{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003672547,0.0001466332,0.0001740842,0.0002653476,0.00006155152,0.00008257161,0.0009067489,0.00005312228,5.534051e-7],"category_scores_gemma":[0.005813382,0.0001151618,0.00006311793,0.0007721891,0.00003022231,0.0002651973,0.0003989326,0.0001895135,4.946142e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007372833,"about_ca_system_score_gemma":0.00002770887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001338501,"about_ca_topic_score_gemma":2.055154e-7,"domain_scores_codex":[0.9990235,0.000003716636,0.0002429716,0.0002707667,0.00028279,0.0001762746],"domain_scores_gemma":[0.9986883,0.0007393034,0.0001120515,0.0003133069,0.0001027513,0.0000442235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001464138,0.0004489607,0.2388211,0.02830784,0.001336419,0.00004867412,0.04969174,0.01273125,0.1848417,0.2829949,0.03413437,0.1664966],"study_design_scores_gemma":[0.000681524,0.0009246173,0.02359963,0.008466234,0.0001483067,0.0001380691,0.0002965741,0.5341299,0.2542319,0.1759917,0.0001344755,0.001257008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7125371,0.0001610537,0.2813063,0.0003756789,0.0003241859,0.0002021911,0.00000375659,0.005049613,0.00004021057],"genre_scores_gemma":[0.8197222,0.000003666968,0.1802067,0.00002132091,0.00001625201,0.000007503574,1.433525e-7,0.00001679797,0.000005424748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5213987,"threshold_uncertainty_score":0.6959581,"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."}}