{"id":"W4404860113","doi":"10.1007/s10664-024-10589-8","title":"Contrasting test selection, prioritization, and batch testing at scale","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Prioritization; Selection (genetic algorithm); Scale (ratio); Test (biology); Computer science; Regression testing; Reliability engineering; Engineering; Machine learning; Biology; Geography; Management science; Cartography; Operating system; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04602467,0.001200436,0.001486042,0.001894178,0.001043001,0.003019786,0.003107627,0.002046447,0.003823576],"category_scores_gemma":[0.2828362,0.0006015443,0.000863053,0.002239321,0.004027347,0.007002588,0.002319755,0.00261113,0.0003653484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002964937,"about_ca_system_score_gemma":0.003584174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01199396,"about_ca_topic_score_gemma":0.01306007,"domain_scores_codex":[0.9616919,0.02681852,0.001059463,0.003108744,0.005537163,0.001784354],"domain_scores_gemma":[0.4532197,0.4980282,0.0159197,0.0189081,0.0101573,0.003766925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01395391,0.004135782,0.2827919,0.001110226,0.001632448,0.0008340558,0.003451646,0.1524799,0.01331132,0.1118995,0.007232205,0.4071671],"study_design_scores_gemma":[0.002391783,0.006983165,0.3213064,0.0002877353,0.001190549,0.0005499144,0.003169299,0.3992859,0.00986393,0.2504798,0.004226229,0.000265319],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8943175,0.001929488,0.08601288,0.003279584,0.0001229563,0.0002658672,0.0002223964,0.0006469449,0.01320238],"genre_scores_gemma":[0.986739,0.00007881837,0.01202115,0.0001860204,0.00004797602,0.00006975466,0.00008790527,0.00006861456,0.0007007273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04602467,"threshold_uncertainty_score":0.2434046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01666081653409694,"score_gpt":0.2537672231562379,"score_spread":0.237106406622141,"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."}}