{"id":"W2092865291","doi":"10.7202/1008341ar","title":"Reliability and Validity of a Scale-based Assessment for Translation Tests","year":2012,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Translation Studies and Practices","field":"Arts and Humanities","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Reliability (semiconductor); Test (biology); Computer science; Quality (philosophy); Christian ministry; Artificial intelligence; Translation (biology); Natural language processing; Mathematics education; Machine learning; Psychology","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":[],"category_scores_codex":[0.07508687,0.0007450766,0.001296623,0.005689291,0.001015699,0.002529094,0.001486072,0.001099617,0.001425305],"category_scores_gemma":[0.2379142,0.0006002946,0.00263796,0.004599425,0.002106061,0.002766926,0.002125284,0.001383314,0.0006652358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001158166,"about_ca_system_score_gemma":0.001689711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001229784,"about_ca_topic_score_gemma":0.001722756,"domain_scores_codex":[0.8891096,0.05693819,0.01099986,0.005652249,0.03648263,0.0008174477],"domain_scores_gemma":[0.7379909,0.1640551,0.02013601,0.01523038,0.06040185,0.002185694],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001633313,0.001162713,0.6883507,0.002121975,0.002725395,0.000242096,0.0177832,0.002739851,0.006806968,0.006647633,0.004299277,0.2654869],"study_design_scores_gemma":[0.0005740558,0.004925698,0.92061,0.001818826,0.00108746,0.000732163,0.009132936,0.0313504,0.006286395,0.008814983,0.01430599,0.0003612427],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8828825,0.002476751,0.08469748,0.0007663212,0.001018736,0.002283758,0.000778696,0.0004451621,0.02465062],"genre_scores_gemma":[0.9657952,0.0004043481,0.03067503,0.0001324429,0.000103177,0.001642798,0.0004997205,0.00009631734,0.0006509626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9249131,"threshold_uncertainty_score":0.3971021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.165354839471253,"score_gpt":0.3437038458073066,"score_spread":0.1783490063360536,"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."}}