{"id":"W4416248181","doi":"10.1007/s10664-025-10761-8","title":"SBEST: Spectrum-based fault localization without fault-triggering tests","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Concordia University","funders":"","keywords":"Stack (abstract data type); Software bug; Context (archaeology); TRACE (psycholinguistics); Call stack; Fault (geology); Software regression; Software; Debugging","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001681994,0.001837779,0.001408279,0.003208433,0.0005979371,0.001100323,0.003098178,0.001363273,0.006734475],"category_scores_gemma":[0.009959416,0.0007178409,0.0008673638,0.001345972,0.001182128,0.00270399,0.002465901,0.001403544,0.0025714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005111044,"about_ca_system_score_gemma":0.001262985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002120033,"about_ca_topic_score_gemma":0.002619432,"domain_scores_codex":[0.997171,0.0006665667,0.0001635219,0.0004838677,0.001274442,0.0002406605],"domain_scores_gemma":[0.9920861,0.002998071,0.0007610139,0.002644101,0.00118563,0.0003250115],"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":[0.003024251,0.000813999,0.009108804,0.0007088885,0.000300243,0.0006970906,0.0003217324,0.101354,0.06372995,0.02102783,0.02109164,0.7778215],"study_design_scores_gemma":[0.0002564294,0.0004898979,0.001801451,0.00006207136,0.0001027306,0.0005030567,0.00006821231,0.921379,0.04413567,0.02695158,0.004184089,0.00006586153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02113891,0.0001267535,0.9219695,0.00009138668,0.00007585069,0.000093112,0.0004106087,0.05447465,0.001619166],"genre_scores_gemma":[0.4611116,0.00008919377,0.5311285,0.000171415,0.00005888853,0.0001776783,0.001195352,0.003153414,0.002913926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006734475,"threshold_uncertainty_score":0.02252901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01565781770040737,"score_gpt":0.2853496556163299,"score_spread":0.2696918379159225,"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."}}