Metraipolis › archive › dc_02c5aa42eb80
Two Conformal Constructions for Adaptive Within-Document AI-Text Screening — arXiv:2609.31547
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31547
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:04:18.056Z
- SHA-256 of the archived text
4a38dc320e49c0ec5aa4a6a3fe0a3bffeeb9308ce8801cfcc9b6c71402ab627d- Stable URL of this page
https://metraipolis.com/documento/dc_02c5aa42eb80
How to cite
Two Conformal Constructions for Adaptive Within-Document AI-Text Screening — arXiv:2609.31547 — arXiv (en), https://arxiv.org/abs/2609.31547 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02c5aa42eb80 (Metraipolis archive dc_02c5aa42eb80, sha256 4a38dc320e49c0ec5aa4a6a3fe0a3bffeeb9308ce8801cfcc9b6c71402ab627d)
BibTeX
@misc{dc02c5aa42eb80,
title = {Two Conformal Constructions for Adaptive Within-Document AI-Text Screening — arXiv:2609.31547},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31547},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02c5aa42eb80; sha256 4a38dc320e49c0ec5aa4a6a3fe0a3bffeeb9308ce8801cfcc9b6c71402ab627d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31547. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study false-alert control when screening for text generated by artificial intelligence (AI). The screening procedure selects document prefixes and detectors from observed evidence and may stop before exhausting its inspection budget. We give two finite-sample constructions under document-level exchangeability between human calibration documents and a new null document, with no restriction on dependence among tokens within a document. Construction A registers a finite family of prefix-detector scores and allocates a false-alert budget across their conformal ranks. A union bound protects any executed subset of that family. Construction B calibrates the complete-path maximum of a development-fixed adaptive policy. Each partial-path maximum is bounded by the complete maximum, so a terminal conformal rank protects early stopping without splitting the error budget. We prove marginal control of any false alert across the permitted inspection path and derive necessary calibration counts for rejection. We also state oracle testing, distribution-shift, and independent-audit bounds with their additional assumptions. Both constructions protect stopping within their specified scope; neither proof constructs an e-process or justifies multiplying conformal ranks. Detection power and computational savings remain questions for empirical evaluation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CL). Categorie arXiv: Methodology (stat.ME) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.31547 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:38:49.493Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).