Computer Science Conferences Should Require Nonrepudiable Experimental Results

TL;DR

The paper advocates for requiring tamper-evident, nonrepudiable attestations of experimental results in computer science conferences to ensure integrity and verifiability of reported data.

Contribution

It formally defines the experiment nonrepudiation problem, proposes security properties, and introduces K-Veritas, a prototype system for nonrepudiable result reporting.

Findings

K-Veritas produces signed reports without accessing training data.

Current methods rely on self-reporting and optional code sharing, which are insufficient.

The paper calls for community standards for nonrepudiable experimental results.

Abstract

This position paper argues that computer science conferences should require tamper-evident, nonrepudiable attestations of experimental results. We name the underlying problem experiment nonrepudiation: a compliant protocol must bind the numbers in a paper to an actual executed computation in a way the author cannot later alter or deny. The current system relies on self-reported checklists, optional code sharing, and author-controlled logging. None of these mechanisms answer the question a reviewer cannot check: did the code the paper describes produce the numbers the paper reports? We define the problem formally, state the security properties any compliant protocol must satisfy, and describe a threat model that includes attacks current approaches do not prevent. To show that the problem is solvable, we built K-Veritas, a reference implementation in Go that produces signed reports without accessing training data. K-Veritas is a testbed, not a finished answer. We call on conferences and the community to treat nonrepudiation as a first-class requirement and to help build an open, independent standard for it.