{"id":"W2149277326","doi":"10.7202/1017090ar","title":"The Good Guys and the Bad Guys: The Behavior of Lenient and Demanding Translation Evaluators","year":2013,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Translation Studies and Practices","field":"Arts and Humanities","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Certainty; Quality (philosophy); Product (mathematics); Computer science; Process (computing); Psychology; Carry (investment); Mathematics; Epistemology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001599607,0.0001285229,0.0002139919,0.00003431511,0.002028155,0.0006363089,0.0001434924,0.0000188609,0.0002336393],"category_scores_gemma":[0.00003143172,0.0000482165,0.0001390169,0.00004092035,0.001035933,0.0005055311,0.00001273691,0.000225656,0.000002588913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005314202,"about_ca_system_score_gemma":0.00001112563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001459601,"about_ca_topic_score_gemma":0.0004362556,"domain_scores_codex":[0.9986852,0.0004144699,0.0003599125,0.00009897711,0.0002801206,0.0001613487],"domain_scores_gemma":[0.9984957,0.0009861032,0.0002413822,0.0001170119,0.0001175679,0.000042208],"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":[0.0001137294,0.00004539083,0.001887139,0.00002438163,0.001236865,9.360686e-7,0.03555958,0.00001382437,0.0001372928,0.09287827,0.0004542721,0.8676483],"study_design_scores_gemma":[0.001827025,0.0001721586,0.0229989,0.00003225832,0.004556894,0.0001311498,0.01182002,0.0002337237,0.0000969999,0.0292484,0.9286785,0.000204017],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6460307,0.3359447,0.0002710084,0.01312773,0.0006523863,0.0008235898,0.00001037065,0.0000142181,0.003125311],"genre_scores_gemma":[0.9521819,0.04709737,0.00009959727,0.00008586354,0.0002081795,0.00006413919,4.726288e-7,0.00001144084,0.0002510775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9282242,"threshold_uncertainty_score":0.9992711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08563314953086039,"score_gpt":0.2871850868551861,"score_spread":0.2015519373243257,"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."}}