{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01587635,0.0004386678,0.0005869489,0.001847545,0.00219104,0.003888851,0.0005267996,0.001078144,0.001726189],"category_scores_gemma":[0.07604349,0.0004577495,0.0003489958,0.0009276133,0.00224177,0.00130044,0.0023308,0.001316128,0.0007295733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008925245,"about_ca_system_score_gemma":0.0007346775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001829973,"about_ca_topic_score_gemma":0.002669276,"domain_scores_codex":[0.9850701,0.01058096,0.0007378332,0.0009768803,0.001962887,0.0006714065],"domain_scores_gemma":[0.9441412,0.03115505,0.01027184,0.00338597,0.006073637,0.004972229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.002594211,0.0004381922,0.5600624,0.0002724695,0.000194969,0.001425673,0.3251834,0.0004322688,0.01164761,0.001467583,0.00191846,0.09436274],"study_design_scores_gemma":[0.0001413158,0.002445823,0.6167928,0.0003651685,0.0001631095,0.002729257,0.3436617,0.006018865,0.005094704,0.003697276,0.01851415,0.0003757999],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965358,0.0001686822,0.0009279533,0.0001730518,0.00001405863,0.00004323272,0.00001009258,0.00002271674,0.002104497],"genre_scores_gemma":[0.9963591,0.000122021,0.001124681,0.0001939347,0.00001448366,0.00004509903,0.00003488701,0.00002602565,0.002079724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01587635,"threshold_uncertainty_score":0.08396316,"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."}}