{"id":"W3207461908","doi":"10.1016/j.adolescence.2021.10.001","title":"Measuring advanced theory of mind: Do story‐based tasks work?","year":2021,"lang":"en","type":"article","venue":"Journal of Adolescence","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"Narodowe Centrum Nauki","keywords":"Psychology; Theory of mind; Work (physics); Cognitive science; Cognitive psychology; Applied psychology; Psychoanalysis; Cognition; Psychiatry","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":[0.0008298939,0.0001088085,0.0002705209,0.0000963662,0.0000500612,0.00001390346,0.0002074097,0.00005893643,0.0005968657],"category_scores_gemma":[0.0002602385,0.00009495944,0.0001485136,0.0002011944,0.00005962054,0.00006054531,0.00002856109,0.0005011893,0.00003332271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004769317,"about_ca_system_score_gemma":0.0002118733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.580344e-7,"about_ca_topic_score_gemma":4.494021e-7,"domain_scores_codex":[0.998699,0.0002609542,0.000386415,0.0001635052,0.0003049916,0.0001851156],"domain_scores_gemma":[0.9988405,0.0001480958,0.0004545868,0.0001950792,0.0002690566,0.00009266292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00283913,0.00134581,0.3810635,0.0001714503,0.0003146746,0.001358337,0.006801169,0.0008981677,0.08230322,0.002615178,0.002936244,0.5173531],"study_design_scores_gemma":[0.001187017,0.0001604351,0.9791272,0.001546797,0.00003286763,0.0001089495,0.001183177,0.000001484608,0.01019843,0.0001231222,0.00617289,0.0001576322],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894227,0.004092157,0.002107495,0.0005307551,0.0008804854,0.00005017231,0.00000180072,0.000008034609,0.002906341],"genre_scores_gemma":[0.9949924,0.00002087032,0.004115907,0.0001972741,0.0001389865,5.260289e-7,4.180815e-7,0.00001298037,0.00052069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5980637,"threshold_uncertainty_score":0.6535261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03268063581568743,"score_gpt":0.276184905650411,"score_spread":0.2435042698347236,"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."}}