{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002988872,0.0003299527,0.0003259602,0.0003915429,0.0001784115,0.0002350954,0.0008117364,0.0001730371,0.0000067101],"category_scores_gemma":[0.002444045,0.0003300446,0.0001143879,0.001494956,0.0000332401,0.0002777669,0.0002541643,0.0003457122,0.00002460581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002139345,"about_ca_system_score_gemma":0.000144765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000474195,"about_ca_topic_score_gemma":0.000003486414,"domain_scores_codex":[0.9980587,0.0000370401,0.0003959383,0.0006189129,0.0003583004,0.0005310681],"domain_scores_gemma":[0.998156,0.0007701451,0.00007497206,0.0007457039,0.00009728661,0.0001559477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001147672,0.000184524,0.5694888,0.0003021368,0.00005371336,0.00008842591,0.0002266048,0.3939445,0.0001181643,0.001113398,0.01594483,0.01852345],"study_design_scores_gemma":[0.0003554735,0.00007117067,0.02635163,0.0004587669,0.00001553087,0.00001551944,7.002429e-7,0.9558288,0.002680573,0.003106197,0.01057718,0.0005384132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01358966,0.0002060489,0.9603709,0.0005699089,0.0004564361,0.0001957347,0.000001575766,0.02452233,0.00008738725],"genre_scores_gemma":[0.7370477,0.00000308053,0.2618835,0.0008266711,0.00008129121,0.00003087235,0.00000683401,0.00003345054,0.00008655217],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7234581,"threshold_uncertainty_score":0.9999152,"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."}}