{"id":"W2767331170","doi":"10.1109/ase.2017.8115624","title":"Detecting fragile comments","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Identifier; Code refactoring; Computer science; Eclipse; Correctness; Programming language; Precision and recall; Feature (linguistics); Java; Set (abstract data type); Syntax; Data mining; Software; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001848678,0.00003972286,0.00004122829,0.00002982742,0.0002917327,0.0003918552,0.001399757,0.00001769688,0.00002761418],"category_scores_gemma":[0.0007306108,0.00003563316,0.00001576176,0.00003150028,0.00001390634,0.0003327317,0.0006073632,0.00008453735,0.0001779729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001724892,"about_ca_system_score_gemma":0.0000101176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007072862,"about_ca_topic_score_gemma":0.00000312341,"domain_scores_codex":[0.9994892,0.000006647121,0.00004649016,0.0001324757,0.0001555869,0.0001696252],"domain_scores_gemma":[0.9988319,0.0001699418,0.00001892877,0.0009008565,0.00002534284,0.00005302051],"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":[0.00000179204,0.00005984767,0.360413,0.00002471751,0.00003295459,0.00007719336,0.0005662593,0.000130627,0.00231335,0.01582811,0.01123169,0.6093204],"study_design_scores_gemma":[0.0006833812,0.000087051,0.7870442,0.00003591288,0.000001464175,0.00002283308,0.00001431849,0.1359648,0.04654841,0.002731824,0.02645401,0.000411849],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1214075,0.00001092747,0.8683739,0.0009009021,0.0004059685,0.0000536544,1.307492e-7,0.0003832106,0.008463784],"genre_scores_gemma":[0.9578907,6.442748e-7,0.04131918,0.00007262584,0.00002964303,0.000004279569,4.793683e-8,0.000003657935,0.0006791741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8364832,"threshold_uncertainty_score":0.3778669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03487120117828642,"score_gpt":0.311380313370458,"score_spread":0.2765091121921716,"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."}}