{"id":"W2741328617","doi":"10.1145/3106237.3106274","title":"Better test cases for better automated program repair","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Metric (unit); Artificial intelligence; Benchmark (surveying); Test (biology); Machine learning; Software bug; Pattern recognition (psychology); Data mining; Software; Programming language; Engineering","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":[0.000250762,0.0001362871,0.0001378065,0.00005396146,0.0004880643,0.0005911202,0.001016095,0.0000678399,0.000005371109],"category_scores_gemma":[0.001568299,0.0001083177,0.0001021147,0.00005320075,0.00007351606,0.0003918796,0.0003047973,0.00006688286,0.0000263465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001674226,"about_ca_system_score_gemma":0.0000289107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001565495,"about_ca_topic_score_gemma":0.00001037937,"domain_scores_codex":[0.9990013,0.00001268941,0.0001675401,0.0003815381,0.000132806,0.0003041333],"domain_scores_gemma":[0.997699,0.0005960267,0.0001126811,0.001408649,0.0001162633,0.00006740628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001280816,0.00009917173,0.05822735,0.00001840596,0.000008991991,0.0000449235,0.00002861679,1.675205e-7,0.00001453746,0.0002222653,0.8445455,0.09678876],"study_design_scores_gemma":[0.0003348007,0.0006621883,0.05058042,0.00007898876,0.00001325127,0.0001397533,6.732137e-7,0.9022577,0.001256721,0.0161507,0.02810263,0.0004221803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.0201278,0.00002473986,0.11176,0.009821402,0.0004534515,0.001149699,0.00000896188,0.8526846,0.003969321],"genre_scores_gemma":[0.1464303,3.479909e-7,0.8512427,0.001576481,0.00009914507,0.0002193799,0.000002456325,0.00001293409,0.0004161889],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9022576,"threshold_uncertainty_score":0.5700185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04420587928543526,"score_gpt":0.3430140819929544,"score_spread":0.2988082027075191,"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."}}