{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005061737,0.001727064,0.0007926928,0.002147079,0.0006095315,0.001630208,0.002968446,0.001257141,0.002012329],"category_scores_gemma":[0.02351421,0.000986073,0.001397538,0.001408025,0.002244628,0.003035022,0.001453864,0.001549106,0.000915639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123544,"about_ca_system_score_gemma":0.003266364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00426089,"about_ca_topic_score_gemma":0.00480011,"domain_scores_codex":[0.9903637,0.003202372,0.0006825386,0.001482922,0.003619486,0.0006490049],"domain_scores_gemma":[0.9782602,0.01188879,0.002283297,0.00537572,0.001931472,0.0002605848],"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":[0.002065563,0.001282859,0.04198906,0.001247725,0.0005002331,0.001703655,0.001707514,0.2119922,0.1793752,0.02638942,0.01626945,0.515477],"study_design_scores_gemma":[0.000241495,0.0007682242,0.004846613,0.000111256,0.0001259071,0.0008780656,0.0002431984,0.8195373,0.1517743,0.01222633,0.009117804,0.0001294562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1899872,0.0003382456,0.6878874,0.0003583385,0.00008737156,0.0004315526,0.001420421,0.1165137,0.002975822],"genre_scores_gemma":[0.5549897,0.0001456238,0.4362004,0.0002513745,0.00002426342,0.0002792196,0.00254366,0.0043439,0.001221832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005061737,"threshold_uncertainty_score":0.02676934,"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."}}