{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01278441,0.0001289833,0.0005081631,0.0009969571,0.0003452318,0.0003739678,0.0005523786,0.000100601,0.0004338571],"category_scores_gemma":[0.001655843,0.0001298286,0.0001282233,0.001253629,0.00007113931,0.0005547245,0.0001614615,0.001683176,0.0001193284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002392069,"about_ca_system_score_gemma":0.000239735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001080337,"about_ca_topic_score_gemma":0.002254669,"domain_scores_codex":[0.9967526,0.0002202812,0.001631144,0.0003945597,0.000423196,0.0005781953],"domain_scores_gemma":[0.9980666,0.0005890178,0.0002513546,0.0003616545,0.0004851788,0.0002461666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002372322,0.004453843,0.7481876,0.00003521931,0.00008598712,0.0006099299,0.02296605,0.01197113,0.0007279537,0.01161317,0.0007763921,0.1983355],"study_design_scores_gemma":[0.0005859345,0.003228812,0.09085584,0.0004482559,0.00002524571,0.0001853062,0.1576092,0.6319863,0.005006418,0.09655152,0.0124828,0.001034441],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9844769,0.001484715,0.01170957,0.001094231,0.0002894883,0.0001382413,0.000008001939,0.000004600698,0.0007942331],"genre_scores_gemma":[0.997822,0.0007358533,0.0007240174,0.00004071902,0.0004245105,0.000003576406,0.000002961665,0.00002141342,0.000224878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6573318,"threshold_uncertainty_score":0.7312656,"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."}}