{"id":"W1587813117","doi":"10.18806/tesl.v21i1.275","title":"Locally Developed Oral Skills Evaluation in ESL/EFL Classrooms: A Checklist for Developing Meaningful Assessment Procedures","year":2003,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Checklist; Psychology; Identification (biology); Mathematics education; Authentic assessment; Test (biology); Pedagogy; Alternative assessment; Medical education; Curriculum","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1014634,0.001813403,0.001913345,0.009605623,0.003275138,0.003092915,0.005564727,0.00208101,0.001999556],"category_scores_gemma":[0.1738469,0.001096136,0.001788717,0.00279265,0.003991268,0.003912405,0.006376942,0.003192415,0.002297695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005484229,"about_ca_system_score_gemma":0.02727381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005085581,"about_ca_topic_score_gemma":0.01246976,"domain_scores_codex":[0.8552002,0.08147296,0.03557154,0.001905429,0.02392046,0.001929524],"domain_scores_gemma":[0.7765827,0.1011211,0.0160971,0.01332029,0.0888077,0.004071214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005208055,0.001417377,0.02322698,0.005030964,0.0001058901,0.0008686854,0.03039243,0.007001017,0.01982796,0.01105706,0.03954763,0.8610032],"study_design_scores_gemma":[0.0009963943,0.006729617,0.09880564,0.02244861,0.0004703472,0.005137474,0.0612005,0.03349518,0.08225571,0.03151162,0.6549697,0.00197926],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07898046,0.00265851,0.8220541,0.004976527,0.0008423852,0.05517241,0.001760086,0.005794594,0.02776095],"genre_scores_gemma":[0.05002214,0.0009882476,0.9151022,0.0003096391,0.00004918869,0.02899612,0.001061758,0.00036832,0.003102398],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1014634,"threshold_uncertainty_score":0.5365959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04566302773426684,"score_gpt":0.3105659843108914,"score_spread":0.2649029565766245,"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."}}