The Science of Certainty
K-Veritas seals each result to the code that produced it.
Official implementation of Computer Science Conferences Should Require Nonrepudiable Experimental Results (Keita and Homan, NeurIPS 2026 Position Paper Track).
Built for
Conferences
Check that submitted results came from the submitted code.
Journals
Reproducibility you can check, even when the data can't be shared.
Universities and research labs
A record of what researchers and students actually ran.
Benchmarks
Scores tied to the run that produced them, in any field of computing.
“What is written in the paper should be what was truly gotten from the experiments.”
Reports verified
Trusted by
