{"id":"W4415007625","doi":"10.1145/3763174","title":"AutoVerus: Automated Proof Generation for Rust Code","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Correctness; Mathematical proof; Debugging; Code (set theory); Proof of concept; Suite; Benchmark (surveying); Rust (programming language); Automated theorem proving","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":[0.0003197208,0.0001312901,0.0001512512,0.00009063027,0.0002102048,0.0002322517,0.00221354,0.00006799896,0.00000117208],"category_scores_gemma":[0.0008449892,0.00008665887,0.00007936863,0.0003953403,0.00004089536,0.0003227157,0.0009538286,0.00009312537,0.000001090654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003474515,"about_ca_system_score_gemma":0.00004027092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001396631,"about_ca_topic_score_gemma":0.000001781982,"domain_scores_codex":[0.9989992,0.000006082718,0.0002170779,0.0003351557,0.0002222823,0.0002201649],"domain_scores_gemma":[0.9989699,0.00006250889,0.0001862519,0.0005443842,0.0002084081,0.00002859163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004727316,0.0003768945,0.0009941664,0.0005102969,0.00009479608,8.00859e-7,0.001416385,0.00005602868,0.06628951,0.1717945,0.08059334,0.677826],"study_design_scores_gemma":[0.001170084,0.0003628742,0.001589627,0.0006695011,0.0000583426,0.000006664136,0.00039822,0.3448539,0.5750922,0.00680638,0.06858975,0.0004025074],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6565502,0.003559729,0.2688667,0.0389211,0.004429968,0.01177096,0.000198728,0.008548141,0.007154456],"genre_scores_gemma":[0.5025616,0.00000756883,0.4952793,0.0005018241,0.0001515251,0.0002803085,0.0000133539,0.00001846901,0.00118612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6774235,"threshold_uncertainty_score":0.4113345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02026451834181121,"score_gpt":0.3060811090185903,"score_spread":0.2858165906767791,"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."}}