{"id":"W4404444986","doi":"10.1609/aiide.v20i1.31885","title":"Evaluating the Effects of AI Directors for Quest Selection","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Canadian Institute for Advanced Research","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence; Psychology","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":[0.0004714332,0.0002588567,0.0002633255,0.0001559536,0.0002024988,0.0008321531,0.0008950077,0.00006063601,0.00001074312],"category_scores_gemma":[0.001088744,0.0001611509,0.0002002238,0.0004734577,0.0002621403,0.001248324,0.0003137928,0.0002936125,0.00001313546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001125888,"about_ca_system_score_gemma":0.00009265396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000442709,"about_ca_topic_score_gemma":0.000007279735,"domain_scores_codex":[0.9980618,0.00002750738,0.000592215,0.0005434809,0.0004513182,0.0003236953],"domain_scores_gemma":[0.9979784,0.0008943543,0.0002671986,0.0001929237,0.0006032702,0.00006386317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001523744,0.0001942425,0.0001238288,0.0002720642,0.00008562511,3.934576e-7,0.003903368,0.00004755,0.08508871,0.605147,0.0001042735,0.3048806],"study_design_scores_gemma":[0.00002047083,0.001477653,0.00004566712,0.0008850445,0.00002529404,0.000004803021,0.0009618982,0.1867799,0.7368644,0.07254388,0.0002393103,0.0001516427],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8216894,0.0002527742,0.1590186,0.006983198,0.002496139,0.003018544,0.00002619605,0.000194786,0.00632028],"genre_scores_gemma":[0.9988549,0.0000365776,0.0003289613,0.000187965,0.00006973603,0.0001617482,9.578669e-7,0.00001642013,0.0003426719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6517757,"threshold_uncertainty_score":0.8024471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05483724577607038,"score_gpt":0.3546303239359725,"score_spread":0.2997930781599021,"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."}}