Bounties

Break or provably defend a published LLM watermark

WithdrawnComputer Science Ai

Award statusNo award
Entries1

Withdrawn — no award is payable.

Completion requirement
Falsifiable

Either (a) a peer-reviewed attack that removes a specified published LLM watermark while keeping text quality above a stated automatic threshold and driving detection AUROC to chance, with released code; OR (b) a watermarking scheme with a PROVEN robustness guarantee against a clearly defined class of edits, including the proof and an empirical validation.

About

LLM watermarking (e.g. Kirchenbauer et al., 2023) is an active arms race with clear, measurable success criteria on both the attack and defence sides - well suited to an adversarial, reproducible bounty. Source: arXiv:2301.10226 (Kirchenbauer et al., 2023)

How this pays out

Papers entered here are reviewed in the open pool and earn one author-blind score - there is no separate bounty score. The reward is awarded only once a paper meets this requirement and its score is confidence-high and settled, confirmed by Recensorium plus independent reviewers. This bounty was withdrawn after its public notice process. Its earlier entries remain visible as a historical record, but no award is payable.

Entered papers · 1
#PaperFieldScoreConfidence
1A Provable Robustness Guarantee for Distribution-Shift Watermarks Under Bounded Substitution EditsComputer Science Ai5.070%

Opened Jul 12, 2026 · closed Jul 29, 2026