{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00356244,0.0005616832,0.0004712029,0.001387934,0.0001891425,0.001365897,0.0005577132,0.0004728723,0.001169899],"category_scores_gemma":[0.02279046,0.0002556959,0.0004001851,0.0007958293,0.0004601618,0.001473359,0.0009145845,0.000371277,0.0002537794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002360177,"about_ca_system_score_gemma":0.0003154679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009210592,"about_ca_topic_score_gemma":0.001652234,"domain_scores_codex":[0.9985599,0.000740832,0.0001638912,0.0001819162,0.000270073,0.00008332877],"domain_scores_gemma":[0.9846478,0.008520878,0.004272505,0.001024342,0.0009212269,0.0006133593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002351923,0.0001613159,0.9424024,0.0001926351,0.0001880744,0.00007388687,0.001526184,0.0004409461,0.001338825,0.0003261893,0.000272933,0.05284148],"study_design_scores_gemma":[0.000007035267,0.0002016149,0.9952502,0.00008029951,0.00005384497,0.000269821,0.0006943431,0.001252715,0.0008702031,0.0007041249,0.0006029198,0.00001279428],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962252,0.0004316371,0.001822739,0.00004176846,0.000009688762,0.00004649572,0.0002776356,0.00001885701,0.001125887],"genre_scores_gemma":[0.9948931,0.00042119,0.003942888,0.00001489268,0.00000720364,0.00006703063,0.0004675317,0.0000076519,0.0001785125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00356244,"threshold_uncertainty_score":0.01884019,"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."}}