{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003039447,0.0001275335,0.0001699623,0.0003046061,0.000232832,0.00002028318,0.001092124,0.0001301898,0.00003516278],"category_scores_gemma":[0.0001285914,0.000126733,0.00004730532,0.0006820092,0.0001502678,0.00009236731,0.0002969268,0.0003167415,0.00005190464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005878483,"about_ca_system_score_gemma":0.00006415086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000151701,"about_ca_topic_score_gemma":0.0001221251,"domain_scores_codex":[0.9983948,0.000499666,0.000378434,0.0003947766,0.00006574127,0.0002665234],"domain_scores_gemma":[0.9978005,0.0003299873,0.0001131107,0.001689238,0.00003373244,0.00003339162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004013091,0.002021899,0.003231349,0.00002454524,0.00001866408,0.00002431226,0.002033167,0.0002596393,0.9621677,0.0188655,0.002987856,0.008325268],"study_design_scores_gemma":[0.01782125,0.0004850686,0.03503823,0.0003253954,0.0002578768,0.0002921296,0.006483137,0.6131151,0.1858642,0.04792665,0.08999877,0.002392131],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8921749,0.0008741495,0.03769989,0.007442117,0.0003065437,0.001898454,0.000115577,0.001032459,0.05845589],"genre_scores_gemma":[0.9872096,0.0002850946,0.004661915,0.006021521,0.000007740705,0.0004460223,0.000148155,0.00001186222,0.001208086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7763035,"threshold_uncertainty_score":0.5168023,"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."}}