{"id":"W4408458755","doi":"10.1080/23279095.2025.2479850","title":"Incorrect encoding responses improve the classification accuracy of the Word Choice Test","year":2025,"lang":"en","type":"article","venue":"Applied Neuropsychology Adult","topic":"Traumatic Brain Injury Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Word (group theory); Encoding (memory); Computer science; Natural language processing; Test (biology); Artificial intelligence; Multiple choice; Arithmetic; Statistics; Linguistics; Mathematics; Significant difference","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":[0.0005418744,0.0001612651,0.0002500242,0.0001471318,0.0002153759,0.00001678085,0.0006229181,0.0001399042,0.00004905276],"category_scores_gemma":[0.008348339,0.00009314729,0.00009103896,0.0009284657,0.0006392271,0.00003228282,0.000151014,0.0008153084,0.0000545042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003852977,"about_ca_system_score_gemma":0.0001645593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001818668,"about_ca_topic_score_gemma":0.00001256262,"domain_scores_codex":[0.9982942,0.0002748036,0.000448788,0.0004146082,0.0002723256,0.0002952321],"domain_scores_gemma":[0.991204,0.007013414,0.0002193549,0.001331809,0.0001840558,0.0000474294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001284777,0.0003656168,0.03820902,0.0001077146,0.00007625103,0.000004424304,0.0004518353,8.244417e-7,0.8488923,0.01333146,0.01140242,0.08587339],"study_design_scores_gemma":[0.001455149,0.000135349,0.9673039,0.00007891565,0.00007002267,0.00003287945,0.0003077121,0.00009019682,0.02511977,0.001016427,0.004307948,0.00008169097],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9021658,0.00002345334,0.0001382354,0.04393647,0.0006332193,0.001376872,0.00001094728,0.00007387644,0.05164111],"genre_scores_gemma":[0.9893411,0.00003198204,0.0001282941,0.007837895,0.00009759413,0.0002143641,0.000002969701,0.00002187231,0.002323934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9290949,"threshold_uncertainty_score":0.9994345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05326295539929731,"score_gpt":0.3735516792154511,"score_spread":0.3202887238161538,"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."}}