{"id":"W3172592804","doi":"10.3929/ethz-b-000489720","title":"Formally Validating a Practical Verification Condition Generator (extended version)","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Correctness; Soundness; Computer science; Programming language; Generator (circuit theory); Certificate; Implementation; Transformation (genetics); Control flow; Debugging; Theoretical computer science","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":[0.005768765,0.001070328,0.0004807019,0.0007460745,0.0006289836,0.002894519,0.001842962,0.001904458,0.04063356],"category_scores_gemma":[0.01737302,0.0008996462,0.001261579,0.0004852779,0.002496925,0.003461716,0.002360459,0.002562729,0.01072291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000970153,"about_ca_system_score_gemma":0.002774771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002571048,"about_ca_topic_score_gemma":0.002300225,"domain_scores_codex":[0.996342,0.0009267909,0.0003347131,0.0008886669,0.001028599,0.0004792741],"domain_scores_gemma":[0.9866296,0.00606762,0.0005486445,0.004599383,0.001995482,0.0001592145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001487158,0.0005909048,0.005363968,0.002224199,0.0001754102,0.002061152,0.001950534,0.07417049,0.0835067,0.448079,0.07379697,0.3065937],"study_design_scores_gemma":[0.0006917614,0.0007189793,0.001775453,0.0004530474,0.0001728531,0.002306008,0.0001888005,0.2309848,0.2110978,0.1468373,0.4044967,0.0002764946],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007060407,0.0000831849,0.960422,0.0005230276,0.0002094567,0.0004877789,0.001134792,0.02202008,0.008059263],"genre_scores_gemma":[0.2688269,0.0002585689,0.6991039,0.0008334389,0.0002031275,0.0008644416,0.003401091,0.005038571,0.02146997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04063356,"threshold_uncertainty_score":0.1359328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1001160946931149,"score_gpt":0.2374576539762914,"score_spread":0.1373415592831765,"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."}}