{"id":"W2360967250","doi":"10.1145/2884781.2884804","title":"Automatically learning semantic features for defect prediction","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":692,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software bug; Focus (optics); ENCODE; Machine learning; Code (set theory); Artificial intelligence; Software; Software engineering; Data mining; Programming language","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":[0.0006788636,0.001340996,0.0009724786,0.00394356,0.0004802903,0.0006027179,0.001027311,0.001201661,0.001204738],"category_scores_gemma":[0.006156437,0.000385203,0.0008928801,0.002078668,0.0005241603,0.002787068,0.000903044,0.001133456,0.0007210067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006658527,"about_ca_system_score_gemma":0.001055159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003697345,"about_ca_topic_score_gemma":0.005896444,"domain_scores_codex":[0.9990923,0.0001383379,0.00006874122,0.0002945128,0.0003036232,0.0001024771],"domain_scores_gemma":[0.9963439,0.001911464,0.0004594012,0.0004566735,0.0007136806,0.000114803],"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":[0.0007076703,0.001071619,0.06411071,0.0006174032,0.0001736561,0.0007695646,0.0002616833,0.1032741,0.02662402,0.01126487,0.03357187,0.7575529],"study_design_scores_gemma":[0.00004269535,0.0001397068,0.007829441,0.00005106588,0.00007390664,0.0002197876,0.00008586019,0.9543732,0.009957517,0.02288428,0.004307881,0.00003469535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3142498,0.001647644,0.6528025,0.0007202987,0.0001687006,0.0002217196,0.007530902,0.0191849,0.003473699],"genre_scores_gemma":[0.8248921,0.000355069,0.1604596,0.0001164268,0.00007470138,0.0002114607,0.01274989,0.0003400081,0.000800742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00394356,"threshold_uncertainty_score":0.007351637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051924701454742,"score_gpt":0.2535673509846479,"score_spread":0.2430481039701005,"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."}}