{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001805115,0.0001366371,0.000179894,0.00004110545,0.0001579996,0.0001380927,0.0003324439,0.00006354201,0.000001430622],"category_scores_gemma":[0.00007683725,0.0001300539,0.0001175421,0.0002328315,0.00002564121,0.0004916535,0.00006444344,0.00009399345,0.000001084708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001717911,"about_ca_system_score_gemma":0.00004839165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006914186,"about_ca_topic_score_gemma":0.000003362115,"domain_scores_codex":[0.9989389,0.00003713517,0.0002394886,0.0003852293,0.0001484367,0.0002507653],"domain_scores_gemma":[0.9991911,0.0002672384,0.00007263412,0.0002475728,0.0001175555,0.0001038826],"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":[0.00006990842,0.0001977543,0.001301208,0.0002222097,0.00005415046,0.00002219029,0.005685476,0.01064379,0.0005098095,0.02273963,0.03017729,0.9283766],"study_design_scores_gemma":[0.0003341573,0.0002931858,0.000007047338,0.00002929189,0.000008178854,0.000009978152,0.00001423356,0.9816617,0.0005568761,0.01662295,0.000293676,0.0001686952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002881715,0.00007764616,0.9391558,0.001076358,0.00007386635,0.0006532814,0.000001567186,0.05584811,0.0002316877],"genre_scores_gemma":[0.5110445,3.971691e-7,0.4880148,0.0008539909,0.00002475025,0.00004303488,0.000002771699,0.000009462401,0.000006262771],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.971018,"threshold_uncertainty_score":0.5303442,"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."}}