{"id":"W4410794671","doi":"10.56078/atradire.513","title":"Reasoned Translation: Putting Neural Machine Translation and Generative Artificial Intelligence Systems to the “Delisle Test”","year":2025,"lang":"en","type":"article","venue":"À tradire.","topic":"linguistics and terminology studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine translation; Artificial intelligence; Generative grammar; Translation (biology); Test (biology); Computer science; Machine translation system; Engineering; Chemistry; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001610409,0.0001143754,0.0001456286,0.00005595604,0.0006304873,0.0001838855,0.00008422429,0.00003724475,0.0000201834],"category_scores_gemma":[0.00006768489,0.00007897079,0.00003241313,0.00005233281,0.0001381303,0.00003791883,0.00001083528,0.0001282853,0.00000520503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000901948,"about_ca_system_score_gemma":0.00001215124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002238415,"about_ca_topic_score_gemma":0.001390044,"domain_scores_codex":[0.9993336,0.00004513715,0.0002174021,0.0001847159,0.00007813501,0.0001410282],"domain_scores_gemma":[0.9994838,0.0002839752,0.00003717183,0.0001032876,0.00006725058,0.00002446943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002776132,0.00004585136,0.0002954975,0.00005424397,0.00009693277,0.000007425087,0.05939537,0.0003702297,0.00007669217,0.4694078,0.001812461,0.4684098],"study_design_scores_gemma":[0.0002573386,0.0002358361,0.0007558889,0.000125222,0.0002319326,0.000008890786,0.005714914,0.5346802,0.0003697427,0.0127507,0.4444644,0.0004049797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1225346,0.1133915,0.05375372,0.4857841,0.01678991,0.005553592,0.001040202,0.000959804,0.2001925],"genre_scores_gemma":[0.9976407,0.00003838587,0.0002855299,0.000641148,0.0006563082,0.00003517464,0.00001021549,0.00000706934,0.0006854348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8751061,"threshold_uncertainty_score":0.4849262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1162715920501623,"score_gpt":0.2834782658428905,"score_spread":0.1672066737927282,"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."}}