{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006319378,0.001776261,0.001109014,0.006716064,0.001294974,0.00181467,0.001971189,0.001888601,0.00379276],"category_scores_gemma":[0.06247044,0.000593511,0.0008379499,0.002853735,0.0007202856,0.004178423,0.00290997,0.001434209,0.003695706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001098111,"about_ca_system_score_gemma":0.002262015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004580475,"about_ca_topic_score_gemma":0.00735255,"domain_scores_codex":[0.9866701,0.001837675,0.001600355,0.002548142,0.006806789,0.0005369352],"domain_scores_gemma":[0.8626401,0.06109077,0.0260749,0.01401147,0.03489628,0.001286598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001423929,0.0002629113,0.1458799,0.005724131,0.0002980517,0.004512443,0.005828599,0.004367162,0.07432779,0.009245039,0.08583871,0.6622913],"study_design_scores_gemma":[0.000175342,0.0007324441,0.1119815,0.002543337,0.0007058166,0.008918107,0.005525863,0.1031028,0.2594939,0.01556202,0.4905571,0.0007018342],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.430742,0.005036392,0.4356569,0.001798568,0.001567952,0.001866506,0.03204421,0.0729735,0.01831394],"genre_scores_gemma":[0.5179931,0.001431944,0.4032259,0.001139378,0.0004091088,0.0009570939,0.04366087,0.008363831,0.02281881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006716064,"threshold_uncertainty_score":0.03342044,"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."}}