{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01524126,0.0004802489,0.0004578446,0.003077692,0.006924826,0.006276983,0.002250515,0.001682204,0.001397538],"category_scores_gemma":[0.06272691,0.0004507829,0.0006178707,0.002554065,0.01692384,0.003919709,0.004454658,0.002445285,0.0002928285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03391194,"about_ca_system_score_gemma":0.01786655,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.7256564,"about_ca_topic_score_gemma":0.7678544,"domain_scores_codex":[0.9688408,0.01145943,0.001428998,0.00179725,0.0143978,0.00207573],"domain_scores_gemma":[0.9702678,0.0119373,0.005158749,0.002780956,0.007800633,0.002054555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00008083533,0.00004395532,0.09512686,0.0001115506,0.00003332541,0.0006355554,0.8630092,0.0001099924,0.001013146,0.0153206,0.002556098,0.02195892],"study_design_scores_gemma":[0.000029515,0.0001821476,0.3444324,0.0006555044,0.00007416746,0.001019792,0.5689775,0.001114598,0.001566736,0.009352142,0.07239216,0.0002033274],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9258767,0.00203418,0.004057247,0.01825272,0.0001374917,0.0001566751,0.0003545991,0.00005569515,0.04907459],"genre_scores_gemma":[0.9910364,0.0006404976,0.001204713,0.001426436,0.00003541164,0.00005878621,0.0001457196,0.00005185678,0.005400038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7256564,"threshold_uncertainty_score":0.5519184,"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."}}