{"id":"W3000602293","doi":"10.1109/tcad.2020.2966448","title":"Searching for Bugs Using Probabilistic Suspect Implications","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Suspect; Computer science; Probabilistic logic; Set (abstract data type); Machine learning; Hyperparameter; Algorithmic program debugging; Artificial intelligence; Software bug; Data mining; Programming language; Software","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":[0.0005223448,0.0002384467,0.0003947921,0.0002800227,0.0002368158,0.00028256,0.0006217996,0.0001009281,0.000002218904],"category_scores_gemma":[0.00008747198,0.0002177113,0.0001037745,0.0008232492,0.00006536266,0.0002544577,0.000005717049,0.0003121504,0.000003580753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001302301,"about_ca_system_score_gemma":0.0002697255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001283975,"about_ca_topic_score_gemma":0.000001144556,"domain_scores_codex":[0.9980476,0.0002064277,0.0004987519,0.0005803714,0.0002976819,0.0003691315],"domain_scores_gemma":[0.9969573,0.001823853,0.0001104315,0.0004354721,0.0004287323,0.0002441941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000177343,0.0001273746,0.00002478678,0.0003622994,0.0001387013,0.000004764507,0.0009524796,0.9186191,0.03017362,0.005390489,0.0001127416,0.04407594],"study_design_scores_gemma":[0.000435058,0.0006323871,0.00006598044,0.0001880568,0.00001888486,0.00005186573,0.00003999576,0.9941006,0.003982529,0.0002154778,0.00005469513,0.0002145101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008742857,0.00009651404,0.9888427,0.0001947054,0.0004498845,0.001294303,0.00004147402,0.0003300431,0.000007503756],"genre_scores_gemma":[0.9616072,0.00001004313,0.03809953,0.00004424456,0.00007420082,0.0001204906,0.000002213893,0.00003046509,0.00001163835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9528643,"threshold_uncertainty_score":0.8878008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1022860982032533,"score_gpt":0.2892106682700945,"score_spread":0.1869245700668411,"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."}}