{"id":"W3043761819","doi":"10.1145/3395363.3397369","title":"CoCoNuT: combining context-aware neural translation models using ensemble for program repair","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":329,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Facebook","keywords":"Computer science; Context (archaeology); Machine translation; Artificial intelligence; Programming language; Machine learning; Software engineering; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001403226,0.002429406,0.001866596,0.002025556,0.001050213,0.001718728,0.002550834,0.002208497,0.006176425],"category_scores_gemma":[0.004590666,0.0005311625,0.001279082,0.00216328,0.000472692,0.002730581,0.001985937,0.002282435,0.003824456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009610077,"about_ca_system_score_gemma":0.00177298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01933593,"about_ca_topic_score_gemma":0.03235472,"domain_scores_codex":[0.9989523,0.0002410393,0.00005854419,0.0004403686,0.0001976157,0.0001101105],"domain_scores_gemma":[0.9983,0.0007421717,0.00007720917,0.0002646797,0.0005346805,0.00008126622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007443565,0.0004676324,0.00255327,0.0004507138,0.000490029,0.0004950628,0.0001898541,0.1218722,0.0116761,0.002406065,0.03531808,0.8233366],"study_design_scores_gemma":[0.00003614831,0.0001032712,0.0003649644,0.00003358239,0.00010205,0.00009370947,0.0000538503,0.986635,0.003885145,0.004136001,0.004525202,0.00003099974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07254525,0.007894713,0.8362793,0.001140376,0.001632969,0.0003880895,0.003520635,0.06595095,0.01064771],"genre_scores_gemma":[0.529006,0.002456016,0.4258242,0.001603377,0.0006690269,0.0006070838,0.01775899,0.0042372,0.01783811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01933593,"threshold_uncertainty_score":0.03844678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1833401154001179,"score_gpt":0.3325084569739183,"score_spread":0.1491683415738004,"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."}}