{"id":"W4411449952","doi":"10.1145/3715729","title":"An Empirical Study of Suppressed Static Analysis Warnings","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Spectrum analyzer; False positive paradox; Python (programming language); Computer science; Software; Static analysis; Scalability; Empirical research; False positives and false negatives; Code (set theory); Artificial intelligence; Programming language; Statistics; Telecommunications; Operating system; Mathematics","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":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006074032,0.0002540926,0.0005056435,0.0009748475,0.00006790309,0.00009165994,0.005575232,0.00008831058,0.000005598266],"category_scores_gemma":[0.01073514,0.0002016374,0.0001839418,0.004464231,0.00004246697,0.0003306935,0.001297374,0.0003873263,0.000001739844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000807718,"about_ca_system_score_gemma":0.00006020475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003110128,"about_ca_topic_score_gemma":0.000001013267,"domain_scores_codex":[0.9977868,0.00001654569,0.0004712938,0.0005270116,0.000826635,0.0003716904],"domain_scores_gemma":[0.9966791,0.001058672,0.0001625072,0.00153039,0.0004652351,0.0001041019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003943681,0.0008406437,0.9417418,0.0003460299,0.0007825406,0.000001839448,0.004136174,0.04694258,0.002346176,0.0004163746,0.001557714,0.0008486959],"study_design_scores_gemma":[0.0008161418,0.0008439996,0.8840759,0.0001513494,0.0002572831,0.000001622953,0.0001930318,0.09323194,0.01948226,0.000426725,0.000178925,0.0003407694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9571946,0.00003111297,0.04148457,0.0002578566,0.0001829989,0.0003762047,0.000004200335,0.0004577234,0.00001069254],"genre_scores_gemma":[0.9678928,0.000001875103,0.03190617,0.00004057954,0.00001620852,0.00005305267,8.411228e-7,0.0000222875,0.00006617692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05766583,"threshold_uncertainty_score":0.9998051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0138911653291388,"score_gpt":0.297761580012134,"score_spread":0.2838704146829952,"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."}}