{"id":"W2139763558","doi":"10.1007/0-306-47642-8_24","title":"Effects of Adaptations on Comparability of Test Items and Test Scores","year":2005,"lang":"en","type":"book-chapter","venue":"Kluwer Academic Publishers eBooks","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Comparability; Test (biology); Statistics; Psychology; Econometrics; Computer science; Mathematics; Biology; Ecology","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005626114,0.0005007195,0.001404916,0.001554903,0.0001209714,0.0001974552,0.001618394,0.0009293908,0.0001501468],"category_scores_gemma":[0.1748355,0.0003876939,0.0002905854,0.0003268041,0.00105732,0.0004215949,0.0003776701,0.001623666,0.00001713321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007654722,"about_ca_system_score_gemma":0.0002065282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004459978,"about_ca_topic_score_gemma":0.000008376515,"domain_scores_codex":[0.9942799,0.0002114546,0.002069627,0.001075451,0.001947407,0.0004162286],"domain_scores_gemma":[0.8464647,0.1499041,0.001888851,0.0008842646,0.0006142434,0.0002438834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001575826,0.0002297543,0.08177638,0.0004941011,0.0002399666,0.00001432419,0.001452134,0.00006083725,0.002855425,0.05028442,0.1397145,0.7227206],"study_design_scores_gemma":[0.002874311,0.001591647,0.1998547,0.002237147,0.0003788424,0.00004412421,0.0003867527,0.0006413119,0.002484426,0.4048344,0.3829315,0.001740801],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02534537,0.002771766,0.0003316402,0.0003438874,0.00090236,0.001072224,0.0001696141,0.000106595,0.9689565],"genre_scores_gemma":[0.6750048,0.0001304802,0.005665364,0.0004556598,0.0005596187,0.00004469782,0.00001480876,0.00009958835,0.3180249],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7209798,"threshold_uncertainty_score":0.9998575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2599093244075452,"score_gpt":0.3990953364307693,"score_spread":0.1391860120232241,"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."}}