跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2605.28001 · v2

What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for Selection

首次提交 2026-05-27 13:52
版本更新 2026-11-07 01:01
雷达观测 2026-11-10 10:11
arXiv ↗PDF ↗

摘要

Certified inference-time copyright defences publish a divergence budget between the served model and a safe anchor trained without the protected works. We ask what such a budget certifies. Proved: a budget of K nats says nothing about a work whose surprisal under the anchor is at most K, at every Rényi order. Anchored decoding charges per token, so its budget grows with the output. Measured: at its authors' setting, the budget exceeds the anchor's surprisal of every one of the 758 protected passages we test, so it certifies nothing about them. Proved: serving one of n anchor draws, by any rule, is certified at log n nats for the whole output, at any length; in installments, a window is certified only given the text up to a block boundary. Measured: over a vetted anchor, with an adversarial scorer, selection reproduced no protected passage near-verbatim. Its draws cost 21.8x a metered decode on an anchor-only server. Judged: in the headline configuration, at the only published meter budget that bounds a 50-token window, selection's gain over one anchor draw is reliably positive and the meter's is, by a post-hoc equivalence test, zero. At matched compute selection loses. At the authors' sampling settings on the 8B, the two tie at that budget. Where the meter's certificate is vacuous, the ranking depends on how the stronger model is served. It reverses under a chat template, at the authors' sampling settings on the 8B, and on AlpacaEval.

作者备注:66 pages (13 main text), 6 figures, 45 tables. v2: substantially revised and extended, with a new title and new results; supersedes v1. Code: https://github.com/Vijayavallabh/DA5001_Project

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-07 01:01 · 最新观测版本

What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for Selection

Certified inference-time copyright defences publish a divergence budget between the served model and a safe anchor trained without the protected works. We ask what such a budget certifies. Proved: a budget of K nats says nothing about a work whose surprisal under the anchor is at most K, at every Rényi order. Anchored decoding charges per token, so its budget grows with the output. Measured: at its authors' setting, the budget exceeds the anchor's surprisal of every one of the 758 protected passages we test, so it certifies nothing about them. Proved: serving one of n anchor draws, by any rule, is certified at log n nats for the whole output, at any length; in installments, a window is certified only given the text up to a block boundary. Measured: over a vetted anchor, with an adversarial scorer, selection reproduced no protected passage near-verbatim. Its draws cost 21.8x a metered decode on an anchor-only server. Judged: in the headline configuration, at the only published meter budget that bounds a 50-token window, selection's gain over one anchor draw is reliably positive and the meter's is, by a post-hoc equivalence test, zero. At matched compute selection loses. At the authors' sampling settings on the 8B, the two tie at that budget. Where the meter's certificate is vacuous, the ranking depends on how the stronger model is served. It reverses under a chat template, at the authors' sampling settings on the 8B, and on AlpacaEval.

查看此版本解读 →查看此版本原文 ↗