{"id":"W4400302466","doi":"10.1002/smr.2710","title":"On the value of instance selection for bug resolution prediction performance","year":2024,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Selection (genetic algorithm); Value (mathematics); Resolution (logic); Artificial intelligence; Machine learning; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0008288071,0.00006383007,0.00008305097,0.0001381946,0.0001622443,0.00006754138,0.0001733227,0.0000453584,0.000001945135],"category_scores_gemma":[0.0003398331,0.00004229056,0.0000372701,0.0003581421,0.00003116421,0.0006402847,0.00001262505,0.000191936,0.000001119039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006359391,"about_ca_system_score_gemma":0.000136142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000276636,"about_ca_topic_score_gemma":9.66055e-7,"domain_scores_codex":[0.9992484,0.00005021357,0.000260425,0.0001246112,0.0002341153,0.00008225923],"domain_scores_gemma":[0.9991798,0.0002094267,0.0002164168,0.00008894074,0.0002771651,0.0000282462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006860468,0.0002507942,0.04257886,0.002491729,0.0001354195,0.000001256007,0.003282855,0.05167855,0.002170247,0.6259845,0.01309243,0.2576472],"study_design_scores_gemma":[0.0002949871,0.0008271672,0.06178712,0.0006170264,0.00002576093,0.00008813756,0.00005330961,0.9120723,0.0006847017,0.01774303,0.005717303,0.00008918996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1648381,0.0008449998,0.8328951,0.0008830058,0.000341658,0.00009150816,0.000005874505,0.00005025163,0.00004948515],"genre_scores_gemma":[0.9953518,0.0001279137,0.00427745,0.00004115806,0.0001192833,0.000007460884,0.000002524001,0.000004463556,0.00006796922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8603937,"threshold_uncertainty_score":0.1724559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01208088580929729,"score_gpt":0.2595333875728785,"score_spread":0.2474525017635812,"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."}}