{"id":"W4400582740","doi":"10.1145/3643759","title":"Understanding and Detecting Annotation-Induced Faults of Static Analyzers","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence","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":[0.004572764,0.001154198,0.0006672054,0.004685577,0.0006171915,0.00169176,0.001418407,0.001409862,0.000752366],"category_scores_gemma":[0.03499101,0.0006691461,0.000757088,0.001657995,0.001422308,0.003790471,0.001320717,0.001052522,0.0001990294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001179266,"about_ca_system_score_gemma":0.001651439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003707778,"about_ca_topic_score_gemma":0.004932108,"domain_scores_codex":[0.9916937,0.00253628,0.0006545408,0.001343127,0.003118526,0.0006538118],"domain_scores_gemma":[0.9542338,0.02915878,0.006627103,0.004783086,0.004848645,0.0003487281],"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":[0.0008111766,0.0007609235,0.3331147,0.001132387,0.0002583624,0.004228123,0.0125037,0.04721941,0.1347222,0.0183922,0.003101259,0.4437557],"study_design_scores_gemma":[0.00008216942,0.0006735618,0.1125452,0.0004573537,0.0005780004,0.003179444,0.003413914,0.6718457,0.174018,0.02255343,0.01045698,0.0001961569],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6221396,0.000567366,0.3670848,0.0004096175,0.00004502899,0.000178592,0.000329288,0.007297831,0.001947991],"genre_scores_gemma":[0.8962969,0.0001688756,0.1022392,0.0000771854,0.00002116793,0.00007430744,0.0003603895,0.000341832,0.0004201682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004685577,"threshold_uncertainty_score":0.02418339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05424952230509408,"score_gpt":0.2565203950209407,"score_spread":0.2022708727158466,"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."}}