{"id":"W2967302497","doi":"10.18293/seke2019-219","title":"Feature Evaluation for Automatic Bug Report Summarization (S)","year":2019,"lang":"en","type":"article","venue":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Automatic summarization; Computer science; Precision and recall; Feature (linguistics); Natural language processing; Recall; Artificial intelligence; Sentence; Software; Software bug; Software regression; Information retrieval; Software development; Programming language; Software quality; Linguistics","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":[0.008816846,0.00210495,0.001657996,0.009027217,0.0006797338,0.002155411,0.001745232,0.001170386,0.002096594],"category_scores_gemma":[0.0493961,0.0004718362,0.001625224,0.004205985,0.0002925157,0.002514452,0.001173679,0.001172992,0.001797188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043414,"about_ca_system_score_gemma":0.001302778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006153525,"about_ca_topic_score_gemma":0.005581913,"domain_scores_codex":[0.9937294,0.001878022,0.0009373372,0.001198882,0.001870247,0.000386051],"domain_scores_gemma":[0.9581566,0.02261163,0.004584798,0.002972726,0.01107749,0.0005966585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00178751,0.0007479177,0.07169203,0.002594118,0.00075633,0.0006515136,0.001131224,0.01909544,0.04177251,0.0009820606,0.0413879,0.8174015],"study_design_scores_gemma":[0.0004340048,0.002717043,0.1314848,0.0004878991,0.001701744,0.001399818,0.001261631,0.7375469,0.08948749,0.002716908,0.030395,0.0003667371],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.464184,0.005520133,0.4190954,0.001411441,0.0005955126,0.001492499,0.02264697,0.0801787,0.004875344],"genre_scores_gemma":[0.714016,0.0007008644,0.2446298,0.0001635275,0.0002465885,0.0009052226,0.0358005,0.0009777276,0.002559733],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009027217,"threshold_uncertainty_score":0.04662853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02174730908305818,"score_gpt":0.271068682737073,"score_spread":0.2493213736540148,"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."}}