{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003918683,0.000258566,0.0002767317,0.0001115367,0.0001483702,0.0003042479,0.0008281932,0.0001338078,0.0008370692],"category_scores_gemma":[0.00005430331,0.0001610703,0.000180428,0.0006406615,0.0002683448,0.0001818759,0.000198165,0.0003865194,0.0006983998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003694769,"about_ca_system_score_gemma":0.00002015607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009072295,"about_ca_topic_score_gemma":0.00001359409,"domain_scores_codex":[0.9981421,0.00002059647,0.0003771641,0.0006169828,0.0004200109,0.0004231116],"domain_scores_gemma":[0.9991666,0.00005039046,0.00009601665,0.0002113818,0.0003548772,0.000120746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001479978,0.0002676092,0.0001197225,0.00001882546,0.00002661654,0.000002915834,0.003491763,0.000007554226,0.01446523,0.7134305,0.003319558,0.2647017],"study_design_scores_gemma":[0.00007783909,0.002529644,0.002256311,0.0008105307,0.0002543741,0.00002474367,0.009911804,0.002965039,0.118429,0.8538364,0.007842851,0.001061478],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9102157,0.000286903,0.001227411,0.02162966,0.002631985,0.0008142212,0.0000365405,0.0002320059,0.06292555],"genre_scores_gemma":[0.9926408,0.00002026819,0.0002188039,0.0002860026,0.0001472517,0.0001439986,5.283057e-7,0.00002047201,0.006521889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2636402,"threshold_uncertainty_score":0.9165321,"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."}}