{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00207466,0.0001238066,0.0003312535,0.00007205368,0.0004798185,0.0000947914,0.0001696974,0.00001850107,0.001909715],"category_scores_gemma":[0.00007351733,0.00006712069,0.0002993913,0.00005898065,0.0002884369,0.0003116446,0.000007856243,0.0002113345,0.000001982209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001015919,"about_ca_system_score_gemma":0.00000620285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003487656,"about_ca_topic_score_gemma":0.0001200984,"domain_scores_codex":[0.9975421,0.001269706,0.0005778194,0.00009421576,0.0003924698,0.0001237285],"domain_scores_gemma":[0.9983211,0.0008337137,0.000446118,0.0001318572,0.0002329182,0.00003435463],"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":[0.0000367241,0.0002802281,0.0009859577,0.00007906488,0.001804909,7.600157e-7,0.04186265,0.0003198106,0.001839002,0.03596879,0.0001556665,0.9166664],"study_design_scores_gemma":[0.002273678,0.001867775,0.03498286,0.0002354928,0.01490198,0.00009370333,0.01064157,0.002327444,0.007854688,0.08024243,0.8439173,0.0006610709],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6719368,0.2766388,0.03543106,0.004669597,0.00181111,0.0005135366,0.00004685643,0.00003850906,0.008913759],"genre_scores_gemma":[0.97211,0.02168978,0.005455116,0.00002795897,0.0003637843,0.00001049933,0.000001058997,0.0000134908,0.0003283401],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9160054,"threshold_uncertainty_score":0.9990027,"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."}}