# Ideal Attribution and Faithful Watermarks for Language Models

arXiv: https://arxiv.org/abs/2512.07038 · HTML: https://mlsanity.com/paper/2512.07038/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 16 of 16)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Undetectable Watermarks for Language Models](https://mlsanity.com/paper/2306.09194/) (2023)
- [On the Reliability of Watermarks for Large Language Models](https://mlsanity.com/paper/2306.04634/) (2023)
- [Game-theoretic statistics and safe anytime-valid inference](https://mlsanity.com/paper/2210.01948/) (2022)
- [A Survey of Text Watermarking in the Era of Large Language Models](https://mlsanity.com/paper/2312.07913/) (2023)
- [Human heuristics for AI-generated language are flawed](https://mlsanity.com/paper/2206.07271/) (2022)
- [An Undetectable Watermark for Generative Image Models](https://mlsanity.com/paper/2410.07369/) (2024)
- [Publicly-Detectable Watermarking for Language Models](https://mlsanity.com/paper/2310.18491/) (2023)
- [Pseudorandom Error-Correcting Codes](https://mlsanity.com/paper/2402.09370/) (2024)
- [SynthID-Image: Image watermarking at internet scale](https://mlsanity.com/paper/2510.09263/) (2025)
- [Watermarking Language Models for Many Adaptive Users](https://mlsanity.com/paper/2405.11109/) (2024)
- [Ideal Pseudorandom Codes](https://mlsanity.com/paper/2411.05947/) (2024)

## Built on by (most cited first, 1 of 1)

- [Watermark Forensics for Generative Models: An Information-Theoretic Perspective](https://mlsanity.com/paper/2607.13003/) (2026)

## Abstract (arXiv)

We introduce ideal attribution mechanisms, a formal abstraction for reasoning about attribution decisions over strings. At the core of this abstraction lies the ledger, an append-only log of the prompt-response interaction history between a model and its user. Each mechanism produces deterministic decisions based on the ledger and an explicit selection criterion, making it well-suited to serve as a ground truth for attribution. We frame the design goal of watermarking schemes as faithful representation of ideal attribution mechanisms. This novel perspective brings conceptual clarity, replacing piecemeal probabilistic statements with a unified language for stating the guarantees of each scheme. It also enables precise reasoning about desiderata for future watermarking schemes, even when no current construction achieves them, since the ideal functionalities are specified first. In this way, the framework provides a roadmap that clarifies which guarantees are attainable in an idealized setting and worth pursuing in practice.