{"id":"W4411232430","doi":"10.1109/tse.2025.3579574","title":"BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Waterloo","funders":"","keywords":"Computer science; Chunking (psychology); Programming language; Software engineering; Artificial intelligence; Natural language processing","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":[0.0003500855,0.0002886574,0.0002374239,0.0006254439,0.0004055385,0.0005758811,0.0003473649,0.0001535358,0.000008348741],"category_scores_gemma":[0.0002132101,0.0003308295,0.00006273948,0.0009493913,0.00007490072,0.0006083957,0.00002326452,0.0006092213,0.000006426237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001621136,"about_ca_system_score_gemma":0.0000595108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001577011,"about_ca_topic_score_gemma":0.000009735791,"domain_scores_codex":[0.9982689,0.00003490845,0.0002810096,0.000643924,0.00030076,0.0004704908],"domain_scores_gemma":[0.998578,0.0007457249,0.0000365975,0.0004419129,0.00009196567,0.0001058395],"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":[0.0000130507,0.0000326389,0.007188668,0.0003235071,0.00007073182,0.00002947143,0.001250019,0.9477327,0.002144053,0.0001120806,0.000008551792,0.04109456],"study_design_scores_gemma":[0.0005982673,0.00007303674,0.03234013,0.0001785254,0.00001495415,0.000052908,0.00002670818,0.9612473,0.004644106,0.00001838916,0.0004119896,0.0003936946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2413834,0.000349912,0.7564265,0.00001065039,0.000457123,0.00019114,0.000003787364,0.001173803,0.000003677528],"genre_scores_gemma":[0.9637802,0.00006997816,0.03552494,0.00002491327,0.00002146558,0.00006741146,0.000003516763,0.0000460467,0.0004615342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7223967,"threshold_uncertainty_score":0.9999143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01039770608685179,"score_gpt":0.2798341540061944,"score_spread":0.2694364479193426,"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."}}