{"id":"W6996631828","doi":"","title":"In the service of the stakeholder: a critical, mixed-method program of research in high-stakes language assessment","year":2011,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Certification; Stakeholder; Language assessment; Language proficiency; Perception; Task (project management); Service (business); Field (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01123245,0.0004050455,0.0007204476,0.0005587314,0.0009149007,0.0001242897,0.002538634,0.0006503655,0.0002855803],"category_scores_gemma":[0.001267992,0.0002964956,0.0002428166,0.003324741,0.0003876606,0.0005607139,0.0002217896,0.002371189,0.00001750906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004385501,"about_ca_system_score_gemma":0.0003613162,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03347684,"about_ca_topic_score_gemma":0.1272018,"domain_scores_codex":[0.9889798,0.005417051,0.001063557,0.0007197907,0.002861061,0.0009588076],"domain_scores_gemma":[0.9952474,0.002356965,0.0004844247,0.0009137887,0.0008768537,0.0001205716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002459149,0.003743207,0.004246652,0.001530909,0.0001505302,0.00007819207,0.008506314,0.000004610602,0.00755663,0.9135002,0.00003339251,0.06040339],"study_design_scores_gemma":[0.003127921,0.0008293704,0.2695106,0.003869516,0.0003899962,0.000004533245,0.565253,0.00001737702,0.02015358,0.1082882,0.02688019,0.001675777],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.859044,0.0001822016,5.340868e-8,0.0003068948,0.0008537797,0.00204438,0.000225893,0.00004070364,0.1373021],"genre_scores_gemma":[0.9952357,0.0001546003,0.001917007,0.0001191178,0.00006071515,0.0005270411,0.00008236634,0.00006385796,0.001839556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8052121,"threshold_uncertainty_score":0.9999487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.10398658210227,"score_gpt":0.4408162889804222,"score_spread":0.3368297068781522,"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."}}