{"id":"W4317606158","doi":"10.31234/osf.io/etjqh","title":"The future of metacognition research: balancing construct breadth with measurement rigor","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Max-Planck-Gesellschaft; Leverhulme Trust; Wellcome Trust; Canadian Institute for Advanced Research","keywords":"Metacognition; Construct (python library); Psychology; Scope (computer science); Cognitive psychology; Cognition; Rigour; Computer science; Epistemology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02908956,0.0002639023,0.0004313282,0.0003263605,0.0004691662,0.00007886409,0.0004835353,0.0003142818,0.0003080525],"category_scores_gemma":[0.0005866171,0.0001500247,0.0001125161,0.0005481808,0.0004755664,0.00002052588,0.0002894524,0.003419002,0.0001075813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001308239,"about_ca_system_score_gemma":0.0002862113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008523862,"about_ca_topic_score_gemma":0.000253954,"domain_scores_codex":[0.9905223,0.006519606,0.0005062594,0.0006294553,0.001291313,0.0005311139],"domain_scores_gemma":[0.9958877,0.001121175,0.0003774555,0.0008863194,0.001675476,0.00005187811],"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":[0.00153733,0.0003284019,0.01823402,0.0007620398,0.005649355,0.00009992994,0.02081476,0.00014878,0.002718483,0.2593486,0.08355489,0.6068034],"study_design_scores_gemma":[0.005545818,0.00222969,0.4327479,0.004234002,0.0009826031,0.0002163652,0.1158995,0.0006089533,0.005339437,0.1347728,0.2946429,0.002780132],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2251751,0.006017875,0.2009083,0.01515789,0.02161828,0.004701409,0.0002282535,0.001788938,0.524404],"genre_scores_gemma":[0.970506,0.00004936975,0.01943937,0.0000852469,0.001131355,0.0002387637,0.00005914647,0.0001011258,0.008389621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7453309,"threshold_uncertainty_score":0.9997566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3110970659156035,"score_gpt":0.4680265977631344,"score_spread":0.1569295318475309,"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."}}