{"id":"W4220992060","doi":"10.1016/j.dr.2022.101021","title":"Looking for the lighthouse: A systematic review of advanced theory-of-mind tests beyond preschool","year":2022,"lang":"en","type":"review","venue":"Developmental Review","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":78,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brock University","funders":"","keywords":"Psychology; Theory of mind; Test (biology); Empathy; Operationalization; Cognitive psychology; PsycINFO; Developmental psychology; Social cognition; Task (project management); Reading (process); Social psychology; Cognition; Epistemology; Linguistics; MEDLINE","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005040256,0.0007892705,0.00578866,0.0001595227,0.0002321718,0.00001709114,0.00139907,0.0001502562,0.004990138],"category_scores_gemma":[0.002594317,0.0004790854,0.001408281,0.0008984049,0.0000989886,0.00005799028,0.0004238858,0.0006378751,0.0002162416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002763649,"about_ca_system_score_gemma":0.0007967684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001248352,"about_ca_topic_score_gemma":6.982011e-7,"domain_scores_codex":[0.9933076,0.001218386,0.003503391,0.0008067215,0.000672583,0.0004913135],"domain_scores_gemma":[0.9920605,0.003574687,0.00320736,0.0009330761,0.0001193653,0.0001049531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004987246,0.00005433548,6.803467e-7,0.5754799,0.0006402154,0.00000493895,0.0001216104,9.356458e-9,9.42207e-8,0.0009156512,0.001935669,0.420842],"study_design_scores_gemma":[0.00009614805,0.00004217033,0.000004308043,0.4890284,0.002639753,0.0001101992,0.00004529904,1.435839e-8,3.270994e-7,0.00001437825,0.50775,0.0002690172],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.78977e-7,0.9806166,0.00002892485,0.00006391318,0.0005251204,0.01386466,0.0001208552,0.00003262336,0.00474717],"genre_scores_gemma":[7.151065e-7,0.9878636,0.001461855,0.0009169179,0.00004715441,0.006787855,0.000240144,0.0001364771,0.002545283],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5058143,"threshold_uncertainty_score":0.9997661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04593237548020817,"score_gpt":0.3636672752264456,"score_spread":0.3177348997462374,"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."}}