{"id":"W4406530729","doi":"10.1075/ml.24023.lan","title":"A psycholinguistic analysis of clinical list-learning tests","year":2024,"lang":"en","type":"article","venue":"The Mental Lexicon","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; Brock University","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Psychology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01569307,0.0001037487,0.0004710947,0.000618878,0.0001207121,0.0001885334,0.0007102098,0.0000584694,0.0008685812],"category_scores_gemma":[0.07780542,0.0000550004,0.0004446295,0.005647229,0.0001832501,0.00005556298,0.0001578447,0.000331436,0.0001100424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001630418,"about_ca_system_score_gemma":0.00003510985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006938615,"about_ca_topic_score_gemma":0.00001189996,"domain_scores_codex":[0.9965618,0.0009078322,0.001061616,0.0004373954,0.0008417887,0.0001895328],"domain_scores_gemma":[0.9584824,0.0405534,0.0002908679,0.0005141069,0.00009024885,0.00006893599],"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":[0.00007845344,0.000108175,0.3499678,0.00001243954,0.000853374,0.00002077745,0.001314087,0.0005345921,0.0007129977,0.005754078,0.005631529,0.6350117],"study_design_scores_gemma":[0.0004093923,0.0004388042,0.648804,0.0001088217,0.0009287308,0.0000180709,0.001998833,0.1823254,0.000175066,0.04564665,0.1188555,0.000290737],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9517572,0.001469292,0.003042761,0.0006623594,0.002762023,0.0001514518,0.00001594903,0.00009730426,0.04004167],"genre_scores_gemma":[0.9950932,0.00004427333,0.002282372,0.0001247821,0.0002068186,0.000005361227,0.000003578397,0.000007489175,0.002232125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6347209,"threshold_uncertainty_score":0.9510354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.634623376166255,"score_gpt":0.6216009030149111,"score_spread":0.01302247315134386,"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."}}