{"id":"W4404341048","doi":"10.48550/arxiv.2410.21798","title":"Efficient Incremental Code Coverage Analysis for Regression Test Suites","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; University of Waterloo","keywords":"Regression testing; Computer science; Code (set theory); Test (biology); Programming language; Code coverage; Regression analysis; Statistics; Mathematics; Machine learning; Software; Geology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004667641,0.0003512967,0.0004226115,0.0007408981,0.0002033456,0.0002670844,0.001505778,0.0002444642,0.000009836773],"category_scores_gemma":[0.0005059615,0.000349145,0.000484909,0.001434264,0.00007610196,0.00004857571,0.003289746,0.0004527255,0.00003014219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003124569,"about_ca_system_score_gemma":0.0001596242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001506271,"about_ca_topic_score_gemma":0.00002642358,"domain_scores_codex":[0.9978521,0.00006926313,0.0002327938,0.001350785,0.0001399233,0.0003551613],"domain_scores_gemma":[0.9967436,0.001487064,0.0002274735,0.00125262,0.000152954,0.0001362932],"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":[0.00008168874,0.0008223621,0.206715,0.0008945104,0.001687171,0.001015126,0.0007653159,0.6694427,0.0003063899,0.08918149,0.02566974,0.003418474],"study_design_scores_gemma":[0.0001855451,0.00008001835,0.001345327,0.0002717137,0.0004823701,0.000003157855,0.000005603332,0.9307182,0.0003392411,0.06597755,0.0001678576,0.0004233618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2248034,0.0001568676,0.7669284,0.00009791556,0.0003808525,0.0003946167,0.0001516436,0.006608238,0.0004779825],"genre_scores_gemma":[0.9822918,0.00002571105,0.01669833,0.00007459232,0.00005869664,0.000005196448,0.00005601706,0.00002318941,0.0007665376],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7574883,"threshold_uncertainty_score":0.999896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07111415282567106,"score_gpt":0.2279870625825795,"score_spread":0.1568729097569084,"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."}}