{"id":"W3089336588","doi":"10.1145/3387940.3392236","title":"Are Automatic Bug Report Summarizers Missing the Target?","year":2020,"lang":"en","type":"article","venue":"","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; Annotation; Conversation; Sentence; Natural language processing; Software; Word (group theory); Interface (matter); Software bug; Gold standard (test); Artificial intelligence; Information retrieval; Programming language; 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":[0.01773229,0.001643996,0.001274683,0.004377145,0.0009342494,0.003704839,0.001938211,0.001538161,0.004316378],"category_scores_gemma":[0.1153935,0.0008756429,0.0007423211,0.002325742,0.000546327,0.00534013,0.001896138,0.00140805,0.006099727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006993408,"about_ca_system_score_gemma":0.001575736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002091891,"about_ca_topic_score_gemma":0.003205319,"domain_scores_codex":[0.982987,0.008044291,0.002060227,0.002421958,0.003871127,0.0006153407],"domain_scores_gemma":[0.884472,0.05036471,0.01356955,0.01675865,0.03322363,0.001611569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007828354,0.0002254968,0.02296625,0.003297907,0.0002459064,0.0005970522,0.006805201,0.001850771,0.04345224,0.003856409,0.0952395,0.8206804],"study_design_scores_gemma":[0.000375304,0.002246191,0.1262559,0.002977634,0.001230093,0.002741848,0.01145317,0.1171042,0.153464,0.0246108,0.5566965,0.000844256],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1732212,0.006566205,0.6770674,0.009436687,0.00306035,0.001172581,0.01336022,0.1009443,0.01517101],"genre_scores_gemma":[0.4280232,0.001793461,0.5289611,0.001850792,0.001277387,0.001373989,0.01972697,0.007113554,0.009879578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01773229,"threshold_uncertainty_score":0.09377843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03465459722830837,"score_gpt":0.2705932469559589,"score_spread":0.2359386497276506,"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."}}