{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01965829,0.0005311784,0.0003912555,0.003428265,0.001028882,0.001643682,0.001288583,0.0008818586,0.001390445],"category_scores_gemma":[0.1864453,0.0005836556,0.0003100416,0.002568746,0.001927084,0.003912123,0.0020741,0.002139419,0.0004201579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006959908,"about_ca_system_score_gemma":0.001232788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001950559,"about_ca_topic_score_gemma":0.002323758,"domain_scores_codex":[0.9807842,0.008362874,0.002045238,0.002349979,0.005663549,0.0007941647],"domain_scores_gemma":[0.6027452,0.2366589,0.09499525,0.0182035,0.04190523,0.005491954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003686884,0.0004543705,0.9053479,0.0004597038,0.0001019336,0.0006015427,0.03861083,0.000521938,0.002643862,0.0006614327,0.001712866,0.04851492],"study_design_scores_gemma":[0.00004510229,0.001123304,0.9454249,0.0003519808,0.00007777489,0.001252755,0.03082201,0.00671124,0.002559137,0.0009557027,0.01058241,0.00009365995],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968978,0.0001884824,0.001259206,0.0001713766,0.000009463416,0.00004659496,0.0001485798,0.00007441913,0.001204128],"genre_scores_gemma":[0.9976841,0.0001276276,0.001259637,0.00008177973,0.00001243646,0.00007731518,0.0002744886,0.00004030961,0.0004421594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01965829,"threshold_uncertainty_score":0.1039641,"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."}}