[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-faster-way-to-catch-ai-code-plagiarism":10,"sections":40},{"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":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},11136,"a-faster-way-to-catch-ai-code-plagiarism","A Faster Way to Catch AI Code Plagiarism","A new hybrid search system traces AI-generated code snippets back to their original training examples without scanning billions of lines one by one.","A new search method can trace AI-written code snippets back to the exact training examples they came from, without scanning the entire training set each time.\n\nResearchers built SourceTracker, a 300-million-parameter encoder for code retrieval, and paired it with a two-stage pipeline called HybridSourceTracker (HST). HST first uses vector search to narrow a massive corpus down to a small set of candidate snippets, then re-ranks those candidates with Winnowing, a classical code-fingerprinting technique, to confirm exact matches. The team trained and evaluated the system on a 10M-snippet subset of TheStackV2, a dataset used to train code-generating LLMs, including snippets with renamed identifiers meant to mimic how people tweak copied code. In a separate in-vitro test using a smaller 100k-snippet search space, HST matched Winnowing's accuracy on 30-token fragments and beat it by up to 5.4% once fragments reached 60 tokens or longer, all while keeping query time logarithmic instead of linear.\n\nWinnowing-style fingerprint matching is accurate, but it checks a snippet against literally everything in the training set, which falls apart at the scale of modern code-LLM training data. HST's vector-search prefilter makes provenance checking plausible for billion-snippet corpora instead of just research-sized ones. That matters as more lawsuits and license disputes turn on whether a model's output counts as original work or a reproduction.\n\nThe catch: this only works if you can actually see what a model trained on, and most commercial code LLMs still will not disclose that, so the harder problem here is access, not math.","[\"ai\",\"code-generation\",\"plagiarism-detection\",\"open-source-licensing\"]","2026-10-09T04:00:00.000Z","2026-10-10T07:50:16.058Z","2026-10-10T07:50:20.391Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Fix the dataset mismatch in the body: the source says the 30-token\u002F60-token accuracy comparison (on-par then +5.4%) was measured on a 100k-snippet in-vitro search space, not on the 10M-snippet TheStackV2 subset as the draft currently states.","resolved","ai",[30,32,33,34],"code-generation","plagiarism-detection","open-source-licensing",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.28510",0,{"sections":41},[42,46,51,56,61,66,71,76,81,86,91,96,101,106],{"name":43,"slug":30,"count":44,"latest_published_at":45},"AI",6840,"2026-10-09T19:36:56.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Security","security",941,"2026-10-09T19:25:43.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",490,"2026-10-09T14:25:43.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Deals","deals",483,"2026-10-09T11:20:39.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Hardware","hardware",233,"2026-10-09T16:07:54.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Science","science",195,"2026-10-09T11:00:57.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Consumer Tech","consumer-tech",183,"2026-10-09T14:50:57.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",120,"2026-10-09T17:02:31.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Software","software",114,"2026-10-08T17:57:01.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Dev Tools","dev-tools",109,"2026-10-09T13:03:48.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"General","general",69,"2026-10-09T19:10:07.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"Gaming","gaming",59,"2026-10-09T11:43:43.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"Reviews","reviews",34,"2026-10-08T14:00:22.000Z",{"name":107,"slug":108,"count":109,"latest_published_at":110},"How-To","how-to",8,"2026-10-05T09:00:00.000Z"]