{"id":"W1996435010","doi":"10.1080/09695940701272773","title":"Did we take the same test? Differing accounts of the Ontario Secondary School Literacy Test by first and second language test‐takers","year":2007,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Carleton University","funders":"","keywords":"Test (biology); Graduation (instrument); Psychology; Context (archaeology); Construct (python library); Literacy; Construct validity; Mathematics education; Fidelity; Test score; Standardized test; Pedagogy; Developmental psychology; Computer science; Psychometrics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002388958,0.0001786905,0.0001731892,0.0001097142,0.0006577378,0.0003841227,0.0003783061,0.00009920697,0.0003271223],"category_scores_gemma":[0.004567929,0.0001313146,0.00003937975,0.0004546433,0.0002520351,0.001184283,0.000179183,0.0005769877,0.000004157873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005247691,"about_ca_system_score_gemma":0.0020187,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04493859,"about_ca_topic_score_gemma":0.1139421,"domain_scores_codex":[0.9983174,0.0002050183,0.0004182057,0.0002808006,0.0004265653,0.0003519708],"domain_scores_gemma":[0.9892814,0.009708045,0.0004543165,0.0003119002,0.0001122827,0.0001321193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001662022,0.0006631211,0.8745536,0.00004868594,0.00002720056,9.822992e-7,0.1114054,5.882509e-7,0.0006239841,0.003228653,0.001569173,0.007861994],"study_design_scores_gemma":[0.0002352006,0.00003407097,0.6397342,0.00005857932,0.00002670472,0.000005609869,0.04729789,0.000003764079,0.00004907619,0.0002276095,0.3122129,0.0001143526],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8785336,0.000717962,0.000005737945,0.03486021,0.0003170077,0.0005951427,0.00003316722,0.0000180155,0.08491918],"genre_scores_gemma":[0.9832307,0.0009199142,0.000621495,0.002271085,0.0003312866,0.00004199333,0.00001052814,0.00001383392,0.01255913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3106437,"threshold_uncertainty_score":0.9614213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02100229501179931,"score_gpt":0.3845813286896781,"score_spread":0.3635790336778789,"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."}}