{"id":"W4205795599","doi":"10.1109/ase51524.2021.9678554","title":"Automatically Annotating Sentences for Task-specific Bug Report Summarization","year":2021,"lang":"en","type":"article","venue":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge; University of Alberta","funders":"","keywords":"Automatic summarization; Computer science; Task (project management); DevOps; Annotation; Software engineering; Information retrieval; World Wide Web; Natural language processing; Software; Artificial intelligence; Programming language; Engineering","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007018221,0.0004846244,0.000451719,0.0004963211,0.0001949681,0.0009185675,0.001836953,0.0002249285,0.000255864],"category_scores_gemma":[0.01128748,0.0005350597,0.0002021106,0.0009795424,0.00005140596,0.0006839476,0.0003985569,0.000493367,0.0001381784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000361947,"about_ca_system_score_gemma":0.0005567026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001308643,"about_ca_topic_score_gemma":0.000003005357,"domain_scores_codex":[0.995818,0.00007892433,0.0008920337,0.001152633,0.001311017,0.0007473992],"domain_scores_gemma":[0.9946885,0.001883843,0.0002369568,0.001290062,0.00161263,0.0002879815],"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":[0.0001251043,0.00123916,0.01151106,0.001111562,0.001562516,0.008048239,0.002304485,0.6880935,0.0550103,0.1265145,0.04460564,0.05987384],"study_design_scores_gemma":[0.000586909,0.00009069535,0.004142082,0.000481555,0.00001185065,0.0002890988,0.00004490338,0.9819797,0.007267535,0.0004662027,0.004020328,0.0006190923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02049132,0.00008376284,0.9698473,0.001146049,0.004059568,0.0004047928,0.0001196565,0.003688516,0.0001590263],"genre_scores_gemma":[0.5101559,0.00007793626,0.4870024,0.0001547806,0.0004116122,0.0002811982,0.0007286748,0.0001037216,0.001083758],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4896646,"threshold_uncertainty_score":0.9997101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03620246813544579,"score_gpt":0.3043772340185386,"score_spread":0.2681747658830928,"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."}}