{"id":"W2956977098","doi":"10.1007/s11409-019-09198-4","title":"Does domain matter? Monitoring accuracy across domains","year":2019,"lang":"en","type":"article","venue":"Metacognition and Learning","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health; York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Overconfidence effect; Task (project management); Calibration; Psychology; Generality; Resolution (logic); Cognitive psychology; Cognition; Domain (mathematical analysis); Artificial intelligence; Metacognition; Domain knowledge; Computer science; Machine learning; Developmental psychology; Statistics; Social psychology; Mathematics","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":[0.002995988,0.0001720756,0.0003288798,0.0001651602,0.0004770181,0.0009927665,0.0002812603,0.00009657888,0.002272973],"category_scores_gemma":[0.0009947084,0.0001023166,0.0001266088,0.0002878074,0.00006390866,0.0006951874,0.0001834581,0.0004139789,0.005421899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002486506,"about_ca_system_score_gemma":0.00001381401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001548213,"about_ca_topic_score_gemma":0.000004138424,"domain_scores_codex":[0.9977303,0.0003166367,0.0005298614,0.0005710463,0.0005281321,0.0003240422],"domain_scores_gemma":[0.9975494,0.001583025,0.0002934639,0.0003038714,0.0001440089,0.0001262288],"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":[0.00003325019,0.00003194429,0.3363387,0.000005198699,0.00001266703,0.000009770895,0.001788451,0.0001073123,0.003508736,0.00003670126,0.000114736,0.6580126],"study_design_scores_gemma":[0.002825923,0.0002168252,0.5146496,0.0002430261,0.00006637416,0.00007883376,0.05393656,0.0008474316,0.0033884,0.1004786,0.3220964,0.001172045],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938811,0.00005507518,0.0009808771,0.0003518572,0.001124118,0.0001346996,0.000008817286,0.0000652357,0.003398233],"genre_scores_gemma":[0.9934351,0.00002329298,0.001896003,0.0002036812,0.0001598034,0.000008790822,0.000005039418,0.00001859508,0.00424963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6568405,"threshold_uncertainty_score":0.9986391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0662592283616116,"score_gpt":0.3990462324451357,"score_spread":0.332787004083524,"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."}}