0,"0.3":3.2,"0.4":3.4,"0.5":3.6,"0.6":3.9,"0.7":4.2,"0.8":4.8,"0.9":5.6},"y":null,"crps":null,"ae":null},{"target_date":"2026-11-04","horizon":1,"point":3.6,"quantiles":{"0.1":2.5,"0.2":2.8,"0.3":3.1,"0.4":3.3,"0.5":3.6,"0.6":3.9,"0.7":4.3,"0.8":4.8,"0.9":5.6},"y":null,"crps":null,"ae":null}]},{"system":"timesfm-3-expert","mode":"live","submitted_at":"2026-11-03T04:09:20-05:00","on_time":true,"source":{"model":"google/timesfm-3.0-pytorch","revision":"43046b85ec22d584a13f8098c2ed39c889e129c2","device":"cpu","covariates":7},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.1,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.8,"0.4":3.0,"0.5":3.1,"0.6":3.3,"0.7":3.5,"0.8":3.8,"0.9":4.1},"y":null,"crps":null,"ae":null},{"target_date":"2026-11-04","horizon":1,"point":3.2,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.9,"0.4":3.0,"0.5":3.2,"0.6":3.3,"0.7":3.5,"0.8":3.7,"0.9":4.1},"y":null,"crps":null,"ae":null}]}],"truth":[{"date":"2026-09-22","value":1.98},{"date":"2026-09-23","value":2.0},{"date":"2026-09-24","value":2.05},{"date":"2026-09-25","value":2.64},{"date":"2026-09-26","value":2.13},{"date":"2026-09-27","value":3.0},{"date":"2026-09-28","value":2.32},{"date":"2026-09-29","value":2.21},{"date":"2026-09-30","value":3.07},{"date":"2026-10-01","value":3.02},{"date":"2026-10-02","value":2.29},{"date":"2026-10-03","value":1.5},{"date":"2026-10-04","value":2.21},{"date":"2026-10-05","value":1.96},{"date":"2026-10-06","value":2.49},{"date":"2026-10-07","value":3.51},{"date":"2026-10-08","value":2.43},{"date":"2026-10-09","value":2.51},{"date":"2026-10-10","value":1.65},{"date":"2026-10-11","value":2.29},{"date":"2026-10-12","value":2.75},{"date":"2026-10-13","value":3.7},{"date":"2026-10-14","value":1.55},{"date":"2026-10-15","value":1.81},{"date":"2026-10-16","value":2.0},{"date":"2026-10-17","value":1.98},{"date":"2026-10-18","value":2.38},{"date":"2026-10-19","value":3.03},{"date":"2026-10-20","value":2.34},{"date":"2026-10-21","value":2.96},{"date":"2026-10-22","value":3.55},{"date":"2026-10-23","value":2.12},{"date":"2026-10-24","value":2.39},{"date":"2026-10-25","value":3.17},{"date":"2026-10-26","value":4.56},{"date":"2026-10-27","value":2.02},{"date":"2026-10-28","value":2.15},{"date":"2026-10-29","value":4.0},{"date":"2026-10-30","value":1.69},{"date":"2026-10-31","value":2.17},{"date":"2026-11-01","value":2.9},{"date":"2026-11-02","value":3.67}],"materials":[],"x_files":["MANIFEST.json","raw/aqhi_hourly.csv","raw/eccc_forecasts.csv","raw/weather_forecast_daily.csv","series.csv","task.json"]}
+{"run_date":"2026-11-03","cutoff":"2026-11-03T05:50:00-05:00","snapshot_at":"2026-11-03T09:08:39+00:00","last_observed":"2026-11-02","target_dates":["2026-11-03","2026-11-04"],"forecasts":[{"system":"chronos-2","mode":"live","submitted_at":"2026-11-03T04:08:50-05:00","on_time":true,"source":{"model":"amazon/chronos-2","revision":"29ec3766d36d6f73f0696f85560a422f50e8498c","device":"cpu","covariates":6},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.3,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.9,"0.4":3.1,"0.5":3.3,"0.6":3.4,"0.7":3.6,"0.8":3.9,"0.9":4.4},"y":2.67,"crps":0.39222222222222225,"ae":0.6299999999999999},{"target_date":"2026-11-04","horizon":1,"point":3.2,"quantiles":{"0.1":2.4,"0.2":2.6,"0.3":2.8,"0.4":3.0,"0.5":3.2,"0.6":3.4,"0.7":3.6,"0.8":3.9,"0.9":4.5},"y":null,"crps":null,"ae":null}]},{"system":"chronos-2-expert","mode":"live","submitted_at":"2026-11-03T04:09:14-05:00","on_time":true,"source":{"model":"amazon/chronos-2","revision":"29ec3766d36d6f73f0696f85560a422f50e8498c","device":"cpu","covariates":7},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.1,"quantiles":{"0.1":2.6,"0.2":2.7,"0.3":2.9,"0.4":3.0,"0.5":3.1,"0.6":3.2,"0.7":3.4,"0.8":3.5,"0.9":3.8},"y":2.67,"crps":0.2922222222222223,"ae":0.43000000000000016},{"target_date":"2026-11-04","horizon":1,"point":3.1,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.9,"0.4":3.0,"0.5":3.1,"0.6":3.2,"0.7":3.3,"0.8":3.5,"0.9":3.8},"y":null,"crps":null,"ae":null}]},{"system":"chronos-2-univariate","mode":"live","submitted_at":"2026-11-03T04:08:57-05:00","on_time":true,"source":{"model":"amazon/chronos-2","revision":"29ec3766d36d6f73f0696f85560a422f50e8498c","device":"cpu","covariates":0},"values":[{"target_date":"2026-11-03","horizon":0,"point":2.8,"quantiles":{"0.1":2.1,"0.2":2.3,"0.3":2.5,"0.4":2.7,"0.5":2.8,"0.6":3.0,"0.7":3.2,"0.8":3.5,"0.9":4.1},"y":2.67,"crps":0.19222222222222224,"ae":0.1299999999999999},{"target_date":"2026-11-04","horizon":1,"point":2.6,"quantiles":{"0.1":1.9,"0.2":2.2,"0.3":2.3,"0.4":2.5,"0.5":2.6,"0.6":2.8,"0.7":3.0,"0.8":3.4,"0.9":3.9},"y":null,"crps":null,"ae":null}]},{"system":"eccc-official","mode":"live","submitted_at":null,"on_time":true,"source":{"report":"ECCC AQHI forecast for Toronto (FEUZB), issued","posted":"2026-11-03T11:00:00+00:00","model":"ECCC"},"values":[{"target_date":"2026-11-03","horizon":0,"point":4.0,"quantiles":null,"y":2.67,"crps":1.33,"ae":1.33},{"target_date":"2026-11-04","horizon":1,"point":3.0,"quantiles":null,"y":null,"crps":null,"ae":null}]},{"system":"seasonal-naive","mode":"live","submitted_at":null,"on_time":true,"source":{},"values":[{"target_date":"2026-11-03","horizon":0,"point":2.02,"quantiles":null,"y":2.67,"crps":0.6499999999999999,"ae":0.6499999999999999},{"target_date":"2026-11-04","horizon":1,"point":2.15,"quantiles":null,"y":null,"crps":null,"ae":null}]},{"system":"timesfm-3","mode":"live","submitted_at":"2026-11-03T04:09:08-05:00","on_time":true,"source":{"model":"google/timesfm-3.0-pytorch","revision":"43046b85ec22d584a13f8098c2ed39c889e129c2","device":"cpu","covariates":6},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.6,"quantiles":{"0.1":2.7,"0.2":3.0,"0.3":3.2,"0.4":3.4,"0.5":3.6,"0.6":3.9,"0.7":4.2,"0.8":4.8,"0.9":5.6},"y":2.67,"crps":0.7188888888888889,"ae":0.9300000000000002},{"target_date":"2026-11-04","horizon":1,"point":3.6,"quantiles":{"0.1":2.5,"0.2":2.8,"0.3":3.1,"0.4":3.3,"0.5":3.6,"0.6":3.9,"0.7":4.3,"0.8":4.8,"0.9":5.6},"y":null,"crps":null,"ae":null}]},{"system":"timesfm-3-expert","mode":"live","submitted_at":"2026-11-03T04:09:20-05:00","on_time":true,"source":{"model":"google/timesfm-3.0-pytorch","revision":"43046b85ec22d584a13f8098c2ed39c889e129c2","device":"cpu","covariates":7},"values":[{"target_date":"2026-11-03","horizon":0,"point":3.1,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.8,"0.4":3.0,"0.5":3.1,"0.6":3.3,"0.7":3.5,"0.8":3.8,"0.9":4.1},"y":2.67,"crps":0.31444444444444447,"ae":0.43000000000000016},{"target_date":"2026-11-04","horizon":1,"point":3.2,"quantiles":{"0.1":2.5,"0.2":2.7,"0.3":2.9,"0.4":3.0,"0.5":3.2,"0.6":3.3,"0.7":3.5,"0.8":3.7,"0.9":4.1},"y":null,"crps":null,"ae":null}]}],"truth":[{"date":"2026-09-22","value":1.98},{"date":"2026-09-23","value":2.0},{"date":"2026-09-24","value":2.05},{"date":"2026-09-25","value":2.64},{"date":"2026-09-26","value":2.13},{"date":"2026-09-27","value":3.0},{"date":"2026-09-28","value":2.32},{"date":"2026-09-29","value":2.21},{"date":"2026-09-30","value":3.07},{"date":"2026-10-01","value":3.02},{"date":"2026-10-02","value":2.29},{"date":"2026-10-03","value":1.5},{"date":"2026-10-04","value":2.21},{"date":"2026-10-05","value":1.96},{"date":"2026-10-06","value":2.49},{"date":"2026-10-07","value":3.51},{"date":"2026-10-08","value":2.43},{"date":"2026-10-09","value":2.51},{"date":"2026-10-10","value":1.65},{"date":"2026-10-11","value":2.29},{"date":"2026-10-12","value":2.75},{"date":"2026-10-13","value":3.7},{"date":"2026-10-14","value":1.55},{"date":"2026-10-15","value":1.81},{"date":"2026-10-16","value":2.0},{"date":"2026-10-17","value":1.98},{"date":"2026-10-18","value":2.38},{"date":"2026-10-19","value":3.03},{"date":"2026-10-20","value":2.34},{"date":"2026-10-21","value":2.96},{"date":"2026-10-22","value":3.55},{"date":"2026-10-23","value":2.12},{"date":"2026-10-24","value":2.39},{"date":"2026-10-25","value":3.17},{"date":"2026-10-26","value":4.56},{"date":"2026-10-27","value":2.02},{"date":"2026-10-28","value":2.15},{"date":"2026-10-29","value":4.0},{"date":"2026-10-30","value":1.69},{"date":"2026-10-31","value":2.17},{"date":"2026-11-01","value":2.9},{"date":"2026-11-02","value":3.67},{"date":"2026-11-03","value":2.67}],"materials":[],"x_files":["MANIFEST.json","raw/aqhi_hourly.csv","raw/eccc_forecasts.csv","raw/weather_forecast_daily.csv","series.csv","task.json"]}