{"id":"W3214959488","doi":"10.1613/jair.1.13219","title":"Teaching People by Justifying Tree Search Decisions: An Empirical Study in Curling","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Institute for Advanced Research","keywords":"Curling; Outcome (game theory); Counterfactual thinking; Decision tree; Computer science; Action (physics); Tree (set theory); Decision tree learning; Machine learning; Artificial intelligence; Value (mathematics); Psychology; Cognitive psychology; Mathematics; Social psychology; Mathematical economics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01065499,0.0005976395,0.0005726828,0.001088788,0.00120852,0.002017563,0.001247917,0.001913538,0.00702269],"category_scores_gemma":[0.1273009,0.0004245311,0.0004168357,0.0007046628,0.001888184,0.003831998,0.001207018,0.002958721,0.001442242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007307234,"about_ca_system_score_gemma":0.0005822573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002778998,"about_ca_topic_score_gemma":0.003916495,"domain_scores_codex":[0.9921239,0.005496526,0.0003813795,0.0006281817,0.001056154,0.0003138308],"domain_scores_gemma":[0.8312994,0.1494135,0.006388772,0.007020077,0.003897098,0.00198126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005013951,0.02979923,0.4242719,0.003280999,0.0004207155,0.002927881,0.1381114,0.01427076,0.01160726,0.02144771,0.02292988,0.3259183],"study_design_scores_gemma":[0.002135775,0.01651228,0.4654119,0.001639909,0.000424168,0.003414886,0.1063186,0.2484736,0.01491369,0.04631735,0.09370417,0.0007335637],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922513,0.0001770107,0.003409862,0.0002875945,0.00002139367,0.0001745449,0.0000916944,0.00008443611,0.003502055],"genre_scores_gemma":[0.9911582,0.000138029,0.006147746,0.0002804353,0.00002023365,0.0001947534,0.0002356452,0.00007023953,0.001754805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01065499,"threshold_uncertainty_score":0.05634964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4127187630247911,"score_gpt":0.4821149390837808,"score_spread":0.06939617605898973,"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."}}