{"id":"W3094804169","doi":"10.1371/journal.pone.0241721","title":"Testing the stability of theory of mind: A longitudinal approach","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Stability (learning theory); Computer science; Machine learning","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":[0.0003873103,0.00006273015,0.0001814817,0.00001140213,0.00003083083,0.000003073054,0.0001458625,0.00002812131,0.0005151041],"category_scores_gemma":[0.0004606958,0.00004317107,0.00003477784,0.0001451326,0.0001002253,0.00001160092,0.00005552984,0.0001481824,0.00002456115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005612142,"about_ca_system_score_gemma":0.00002331241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009393012,"about_ca_topic_score_gemma":3.165019e-7,"domain_scores_codex":[0.9992331,0.000125242,0.0001970279,0.0001812446,0.0001567022,0.0001066504],"domain_scores_gemma":[0.9993173,0.0003186339,0.0001077751,0.0001658137,0.00005844443,0.00003198673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003664641,0.00301104,0.8800272,0.0003269668,0.0005422389,0.000002693458,0.02385038,0.000002998116,0.07812472,0.007281628,0.00008172636,0.006381982],"study_design_scores_gemma":[0.0002726311,0.0002413844,0.9871084,0.0000549655,0.00007694471,0.000001092641,0.001429871,0.00008054189,0.0104083,0.0002084794,0.00004047631,0.00007693037],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714171,0.000137347,0.0001048852,0.0003761957,0.000009232584,0.0001455883,0.000006383083,0.00001487206,0.02778836],"genre_scores_gemma":[0.9957064,4.665071e-7,0.004105727,0.00007026056,0.00005646014,0.000007368205,0.000002100569,0.000007035298,0.00004422473],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1070812,"threshold_uncertainty_score":0.5640029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2206209895191525,"score_gpt":0.2711594727080062,"score_spread":0.05053848318885371,"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."}}