{"id":"W4416402838","doi":"10.1177/09637214251391158","title":"Metacognition and Uncertainty Communication in Humans and Large Language Models","year":2025,"lang":"en","type":"article","venue":"Current Directions in Psychological Science","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Canadian Institute for Advanced Research","keywords":"Metacognition; Cognition; Language acquisition; Task analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.001166318,0.00005482208,0.00007896742,0.0001605172,0.0005597224,0.00007611376,0.0001618489,0.00004987985,0.0000272588],"category_scores_gemma":[0.0002856227,0.0000433096,0.0000134735,0.001292557,0.0006319124,0.0004167698,0.00006469425,0.0001705838,0.000001699615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001075236,"about_ca_system_score_gemma":0.00002250542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000904317,"about_ca_topic_score_gemma":0.00751014,"domain_scores_codex":[0.9990783,0.0001780688,0.0001287557,0.0002672072,0.0001375864,0.0002100708],"domain_scores_gemma":[0.99971,0.00006446515,0.00002702447,0.000110588,0.00004360262,0.00004431091],"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":[0.00002454255,0.0008122853,0.03114008,0.00001701006,0.000003438326,0.000002377277,0.03872669,0.00005823576,0.0009745342,0.4139806,0.0003521959,0.513908],"study_design_scores_gemma":[0.001579556,0.00006274733,0.7163119,0.0004056511,0.00002418215,0.000002216157,0.04859252,0.005203511,0.0000472958,0.2077406,0.01957282,0.0004570383],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9592729,0.005380207,0.000336276,0.0007539347,0.0002164923,0.0002072187,0.000003431966,0.00004516697,0.03378435],"genre_scores_gemma":[0.9967111,0.002915798,0.0001170931,0.00008868762,0.00001278443,0.00003767939,0.000003564405,8.09763e-7,0.0001124584],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6851718,"threshold_uncertainty_score":0.4304989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05229831553649199,"score_gpt":0.4509386437313984,"score_spread":0.3986403281949064,"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."}}