{"id":"W4308625237","doi":"10.1371/journal.pone.0277356","title":"Reasoning about mental states under uncertainty","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Consistency (knowledge bases); Psychology; Cognitive psychology; Frequentist inference; Information theory; Bayesian probability; Social psychology; Bayesian inference; Computer science; Artificial intelligence; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001796241,0.0000889019,0.0001321942,0.00004359392,0.0003115414,0.00001818038,0.0001263041,0.00001906797,0.01358794],"category_scores_gemma":[0.00001176191,0.00009164993,0.00003295315,0.0001077309,0.00002508722,0.00002014542,0.0001273332,0.0002642816,0.0003446031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001190966,"about_ca_system_score_gemma":0.00002521015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009970688,"about_ca_topic_score_gemma":0.000007269425,"domain_scores_codex":[0.9990097,0.00009473506,0.0001303005,0.0002498607,0.0002740892,0.0002412707],"domain_scores_gemma":[0.9996937,0.00004305266,0.00005190263,0.0001431035,0.00001487258,0.00005336154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002480097,0.03234771,0.4333205,0.0001901144,0.008013414,0.0004064454,0.1419951,0.005147173,0.04277784,0.1535389,0.1563644,0.02341839],"study_design_scores_gemma":[0.004510683,0.001650056,0.7686323,0.0002818735,0.0002412999,0.00005141156,0.02735044,0.001792439,0.001240763,0.00281836,0.1899894,0.001440968],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9766085,0.0003928835,0.000006139654,0.001402514,0.0001526246,0.0001319749,0.00002813545,0.0001114568,0.02116578],"genre_scores_gemma":[0.9840578,0.00001490485,0.0004466974,0.001131223,0.00008379795,0.00006053854,0.0001146483,0.00002103636,0.01406935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3353118,"threshold_uncertainty_score":0.9873137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03722006191695169,"score_gpt":0.2657769852304146,"score_spread":0.2285569233134629,"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."}}