{"id":"W4410106284","doi":"10.3758/s13428-025-02690-7","title":"Assessing autobiographical memory consistency: Machine and human approaches","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Identity, Memory, and Therapy","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Autobiographical memory; Consistency (knowledge bases); Computer science; Human memory; Cognitive psychology; Psychology; Artificial intelligence; Natural language processing; Recall; Cognition; Neuroscience","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01038736,0.0002110646,0.0003957817,0.001121732,0.0008746781,0.0003730511,0.0004289919,0.000291348,0.0006869377],"category_scores_gemma":[0.0002267897,0.0001965992,0.0001537319,0.001048322,0.001169904,0.0001635678,0.0002421784,0.001143267,0.00001936369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005769233,"about_ca_system_score_gemma":0.000118389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001256355,"about_ca_topic_score_gemma":0.0001266537,"domain_scores_codex":[0.9924529,0.005338156,0.0003921156,0.0007009143,0.0004154042,0.0007005195],"domain_scores_gemma":[0.9979743,0.0008450566,0.00005839125,0.000776241,0.0001638664,0.0001821393],"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":[0.00008297215,0.001477421,0.154237,0.0001191031,0.0002151307,0.0002057593,0.001592156,9.947788e-8,0.02983584,0.1186633,0.001832975,0.6917383],"study_design_scores_gemma":[0.001642982,0.000208183,0.9678271,0.00006257048,0.000126696,0.00005130157,0.004802368,0.0000235085,0.003182438,0.01454605,0.007179894,0.0003468692],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8859891,0.005098364,0.00447985,0.0008329769,0.0009201175,0.000974518,0.000009266627,0.0001705775,0.1015252],"genre_scores_gemma":[0.953118,0.00005082959,0.03236386,0.0001070722,0.0001367818,0.0005020331,0.0000182209,0.00004689335,0.01365637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8135902,"threshold_uncertainty_score":0.8017081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4853908485801297,"score_gpt":0.629412572268767,"score_spread":0.1440217236886374,"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."}}