{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2673898,0.001467976,0.001915464,0.004812097,0.01019175,0.007308784,0.006018946,0.004186808,0.002789762],"category_scores_gemma":[0.2146005,0.001622765,0.001768604,0.004777394,0.006458816,0.005689577,0.006369501,0.003213103,0.0005877544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01250151,"about_ca_system_score_gemma":0.02397518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008924136,"about_ca_topic_score_gemma":0.02800084,"domain_scores_codex":[0.7167116,0.2482957,0.007527935,0.008726214,0.01468391,0.004054577],"domain_scores_gemma":[0.6529102,0.2694492,0.01277532,0.02704312,0.03515228,0.002669919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00328351,0.02076297,0.03037122,0.00865541,0.001051586,0.001456797,0.6217349,0.002134677,0.0156772,0.02223568,0.003886463,0.2687496],"study_design_scores_gemma":[0.00864992,0.04755348,0.06582902,0.01080028,0.001825159,0.001183855,0.6657168,0.01112965,0.0425793,0.03169959,0.1122771,0.0007558915],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7253956,0.002517801,0.09320697,0.003043628,0.0005711085,0.1662154,0.0004071194,0.0002505289,0.008391839],"genre_scores_gemma":[0.5537109,0.0008746502,0.2674043,0.004028167,0.0002263471,0.1697758,0.0002253121,0.0001359866,0.003618492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2673898,"threshold_uncertainty_score":0.9034389,"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."}}