{"id":"W4417328030","doi":"10.1038/s44271-025-00359-7","title":"Event segmentation applications in large language model enabled automated recall assessments","year":2025,"lang":"en","type":"article","venue":"Communications Psychology","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital; Baycrest Hospital; University of Toronto","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Government of Canada","keywords":"Recall; Event (particle physics); Segmentation; Precision and recall; Comprehension; Leverage (statistics); Cognition","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002135403,0.001201069,0.0005130226,0.0009618257,0.0003106736,0.001636769,0.001248397,0.0007645958,0.004896785],"category_scores_gemma":[0.01400356,0.0003228847,0.0008401461,0.0004269445,0.0003686139,0.001688203,0.001354968,0.001084878,0.001654508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000755307,"about_ca_system_score_gemma":0.0008708976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004140479,"about_ca_topic_score_gemma":0.006998538,"domain_scores_codex":[0.9990583,0.0003524618,0.00008570714,0.0002575383,0.000200825,0.00004511111],"domain_scores_gemma":[0.9946921,0.003004427,0.0004939584,0.0008293449,0.0008205145,0.0001594815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001908009,0.000624489,0.01963997,0.001093253,0.0003517816,0.001069673,0.0041042,0.1699389,0.09283991,0.01492482,0.01166281,0.6818422],"study_design_scores_gemma":[0.00003984397,0.0002181907,0.003185591,0.00004965273,0.00003922437,0.0001562741,0.0003463831,0.9509802,0.0267714,0.01324482,0.004905844,0.00006257675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1204545,0.0002908853,0.8445909,0.0002078641,0.0001013365,0.0002964981,0.001774479,0.02961409,0.002669511],"genre_scores_gemma":[0.6099902,0.0001498215,0.3836602,0.0001224749,0.00003311446,0.0005743499,0.002369755,0.0007893155,0.002310707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004896785,"threshold_uncertainty_score":0.01638138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05842552647935178,"score_gpt":0.4710189457963528,"score_spread":0.412593419317001,"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."}}