{"id":"W4389158953","doi":"10.1145/3611643.3616272","title":"Statfier: Automated Testing of Static Analyzers via Semantic-Preserving Program Transformations","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Huawei Technologies; National Natural Science Foundation of China","keywords":"Computer science; Static analysis; Heuristics; Key (lock); Test suite; Spectrum analyzer; Spurious relationship; Selection (genetic algorithm); Program analysis; Documentation; Static program analysis; Programming language; Data mining; Test case; Software; Artificial intelligence; Machine learning","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":[0.0005183482,0.0001186762,0.0001733707,0.0003401227,0.0001343779,0.0001057629,0.0006462782,0.00003897819,0.000007826058],"category_scores_gemma":[0.0005581069,0.0001061075,0.00004932483,0.002682372,0.00003892095,0.0004293505,0.0001508667,0.00008775122,0.00002371425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001837202,"about_ca_system_score_gemma":0.00007020274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003648163,"about_ca_topic_score_gemma":0.00001424536,"domain_scores_codex":[0.9987398,0.00005313059,0.000373727,0.0002186562,0.0002891317,0.0003255657],"domain_scores_gemma":[0.9984624,0.000703829,0.0001060569,0.0004668263,0.000187901,0.00007300181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005550812,0.0003966325,0.04523105,0.0009093596,0.0001440207,0.00006956015,0.006912835,0.01092735,0.003119498,0.00326715,0.09775286,0.8312641],"study_design_scores_gemma":[0.00009159791,0.0001082784,0.005569573,0.00008450188,0.000008106575,0.00000849431,0.00001947189,0.9792048,0.001398505,0.01332141,0.00005824275,0.0001269599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04857743,0.00000858023,0.838717,0.000420229,0.0000617063,0.0003343339,0.000003171672,0.1101965,0.001681111],"genre_scores_gemma":[0.5066167,0.000001441989,0.4932684,0.00003036786,0.000004053531,0.00003313654,0.000005817301,0.000007949247,0.00003223752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9682775,"threshold_uncertainty_score":0.4326937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04095253853958841,"score_gpt":0.3210001708726699,"score_spread":0.2800476323330814,"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."}}