{"id":"W4389914237","doi":"10.1073/pnas.2303706120","title":"Validation of the reading the mind in the eyes test requires an interpretable factor model","year":2023,"lang":"en","type":"letter","venue":"Proceedings of the National Academy of Sciences","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Macquarie University; Australian Government; John Templeton Foundation","keywords":"Reading (process); Factor (programming language); Test (biology); Artificial intelligence; Psychology; Computer science; Natural language processing; Biology; Philosophy; Linguistics; Programming language; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0250247,0.0006677659,0.001134991,0.0007722994,0.001084935,0.001714454,0.002248514,0.005425554,0.004984644],"category_scores_gemma":[0.1760488,0.0002308577,0.0008836346,0.0004263149,0.002955231,0.002110853,0.000881723,0.007168922,0.004383725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001777056,"about_ca_system_score_gemma":0.002680606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008863283,"about_ca_topic_score_gemma":0.009642405,"domain_scores_codex":[0.9906533,0.005314558,0.001163075,0.0008066163,0.001807722,0.0002546122],"domain_scores_gemma":[0.8372011,0.1372261,0.001924763,0.007627673,0.01482546,0.001195006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001657899,0.0006942344,0.1015399,0.0002550879,0.0003236695,0.004296628,0.001468914,0.004705942,0.002244177,0.04243176,0.4780315,0.3623503],"study_design_scores_gemma":[0.001104514,0.001248321,0.08927091,0.001148499,0.0002260035,0.007305223,0.002363506,0.1755547,0.004411857,0.550965,0.1660594,0.0003421226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06715575,0.000754347,0.03182076,0.8576276,0.01181884,0.0002331793,0.001449035,0.0005216533,0.02861887],"genre_scores_gemma":[0.6397498,0.0008886494,0.05533936,0.271351,0.01336527,0.0006832716,0.001444574,0.0003378781,0.01684014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0250247,"threshold_uncertainty_score":0.1323448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1442034820622564,"score_gpt":0.3820070259423926,"score_spread":0.2378035438801362,"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."}}