{"id":"W4386724574","doi":"10.31234/osf.io/x2f4a","title":"Shadows of wisdom: Classifying meta-cognitive and morally-grounded narrative content via Large Language Models","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Narrative; Humility; Psychology; Categorization; Classifier (UML); Workflow; Social psychology; Computer science; Artificial intelligence; Linguistics; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007894401,0.0004465491,0.001020397,0.0002485793,0.0001080501,0.0001940211,0.0009271845,0.0002837615,0.00004327871],"category_scores_gemma":[0.0000809065,0.0003676555,0.0003245206,0.0001911693,0.00009435711,0.0005052762,0.003263153,0.0006243492,0.00001057584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006588165,"about_ca_system_score_gemma":0.0001409224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001468631,"about_ca_topic_score_gemma":0.000501406,"domain_scores_codex":[0.9969586,0.0002107368,0.000675894,0.001167494,0.0005425254,0.0004447068],"domain_scores_gemma":[0.9979924,0.0002730456,0.0004077897,0.0008420137,0.0003462174,0.0001385492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000133443,0.0006828501,0.0003735897,0.001881482,0.01384728,0.0005338235,0.4244699,0.02377336,0.004087951,0.4946359,0.0004337761,0.03514665],"study_design_scores_gemma":[0.0006609175,0.00004694935,0.0001205784,0.0001672427,0.0003206606,0.000008062174,0.009052214,0.9332985,0.0009526385,0.05491563,0.00000389023,0.0004527362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04386329,0.001086137,0.9505007,0.0006505645,0.000387946,0.0007764864,0.00004970007,0.0003590554,0.002326083],"genre_scores_gemma":[0.9299215,0.00005384595,0.06762382,0.0003444212,0.00005561732,0.0001693815,0.00002520219,0.00003261598,0.001773598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9095252,"threshold_uncertainty_score":0.9998775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.231357794968577,"score_gpt":0.3276528238762003,"score_spread":0.09629502890762323,"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."}}