{"id":"W4313302961","doi":"10.3138/cmlr-2021-0060","title":"Evaluating the Explanation Inference of a High-Stakes French Listening Test: An Argument-Based Perspective","year":2022,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Carleton University","funders":"","keywords":"Construct (python library); Argument (complex analysis); Operationalization; Inference; Argumentation theory; Test (biology); Perspective (graphical); Psychology; Active listening; Computer science; Epistemology; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3446029,0.001329045,0.002219872,0.01515352,0.005211367,0.009887854,0.0048939,0.003616577,0.002632353],"category_scores_gemma":[0.5951672,0.0005912159,0.002174332,0.00612382,0.01514384,0.008540073,0.007543652,0.004285159,0.0004305273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01642762,"about_ca_system_score_gemma":0.01956591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02954392,"about_ca_topic_score_gemma":0.04671257,"domain_scores_codex":[0.7271537,0.2073431,0.01378156,0.006095119,0.04194747,0.00367916],"domain_scores_gemma":[0.1871229,0.7258903,0.01897386,0.01453837,0.0520955,0.001378978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0008166219,0.0008772064,0.1321328,0.006347694,0.001004732,0.00194384,0.2404791,0.004400019,0.004216839,0.1675229,0.006258553,0.4339997],"study_design_scores_gemma":[0.0005183543,0.003868682,0.2711813,0.02274617,0.001885763,0.002226943,0.2500748,0.02651053,0.02821059,0.2547433,0.1369905,0.001043036],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6836029,0.01218939,0.1858515,0.03059699,0.0007557021,0.003681106,0.0006040696,0.0003300785,0.08238821],"genre_scores_gemma":[0.9236073,0.001686661,0.06898511,0.002267413,0.0001200782,0.001359392,0.0004578765,0.0000581435,0.001457964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3446029,"threshold_uncertainty_score":0.8082213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07957348259436121,"score_gpt":0.4150387317426647,"score_spread":0.3354652491483035,"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."}}