{"id":"W2090116619","doi":"10.1007/s00426-014-0606-0","title":"A new paper and pencil task reveals adult false belief reasoning bias","year":2014,"lang":"en","type":"article","venue":"Psychological Research","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kwantlen Polytechnic University; Simon Fraser University","funders":"Canada Research Chairs","keywords":"Sandbox (software development); Task (project management); Perspective (graphical); Psychology; Theory of mind; Object (grammar); Pencil (optics); Cognitive psychology; Inference; Computer science; Artificial intelligence; Cognition","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003949465,0.0002244082,0.000336696,0.0001707119,0.0003568205,0.0001409643,0.0004556402,0.0002839964,0.005491191],"category_scores_gemma":[0.004329235,0.0001657239,0.00008154957,0.000494097,0.0002407111,0.00007287643,0.0002454092,0.00123921,0.00324516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000440475,"about_ca_system_score_gemma":0.00003269381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002699827,"about_ca_topic_score_gemma":0.0000242352,"domain_scores_codex":[0.9957093,0.001105235,0.0003745897,0.001053654,0.0007606851,0.0009965545],"domain_scores_gemma":[0.9974666,0.001109237,0.0000685536,0.0005738886,0.0002237508,0.0005579588],"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":[0.0006661815,0.0004929483,0.07159899,0.0000251273,0.00006935496,0.0001089306,0.002764495,5.079141e-7,0.005366932,0.2030187,0.2384409,0.4774469],"study_design_scores_gemma":[0.001086449,0.0009521198,0.7718521,0.00009294458,0.000005068932,0.00006382979,0.0002559729,0.000007755539,0.00001113246,0.0106024,0.214816,0.000254153],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7242606,0.0009325921,0.0003509393,0.006306863,0.0002666329,0.000350817,0.000003380135,0.0001474549,0.2673808],"genre_scores_gemma":[0.9703699,0.0001773265,0.003263398,0.002214287,0.0005191579,0.00005162976,0.000007212286,0.00003025506,0.02336685],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7002532,"threshold_uncertainty_score":0.9975309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1524668123643225,"score_gpt":0.4389159677443614,"score_spread":0.2864491553800389,"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."}}