{"id":"W2170351971","doi":"10.7202/004583ar","title":"Different Methods of Evaluating Student Translations: The Question of Validity","year":2002,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Translation Studies and Practices","field":"Arts and Humanities","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Variety (cybernetics); External validity; Psychology; Mathematics education; Factor (programming language); Foreign language; Null (SQL); Test validity; Natural language processing; Computer science; Statistics; Mathematics; Artificial intelligence; Social psychology; Psychometrics; Data mining; Programming language","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2734099,0.001444644,0.002659845,0.008371273,0.002335667,0.004667351,0.002856961,0.002200713,0.001050392],"category_scores_gemma":[0.5771812,0.0009360879,0.002416369,0.005304531,0.009949829,0.006771595,0.006092836,0.002158767,0.0009283092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002684014,"about_ca_system_score_gemma":0.00423796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002710157,"about_ca_topic_score_gemma":0.003138411,"domain_scores_codex":[0.5781722,0.2693903,0.03623433,0.01583403,0.09740866,0.002960461],"domain_scores_gemma":[0.2868587,0.543566,0.03671463,0.05207812,0.07849627,0.002286248],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00231421,0.0008529362,0.402754,0.00402108,0.004248237,0.0001629205,0.04395538,0.00269577,0.005151404,0.01780903,0.002781567,0.5132535],"study_design_scores_gemma":[0.001476648,0.007669645,0.7296639,0.01071959,0.00223605,0.00150787,0.04958214,0.03640265,0.0270756,0.09674335,0.03562615,0.001296453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6693493,0.00987759,0.2698033,0.006288151,0.001617442,0.003934398,0.0007744958,0.0005774755,0.03777792],"genre_scores_gemma":[0.9014913,0.00149845,0.09097691,0.0007511327,0.0003570883,0.002977449,0.0004791853,0.0002193917,0.001249101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7265902,"threshold_uncertainty_score":0.896015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.373472000166517,"score_gpt":0.4392137023053821,"score_spread":0.0657417021388651,"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."}}