{"id":"W2757935660","doi":"10.1109/tse.2017.2755005","title":"Revisiting the Performance Evaluation of Automated Approaches for the Retrieval of Duplicate Issue Reports","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Information retrieval; Eclipse; Categorical variable; Software; Notation; Data mining; Machine learning; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.002606782,0.0001538995,0.0001965475,0.0001135241,0.000432897,0.000100473,0.0009705554,0.00006945519,0.000005181417],"category_scores_gemma":[0.001232031,0.0001089399,0.0001263746,0.0002748833,0.00006984731,0.0003354322,0.00001278966,0.0002462866,0.000001852431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007168687,"about_ca_system_score_gemma":0.00009113093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001271558,"about_ca_topic_score_gemma":3.503562e-7,"domain_scores_codex":[0.9983641,0.00003108786,0.0003816648,0.0002816584,0.0006910512,0.0002504746],"domain_scores_gemma":[0.996334,0.001466868,0.0002400304,0.001579448,0.0003394139,0.0000403031],"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":[0.000008937129,0.00001448173,0.0002365175,0.0001486433,0.00007031999,6.546788e-7,0.0002441562,0.9342889,0.0007511694,0.00002720388,0.00001674759,0.06419224],"study_design_scores_gemma":[0.0001832397,0.00003621727,0.01487548,0.0001311186,0.00004699894,0.00001711984,0.000009287509,0.9140632,0.07040825,0.000004935305,0.0001182824,0.0001058357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1303318,0.0001578175,0.8677899,0.0001691167,0.0005843102,0.0005823676,0.000005436756,0.0003752149,0.000004085429],"genre_scores_gemma":[0.9816102,0.0000220723,0.01809216,0.000003453935,0.00008177593,0.0001359424,7.192915e-7,0.00002501772,0.0000286151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8512785,"threshold_uncertainty_score":0.444244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05980927837122244,"score_gpt":0.2995360331029995,"score_spread":0.2397267547317771,"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."}}