{"id":"W2783668521","doi":"10.1016/j.psychres.2018.01.026","title":"Reliability of two social cognition tests: The combined stories test and the social knowledge test","year":2018,"lang":"en","type":"article","venue":"Psychiatry Research","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reliability (semiconductor); Psychology; Cognition; Test (biology); Social cognition; Psychometrics; Social cognitive theory; Clinical psychology; Developmental psychology; Psychiatry","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":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.00261604,0.000153493,0.0002302208,0.00007230865,0.002208108,0.00006786143,0.0003719997,0.0001122467,0.000405728],"category_scores_gemma":[0.0004746779,0.00008950612,0.0001095881,0.0006378235,0.00338992,0.00005628758,0.0001543642,0.0005764532,0.0001975249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003973833,"about_ca_system_score_gemma":0.0002040488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000148312,"about_ca_topic_score_gemma":0.0003785822,"domain_scores_codex":[0.9977469,0.0006111858,0.0003655103,0.0003547506,0.0004873938,0.0004342924],"domain_scores_gemma":[0.9974116,0.001503614,0.0001036893,0.0002222613,0.0006974741,0.00006133869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001557695,0.003749801,0.3652269,0.000184424,0.0001485571,6.78686e-7,0.04214596,1.496696e-8,0.0002687572,0.2473417,0.3312967,0.008078899],"study_design_scores_gemma":[0.003419743,0.000257392,0.8922592,0.00005466428,0.00002883187,0.000003247839,0.004442453,0.000005155552,0.000008726187,0.08724992,0.01214332,0.0001273889],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8307247,0.0007086355,0.00001235325,0.06683157,0.002945516,0.0009798459,0.0001140771,0.00005632966,0.09762701],"genre_scores_gemma":[0.9933693,0.00003478341,0.00002862289,0.0003315524,0.003861012,0.00006207005,0.00001611029,0.00001677775,0.002279813],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5270323,"threshold_uncertainty_score":0.9993223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06028750589072,"score_gpt":0.4127366358973296,"score_spread":0.3524491300066095,"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."}}