{"id":"W4400421435","doi":"10.1016/j.procs.2024.06.069","title":"Triage Software Update Impact via Release Notes Classification","year":2024,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Triage; Categorization; Classifier (UML); Software; Machine learning; Process (computing); Artificial intelligence","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001334956,0.0002551401,0.00018943,0.0007321014,0.0002639561,0.001870996,0.002911408,0.00006908767,0.00001506449],"category_scores_gemma":[0.000976591,0.0002139688,0.0001097925,0.004146989,0.0002648212,0.002582074,0.0008312039,0.0003735973,0.0005891468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000304725,"about_ca_system_score_gemma":0.0009801462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001557749,"about_ca_topic_score_gemma":8.446987e-7,"domain_scores_codex":[0.9965495,0.00003623623,0.0002986287,0.001206799,0.001123056,0.0007858008],"domain_scores_gemma":[0.9972168,0.00098295,0.000049777,0.001025886,0.0003168453,0.0004077578],"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":[0.000007804673,0.00007870559,0.003997809,0.0001826718,0.00002254887,0.000113142,0.001033406,0.002543675,0.006266953,0.007533248,0.001821913,0.9763981],"study_design_scores_gemma":[0.000111172,0.0001114611,0.02802846,0.0000789401,0.00000366615,0.0001066695,9.642783e-7,0.9643697,0.004283913,0.001833971,0.0007575617,0.000313549],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04096212,0.0004766595,0.9539187,0.0008374498,0.001541611,0.0002675538,0.000003569774,0.001973157,0.00001917363],"genre_scores_gemma":[0.778231,0.00001952739,0.2212786,0.0001118149,0.0002854976,0.00003627457,0.000002995891,0.00001899047,0.00001531982],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9760846,"threshold_uncertainty_score":0.9991652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02340600854374134,"score_gpt":0.3028551375921746,"score_spread":0.2794491290484333,"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."}}