{"id":"W4407928271","doi":"10.1177/00131644251319047","title":"Shortening Psychological Scales: Semantic Similarity Matters","year":2025,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Similarity (geometry); Sentence; Semantic similarity; Scale (ratio); Computer science; Natural language processing; Sample (material); Artificial intelligence; Embedding; Correlation; Information retrieval; Mathematics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00783861,0.0002330927,0.0003964857,0.0004035595,0.0003736856,0.0002564842,0.0007312972,0.0001676201,0.001099224],"category_scores_gemma":[0.02103406,0.0001482563,0.0001416046,0.001564084,0.0002792564,0.0001034303,0.0001345064,0.0003548312,0.00009916684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006525017,"about_ca_system_score_gemma":0.00003009304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008676394,"about_ca_topic_score_gemma":0.000003381889,"domain_scores_codex":[0.9956552,0.0006578178,0.0008245712,0.001065936,0.001393154,0.0004032616],"domain_scores_gemma":[0.9921536,0.006434592,0.0001875661,0.0005617664,0.0004642158,0.0001983021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001583455,0.001835996,0.4270843,0.00002707272,0.00007493682,0.000006545572,0.0001234216,0.00002549091,0.001289816,0.02128134,0.2401358,0.3079569],"study_design_scores_gemma":[0.000306491,0.000124627,0.787795,0.00004535712,0.00001211147,0.00002147974,0.0002035467,0.00006445942,0.00001244205,0.2021216,0.009130483,0.0001624091],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.759869,0.002567384,0.06129149,0.1144603,0.005202896,0.0005977091,0.00001088577,0.0001384848,0.05586191],"genre_scores_gemma":[0.9760008,0.00005108996,0.01521839,0.007644137,0.0001779479,0.00005659786,0.000002686808,0.000005075284,0.0008432298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3607107,"threshold_uncertainty_score":0.9998139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6635170864862416,"score_gpt":0.5275220275597801,"score_spread":0.1359950589264616,"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."}}