{"id":"W2180011677","doi":"10.1093/deafed/env049","title":"Comprehension of Written Grammar Test: Reliability and Known-Groups Validity Study With Hearing and Deaf and Hard-of-Hearing Students","year":2015,"lang":"en","type":"article","venue":"The Journal of Deaf Studies and Deaf Education","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Test (biology); Grammar; Comprehension; Audiology; Reliability (semiconductor); Sentence; Test validity; Vocabulary; Developmental psychology; Psychometrics; Linguistics; Natural language processing; Computer science; Medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007251097,0.0005349714,0.0006901963,0.001581536,0.0007203223,0.000861962,0.0007216539,0.0006648403,0.001450239],"category_scores_gemma":[0.01764368,0.0004695663,0.0006217957,0.0005383798,0.001093159,0.001199744,0.001812354,0.0009970051,0.0005305368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004575012,"about_ca_system_score_gemma":0.0005876895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001943606,"about_ca_topic_score_gemma":0.003500164,"domain_scores_codex":[0.9966273,0.0007949309,0.0004485295,0.0005703761,0.001272584,0.0002863002],"domain_scores_gemma":[0.9869351,0.005138101,0.002579568,0.00117432,0.003123431,0.00104954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000265896,0.00097186,0.9797427,0.00003728694,0.00007267087,0.0001490101,0.007964376,0.00007234634,0.002031234,0.00005240004,0.0001027806,0.008537511],"study_design_scores_gemma":[0.00005321141,0.001517828,0.9922534,0.00001102023,0.00003075969,0.0003650276,0.003778522,0.0002993883,0.001280631,0.00006569579,0.0003306643,0.00001404575],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9996551,0.00001762056,0.00008282769,0.000006631743,0.000003449235,0.00002921183,0.00002593544,0.000002029456,0.0001770469],"genre_scores_gemma":[0.999221,0.00002078883,0.0002978358,0.00002065581,0.000004797957,0.0000627241,0.0001042662,0.000003454043,0.0002644614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007251097,"threshold_uncertainty_score":0.03834796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1353991389432234,"score_gpt":0.3983073291637506,"score_spread":0.2629081902205272,"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."}}