{"id":"W4393147499","doi":"10.1609/aaai.v38i9.28820","title":"How to Evaluate Behavioral Models","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of British Columbia","funders":"Universities Space Research Association; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Psychology; Computer science","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04595368,0.002238557,0.002225672,0.003506032,0.001320272,0.0103121,0.003532907,0.003837052,0.007368232],"category_scores_gemma":[0.2600628,0.001108577,0.001886409,0.001953069,0.004431979,0.01504304,0.003717939,0.006437798,0.00294737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004058414,"about_ca_system_score_gemma":0.00530396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006685336,"about_ca_topic_score_gemma":0.004165202,"domain_scores_codex":[0.964842,0.02240324,0.002198399,0.002853728,0.006709015,0.000993586],"domain_scores_gemma":[0.8544774,0.09478331,0.00764244,0.01746649,0.02280334,0.002826956],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000506161,0.0004850661,0.01965891,0.0009844992,0.0007147039,0.0001646049,0.001309355,0.1740114,0.002029585,0.4348997,0.03227736,0.3329587],"study_design_scores_gemma":[0.00009514447,0.0002023188,0.002785576,0.0005321521,0.0001004728,0.00008255698,0.0005431519,0.3288741,0.002042213,0.6521436,0.01246976,0.0001289598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03154374,0.001372783,0.9281941,0.01508689,0.0006012099,0.0004464722,0.00117335,0.002429191,0.01915232],"genre_scores_gemma":[0.4206609,0.001127829,0.5670474,0.003172794,0.0003347345,0.001087292,0.002067154,0.001138385,0.003363542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9540463,"threshold_uncertainty_score":0.2430292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5217428008825785,"score_gpt":0.4303989367174971,"score_spread":0.09134386416508145,"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."}}