[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-axdafny-pushes-verified-code-generation-to-927":10,"sections":44},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":34,"tags":35,"sources":39,"feedback":43,"feedback_at":22,"cost_usd":43,"total_tokens":43},3054,"axdafny-pushes-verified-code-generation-to-927","AxDafny Pushes Verified Code Generation to 92.7%","A verifier-guided repair framework beats prior Dafny benchmarks by 6.5 points, using a model the paper names GPT-5.5 as its baseline.","A new agentic framework called AxDafny hits 92.7% verification success on DafnyBench, outpacing the previous best proof-hint baseline by 6.5 percentage points.\n\nResearchers built AxDafny as a repair loop: a model generates code, then iteratively patches the formal proof artifacts — invariants, assertions, termination arguments — until a verifier signs off or gives up. To stress-test it, they also produced a new benchmark, LiveCodeBench-Pro-Dafny, which translates 250 competition-style programming problems into Dafny with formal specifications and a verifier-based evaluation harness. The paper identifies GPT-5.5 as the baseline model — that name is taken directly from the arXiv abstract and has not been independently confirmed as a public release. On both benchmarks, AxDafny substantially improves over that baseline.\n\nThe result matters because Dafny is one of the few languages where a compiler can actually *prove* code correct, not just test it — and getting AI to produce those proofs reliably has been a hard open problem. A 92.7% success rate, if it holds on independent evaluation, is the kind of number that makes formal verification look less like a research curiosity and more like something teams might actually ship.\n\nThe paper's own caveat is worth keeping: verification success and runtime test performance measure different things, which is a polite way of saying a formally verified program can still be wrong in ways the spec didn't anticipate.","[\"ai\",\"formal-verification\",\"code-generation\",\"benchmarks\"]","2026-07-01T04:00:00.000Z","2026-07-01T06:06:22.799Z","2026-07-01T06:06:25.519Z","published",null,[24,30],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"The dek and body reference GPT-5.5, which is not a publicly confirmed model release and must be removed or replaced with the exact model identifier as confirmed in a public source before this can publish.","resolved",{"id":31,"reviewer":26,"round":32,"reason":33,"status":29},"editor-r2",2,"The body omits the source's explicit mention of GPT-5.5 as the baseline model, which is the only reason [editor-r1] was raised — but the concern is still open because GPT-5.5 is not a publicly confirmed model release; the article must either replace it with a confirmed model identifier or explicitly note the model name as stated in the arXiv abstract without endorsing it as a verified release.","ai",[34,36,37,38],"formal-verification","code-generation","benchmarks",[40],{"name":41,"url":42},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.32007",0,{"sections":45},[46,50,55,60,65,70,75,80,85,90,95,99,104,109],{"name":47,"slug":34,"count":48,"latest_published_at":49},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":96,"slug":97,"count":93,"latest_published_at":98},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":105,"slug":106,"count":107,"latest_published_at":108},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":110,"slug":111,"count":112,"latest_published_at":113},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]