{"id":"W2159609851","doi":"10.1191/0265532204lt288oa","title":"ESL/EFL instructors’ classroom assessment practices: purposes, methods, and procedures","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":184,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Psychology; English as a foreign language; Mathematics education; Tertiary level; Pedagogy; Second language; Language assessment; Linguistics","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":[0.001259492,0.0001602916,0.0001926141,0.00007346245,0.0006034473,0.0003334264,0.0002522462,0.00009594835,0.00007815419],"category_scores_gemma":[0.004276884,0.000147588,0.00003457235,0.0003582949,0.0001592115,0.0004974992,0.000119671,0.000250586,0.000009544773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001551925,"about_ca_system_score_gemma":0.0004715754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005643806,"about_ca_topic_score_gemma":0.002757241,"domain_scores_codex":[0.9983709,0.0002323285,0.000230163,0.0003362223,0.0004226617,0.0004077303],"domain_scores_gemma":[0.9984898,0.0007326702,0.0003897482,0.0001591591,0.00008756423,0.0001410448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001790745,0.0003189038,0.571827,0.0002207024,0.0001452855,0.0001653321,0.1659635,0.00002255949,0.03583076,0.04561178,0.0003762064,0.1795001],"study_design_scores_gemma":[0.004627989,0.0005317705,0.5233849,0.0008702152,0.0004278018,0.00009897222,0.417603,0.0002602982,0.002466767,0.02205466,0.025515,0.002158609],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8899671,0.001086575,0.0009146828,0.001141978,0.0003414859,0.0005238556,0.000003373891,0.0003853021,0.1056356],"genre_scores_gemma":[0.6683367,0.00004521573,0.3304719,0.0002061011,0.0004152005,0.00002397043,0.000004750965,0.00001726388,0.0004788553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3295572,"threshold_uncertainty_score":0.8531784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06401151606627827,"score_gpt":0.4566933338742858,"score_spread":0.3926818178080075,"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."}}