ModelTrace: open-source tool fingerprints LLMs with 3 long-integer challenges
scaling01 · x · 2026-10-18
ModelTrace (1.7k stars, MIT) is a locally-run active model attribution tool that identifies which family and version a model belongs to. It extracts output fingerprints via three independent long-integer generation challenges and matches them against a unified candidate bank. Supports manual testing (paste outputs) or automated API testing (auto-tries OpenAI Chat Completions and Anthropic Messages formats). Users can build fingerprint banks, and a static GitHub Pages version runs attribution entirely in-browser; API keys are never written to disk.
More from Research
- Optimus launches: an autonomous RL agent harness that runs experiments itself — _AustinCalvert_ · 2026-10-18
- Fields Medalist Timothy Gowers: one-shotting a proof with ChatGPT means we don't understand it — haider1 · 2026-10-18
- NVIDIA to present CANTO: tokenizing CAD geometry for aerodynamics prediction — JeanKossaifi · 2026-10-18
- NeurIPS 2026 journal track: 88 papers, ASU's "Beyond Semantics" among TMLR picks — karthikv792 · 2026-10-18
- Papers with Code adds Auto-Research category, 166 papers already tracked — NielsRogge · 2026-10-18
- Judea Pearl dubs it the 'Ladder of Understanding': correlation alone isn't comprehension — yudapearl · 2026-10-18