{"id":"W4399117309","doi":"10.3758/s13428-024-02441-0","title":"Shadows of wisdom: Classifying meta-cognitive and morally grounded narrative content via large language models","year":2024,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychology of Moral and Emotional Judgment","field":"Neuroscience","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; John Templeton Foundation","keywords":"Narrative; Categorization; Humility; Classifier (UML); Psychology; Workflow; Coding (social sciences); Computer science; Social psychology; Artificial intelligence; Sociology; Linguistics; Social science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.004451828,0.0002025529,0.0004190883,0.0003584312,0.0002560201,0.00009340249,0.0002780054,0.0001177376,0.0003445964],"category_scores_gemma":[0.0005319046,0.0001510159,0.0001914105,0.0005193656,0.0007301879,0.0004119277,0.0002780824,0.0007226162,0.00002142609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006340352,"about_ca_system_score_gemma":0.00007163388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001576849,"about_ca_topic_score_gemma":0.00001914144,"domain_scores_codex":[0.9949049,0.002673082,0.0003435611,0.0007339969,0.00078196,0.0005624713],"domain_scores_gemma":[0.9978238,0.001515189,0.00005542292,0.0002219854,0.0001920501,0.0001915506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001637452,0.0004463544,0.0000667477,0.00008502849,0.0001420001,0.0003948887,0.01016297,0.000002184563,0.9206047,0.01180298,0.0001405832,0.05598784],"study_design_scores_gemma":[0.003015294,0.001874679,0.01165875,0.0004421599,0.001085052,0.0004387539,0.03555157,0.01255333,0.8849486,0.04679446,0.0006870832,0.0009503467],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9503972,0.003155812,0.0409451,0.001145433,0.0002900838,0.001071308,0.0001494032,0.00009953083,0.002746138],"genre_scores_gemma":[0.9831395,0.0001174506,0.01422033,0.0002040403,0.00004386464,0.0004231188,0.000007857147,0.00002832586,0.001815547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05503749,"threshold_uncertainty_score":0.6158249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7650757583834222,"score_gpt":0.5756139618117823,"score_spread":0.18946179657164,"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."}}