{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008221186,0.002627213,0.001238332,0.0061995,0.0004258998,0.002684202,0.002632215,0.001915935,0.006680829],"category_scores_gemma":[0.06377773,0.001028682,0.001389699,0.002004561,0.001150823,0.004943328,0.002040846,0.002168698,0.002271751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094512,"about_ca_system_score_gemma":0.001865573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002871735,"about_ca_topic_score_gemma":0.00334958,"domain_scores_codex":[0.9854398,0.005918598,0.001402801,0.001656502,0.004851455,0.0007308448],"domain_scores_gemma":[0.9214358,0.04815075,0.007430682,0.01412758,0.007956191,0.0008989415],"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":[0.0008067993,0.00191927,0.05632962,0.001347721,0.0002367865,0.002689521,0.0008235904,0.1232042,0.08896373,0.01665823,0.02515726,0.6818634],"study_design_scores_gemma":[0.0005367082,0.001064177,0.0140745,0.0007117449,0.0002586574,0.002201181,0.0004753996,0.8056418,0.11735,0.01895848,0.03854674,0.0001805234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1992685,0.001595839,0.7417679,0.001945663,0.0002224918,0.0007211114,0.001454006,0.04763563,0.005388782],"genre_scores_gemma":[0.466347,0.0004913442,0.5233479,0.0008011628,0.00009885047,0.0003150342,0.004065966,0.003135887,0.001396974],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008221186,"threshold_uncertainty_score":0.04347825,"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."}}