{"id":"W2115276564","doi":"10.1111/j.1467-7687.2008.00793.x","title":"A competitive nonverbal false belief task for children and apes","year":2009,"lang":"en","type":"article","venue":"Developmental Science","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":182,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Nonverbal communication; Task (project management); Cognitive psychology; False belief; Theory of mind; Developmental psychology; Cognition","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":[0.0003775008,0.0001480608,0.0001441137,0.0001012595,0.000466581,0.00008159646,0.0002641271,0.0000386971,0.0001346999],"category_scores_gemma":[0.00004665481,0.0001313866,0.0000274869,0.0003179741,0.0003162924,0.0001436902,0.00008407552,0.00009234728,0.0001347421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008757794,"about_ca_system_score_gemma":0.0001341439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001993994,"about_ca_topic_score_gemma":0.000008876437,"domain_scores_codex":[0.9985929,0.00001400073,0.0001744937,0.0005470631,0.0002373462,0.0004342217],"domain_scores_gemma":[0.9996269,0.00004041253,0.00005386824,0.00008183131,0.00004557776,0.000151378],"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":[0.0002646414,0.0006131231,0.1392441,0.000009714379,0.00008520451,0.00002667651,0.02312971,0.000001317359,0.03245164,0.3459665,0.006969905,0.4512374],"study_design_scores_gemma":[0.0005826019,0.0001604767,0.9848889,0.00002120016,0.000003803406,0.00007646031,0.0004195003,0.000003490745,0.0007551407,0.0003796594,0.01248312,0.00022565],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672628,0.0001302524,0.0001843757,0.0007596412,0.0002273048,0.0004184545,0.00002175997,0.00007928496,0.03091611],"genre_scores_gemma":[0.987892,0.000006908811,0.009838349,0.001387339,0.00005412513,0.00001551034,0.00001774176,0.000006355341,0.0007816596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8456448,"threshold_uncertainty_score":0.5357791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008774160006883771,"score_gpt":0.2704280557340986,"score_spread":0.2616538957272148,"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."}}