{"id":"W4394746056","doi":"10.1145/3597503.3639112","title":"Mozi: Discovering DBMS Bugs via Configuration-Based Equivalent Transformation","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Correctness; Programming language; SQL; Semantics (computer science); Database; Query language; Transformation (genetics); Task (project management)","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":[0.006916138,0.002463517,0.001856618,0.005259435,0.001263919,0.003567623,0.005723133,0.002684209,0.002434068],"category_scores_gemma":[0.04493169,0.001428808,0.002738534,0.002311155,0.004212034,0.006795346,0.005214926,0.003145671,0.0007718733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001868228,"about_ca_system_score_gemma":0.002991938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006683354,"about_ca_topic_score_gemma":0.006636204,"domain_scores_codex":[0.9865384,0.002798398,0.0009573768,0.003102085,0.005387739,0.001216012],"domain_scores_gemma":[0.9787416,0.008456806,0.003428501,0.006303695,0.002564009,0.0005053375],"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":[0.001873632,0.00148025,0.1233657,0.001497203,0.0007910038,0.003482424,0.003200583,0.2043591,0.07110326,0.1271424,0.01905921,0.4426452],"study_design_scores_gemma":[0.000141854,0.0005070473,0.005878457,0.0001544286,0.0001906613,0.001302339,0.0005194409,0.8583049,0.03720901,0.08875596,0.006850495,0.0001853852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0646181,0.0004504231,0.8893278,0.0005957221,0.0000748407,0.0004075733,0.0006860784,0.04139972,0.002439879],"genre_scores_gemma":[0.3694473,0.000179852,0.6244805,0.000404275,0.00003877661,0.0003510918,0.001996029,0.001990844,0.001111286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006916138,"threshold_uncertainty_score":0.03657645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01918079054616061,"score_gpt":0.2707753826562442,"score_spread":0.2515945921100836,"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."}}