{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004647503,0.00252505,0.001319225,0.002256935,0.0008473489,0.001853355,0.005609499,0.002089003,0.004482385],"category_scores_gemma":[0.02009271,0.001670307,0.001642323,0.001340928,0.00153765,0.007209259,0.008826314,0.003802818,0.002536381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001238142,"about_ca_system_score_gemma":0.002941068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007857844,"about_ca_topic_score_gemma":0.01747086,"domain_scores_codex":[0.9959975,0.001070827,0.0002736783,0.001377758,0.001005198,0.0002750352],"domain_scores_gemma":[0.9898369,0.003519681,0.0009207166,0.004080894,0.001176383,0.0004654057],"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":[0.0007517732,0.0007254828,0.01360238,0.0004430714,0.000313096,0.0005082815,0.001543449,0.08985984,0.02072959,0.008526217,0.04028865,0.8227081],"study_design_scores_gemma":[0.0001523586,0.0003110634,0.00207345,0.00004698885,0.00006711255,0.0002484189,0.0002824485,0.9424685,0.02002176,0.019358,0.01487756,0.00009236234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03354417,0.0003777778,0.8230608,0.0007321176,0.0001534372,0.0003617528,0.0008240105,0.1383937,0.002552294],"genre_scores_gemma":[0.1586348,0.0001482844,0.827288,0.0005675703,0.00003934141,0.0003821884,0.003000394,0.005198458,0.004740914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007857844,"threshold_uncertainty_score":0.02457869,"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."}}