{"id":"W3131239688","doi":"10.1371/journal.pone.0244141","title":"Are the classic false belief tasks cursed? Young children are just as likely as older children to pass a false belief task when they are not required to overcome the curse of knowledge","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Curse; False belief; Psychology; Task (project management); Variety (cybernetics); Theory of mind; Social psychology; Cognitive psychology; Test (biology); Cognition; Litmus; Computer science; Artificial intelligence; Sociology","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006890435,0.0007181866,0.001098292,0.0002343425,0.0006529693,0.0001963844,0.001375969,0.0003421761,0.001071057],"category_scores_gemma":[0.0009302095,0.000508945,0.0003631893,0.0007547257,0.00019551,0.0001401144,0.0008503791,0.00109509,0.003565167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001747898,"about_ca_system_score_gemma":0.0002284663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000519257,"about_ca_topic_score_gemma":0.001180646,"domain_scores_codex":[0.9949293,0.0006958108,0.000912143,0.001398995,0.001010224,0.001053553],"domain_scores_gemma":[0.9959735,0.0003575332,0.0007607845,0.001930969,0.0005357052,0.0004415325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007648856,0.01155975,0.8519359,0.0001634451,0.004430663,0.0001817694,0.06597015,0.00002768618,0.008075618,0.004298479,0.04845231,0.004139322],"study_design_scores_gemma":[0.001505122,0.0003265983,0.9860107,0.001453298,0.0004841774,0.00007715553,0.003375588,0.000002757798,0.00172304,0.0002811024,0.004020575,0.0007398665],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.966323,0.002043425,0.000009420551,0.02481235,0.0004416371,0.001889817,0.0005266803,0.0001986373,0.003755076],"genre_scores_gemma":[0.9787703,0.00008723377,0.0001991759,0.006563113,0.0009308025,0.0003172327,0.0001355424,0.0001620217,0.01283464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1340748,"threshold_uncertainty_score":0.9998421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04400144204320148,"score_gpt":0.2854126884626472,"score_spread":0.2414112464194458,"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."}}