{"id":"W2519113869","doi":"10.1109/ivsw.2016.7566604","title":"Revision debug with non-linear version history in regression verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Bottleneck; Preprocessor; Ranking (information retrieval); Regression testing; Software bug; Correctness; Graph; Software engineering; Programming language; Theoretical computer science; Embedded system; Information retrieval; Software system","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002861031,0.00008817343,0.00009020705,0.0001284973,0.00003413199,0.00001015531,0.000348501,0.00005104125,0.00001635419],"category_scores_gemma":[0.000126096,0.00004645935,0.00001702209,0.0001684097,0.00002852337,0.0003402516,0.00008747535,0.00005528711,0.00006841543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002287653,"about_ca_system_score_gemma":0.00007164181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005242744,"about_ca_topic_score_gemma":0.000001875264,"domain_scores_codex":[0.999215,0.00003719908,0.0001287148,0.0003035578,0.0001823316,0.0001331786],"domain_scores_gemma":[0.9991542,0.0001358462,0.00006703123,0.0005384474,0.00006091592,0.00004358348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008947735,0.0001436902,0.02776408,0.00003650508,0.000002781672,0.00004219559,0.0005167327,0.000007419888,0.006918713,0.002022715,0.3423823,0.6200734],"study_design_scores_gemma":[0.007292205,0.002921767,0.07557239,0.0112526,0.00002567219,0.0001832801,0.00002989499,0.2161211,0.08977498,0.01914675,0.5748075,0.00287194],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02580033,0.0001073171,0.9675357,0.0007647703,0.0001319687,0.0001145047,1.421559e-7,0.003768286,0.001776994],"genre_scores_gemma":[0.6717601,0.00002445277,0.3271822,0.0002042993,0.00001974665,0.000006098215,8.70784e-7,0.000007393456,0.0007948196],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6459598,"threshold_uncertainty_score":0.1894557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02317134808403726,"score_gpt":0.2530379753674551,"score_spread":0.2298666272834179,"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."}}