{"id":"W1626448709","doi":"10.18806/tesl.v26i1.129","title":"Teachers' Assessment of ESL Students in Mainstream Classes: Challenges, Strategies, and Decision-Making","year":2008,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mainstream; Psychology; Mathematics education; Work (physics); Pedagogy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001113015,0.0001386127,0.000275312,0.0001435991,0.0004613131,0.0001408961,0.0004524671,0.000077789,0.00110461],"category_scores_gemma":[0.00009815294,0.0001303614,0.00004031142,0.0002251154,0.0001530572,0.000418025,0.00008038381,0.0003897843,3.426172e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007707343,"about_ca_system_score_gemma":0.004654033,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.09261115,"about_ca_topic_score_gemma":0.6643223,"domain_scores_codex":[0.9973118,0.0001584047,0.0004133311,0.0001837308,0.001538737,0.0003939986],"domain_scores_gemma":[0.9990264,0.0003404115,0.0002295149,0.0001148502,0.0001067747,0.0001820712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004397929,0.0004930128,0.893168,0.00002402401,0.0001856965,0.001020492,0.0296192,0.0001113704,0.00003177109,0.01108267,0.009749678,0.05447004],"study_design_scores_gemma":[0.0008782797,0.00007438502,0.906865,0.0001638711,0.00001540275,0.00003934807,0.08102455,0.00002832978,5.078396e-7,0.001508438,0.009221215,0.0001806683],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9738197,0.01035966,0.00007543518,0.0004214126,0.0003615575,0.0001624115,0.000002706918,0.000009928499,0.01478719],"genre_scores_gemma":[0.9935862,0.003975245,0.00174145,0.000468066,0.0001640574,0.000003261678,5.672325e-7,0.00001005176,0.00005107547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5717111,"threshold_uncertainty_score":0.9998085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03541355152976906,"score_gpt":0.3662058004315097,"score_spread":0.3307922489017406,"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."}}