{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002812382,0.0001568345,0.0002102008,0.0001768874,0.0002906577,0.00006243603,0.00227478,0.000220392,0.00003892406],"category_scores_gemma":[0.003596486,0.00006868294,0.0001292734,0.000955629,0.001374451,0.0003621325,0.0002574195,0.0008599947,0.000001793768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003939302,"about_ca_system_score_gemma":0.00005581523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009625369,"about_ca_topic_score_gemma":8.518394e-7,"domain_scores_codex":[0.9975523,0.00006049543,0.0005307487,0.000348047,0.001269765,0.0002386621],"domain_scores_gemma":[0.9957659,0.002937132,0.0009153773,0.00003840832,0.0003334662,0.000009748528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001076881,0.0006229801,0.1928205,0.001445048,0.0003947489,3.226515e-7,0.1306801,0.001736509,0.1632468,0.07268387,0.4259773,0.01028401],"study_design_scores_gemma":[0.0006821734,0.0004369616,0.2866183,0.003455649,0.0003037073,0.00005557346,0.03066726,0.02375257,0.08157356,0.5662885,0.005270481,0.0008952727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7688644,0.00005689928,9.807493e-7,0.2169901,0.0001017748,0.000518734,0.000162397,0.000009678221,0.01329504],"genre_scores_gemma":[0.9835583,0.000005396119,0.00007473936,0.01502228,0.0003547747,0.00004438318,0.000001077728,0.00001074812,0.0009283359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4936046,"threshold_uncertainty_score":0.5064223,"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."}}