{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001161336,0.000607448,0.0004242154,0.0004792516,0.0002790563,0.0007442857,0.000984899,0.001355908,0.008477941],"category_scores_gemma":[0.009581655,0.0004913714,0.0001814048,0.0001798093,0.000765348,0.001382156,0.0006389868,0.00181234,0.00127658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001940521,"about_ca_system_score_gemma":0.0003583256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00110153,"about_ca_topic_score_gemma":0.001680757,"domain_scores_codex":[0.9995011,0.00005544163,0.00005314524,0.0001282089,0.0002262891,0.00003579833],"domain_scores_gemma":[0.9919428,0.004259738,0.001393161,0.00119064,0.000498924,0.0007147011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.005899836,0.003442959,0.06300759,0.0004655643,0.0001157222,0.004579198,0.002218666,0.0003367059,0.8167524,0.003590439,0.007329836,0.09226098],"study_design_scores_gemma":[0.001224982,0.006910996,0.627342,0.0001658279,0.0002378189,0.03338451,0.001846698,0.01232038,0.2894874,0.01744206,0.009425684,0.0002117177],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896079,0.0001800887,0.004275195,0.0005371498,0.0001817737,0.00003771738,0.0005051263,0.0001345703,0.004540566],"genre_scores_gemma":[0.9878629,0.000159877,0.00597155,0.0004798084,0.00005199052,0.00004717855,0.0004883315,0.00007652417,0.004861942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008477941,"threshold_uncertainty_score":0.02836156,"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."}}