{"id":"W3009853975","doi":"10.1002/smr.2250","title":"Guidelines for evaluating bug‐assignment research","year":2020,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Faculty of Graduate Studies and Research, University of Alberta; Alberta Innovates - Technology Futures","keywords":"Computer science; Metric (unit); Ranking (information retrieval); Empirical research; Task (project management); Set (abstract data type); Data science; Data mining; Information retrieval; Statistics; Systems engineering; Mathematics; Engineering; Operations management","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4691598,0.004148416,0.005599611,0.04623996,0.004312763,0.01351479,0.009125081,0.005672105,0.005604661],"category_scores_gemma":[0.7554678,0.003114385,0.006132975,0.02785995,0.006124084,0.01011526,0.007026958,0.005002617,0.004340338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008857794,"about_ca_system_score_gemma":0.01713749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004802534,"about_ca_topic_score_gemma":0.007972544,"domain_scores_codex":[0.3428542,0.4698029,0.1112827,0.009128693,0.06487314,0.002058426],"domain_scores_gemma":[0.1148283,0.6000945,0.05965311,0.03875305,0.1837238,0.002947312],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003609622,0.002329334,0.03469468,0.06044343,0.002738234,0.0006524482,0.01734815,0.007847033,0.01143318,0.0483213,0.08179494,0.7287877],"study_design_scores_gemma":[0.006763606,0.009742638,0.09105337,0.1515033,0.00680815,0.001165821,0.02217465,0.05883285,0.05737302,0.1581158,0.4342593,0.002207523],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04701569,0.04556948,0.7464631,0.01173391,0.00250483,0.09263103,0.01050961,0.006219345,0.03735296],"genre_scores_gemma":[0.05571956,0.003317666,0.8557391,0.00122336,0.0002383579,0.08007022,0.002315805,0.0004579246,0.0009179771],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5308402,"threshold_uncertainty_score":0.6546205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2884186218319023,"score_gpt":0.4726799934303204,"score_spread":0.1842613715984182,"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."}}