{"id":"W3091036576","doi":"10.6084/m9.figshare.15164921.v1","title":"Evaluating real-time probabilistic forecasts with application to National Basketball Association outcome prediction","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Basketball; Outcome (game theory); Probabilistic logic; Association (psychology); Computer science; Econometrics; Statistics; Psychology; Artificial intelligence; Geography; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005355228,0.0002468511,0.0004512673,0.0002376962,0.0001278739,0.0001741731,0.0002474419,0.0002892397,0.06550518],"category_scores_gemma":[0.00173805,0.0002720129,0.0000991331,0.0004034915,0.00000284474,0.0001592712,0.00006980828,0.0002534394,0.007429442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009444222,"about_ca_system_score_gemma":0.0001574859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001204851,"about_ca_topic_score_gemma":0.0001383699,"domain_scores_codex":[0.9980494,0.00001256735,0.0007590652,0.0006394659,0.0002639988,0.000275471],"domain_scores_gemma":[0.9979045,0.0001072791,0.0009977919,0.0004139959,0.0004772096,0.00009920896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007042596,0.0000424614,0.0008903586,0.000232765,0.00005267475,0.000001394036,0.00001254151,0.004845598,3.806016e-7,0.00003235953,0.9937754,0.0001070482],"study_design_scores_gemma":[0.0002021262,0.0000883785,0.00797813,0.0003940088,0.00002223166,0.000002719915,0.000002305636,0.04022604,7.568856e-7,0.0001149528,0.9506477,0.0003207204],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00007887245,0.00005115757,0.00001097523,0.00009417204,0.0001048392,0.0006223429,0.9971849,0.00003493901,0.001817829],"genre_scores_gemma":[0.0003683899,0.00001282276,0.000161307,0.0002036724,0.0004799685,0.0007716505,0.9964736,0.00003111573,0.001497547],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05807574,"threshold_uncertainty_score":0.9999732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08642597181860097,"score_gpt":0.3003286255132063,"score_spread":0.2139026536946054,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}