Metraipolis › archive › dc_e33da19adcdf

Assay: Claims That Decay With the Code. Content-Addressed Evidence Graphs for Accountable AI-Assisted Software Delivery — arXiv:2609.36170

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36170
License (as archived)
CC0-1.0
Archived
2026-10-07T17:58:59.882Z
SHA-256 of the archived text
c0d0e3130b121f0b113f41520df1791424dee850b5854db5e2474f60f0e2ee57
Stable URL of this page
https://metraipolis.com/documento/dc_e33da19adcdf

How to cite

Assay: Claims That Decay With the Code. Content-Addressed Evidence Graphs for Accountable AI-Assisted Software Delivery — arXiv:2609.36170 — arXiv (en), https://arxiv.org/abs/2609.36170 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e33da19adcdf (Metraipolis archive dc_e33da19adcdf, sha256 c0d0e3130b121f0b113f41520df1791424dee850b5854db5e2474f60f0e2ee57)
BibTeX
@misc{dce33da19adcdf,
  title = {Assay: Claims That Decay With the Code. Content-Addressed Evidence Graphs for Accountable AI-Assisted Software Delivery — arXiv:2609.36170},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36170},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e33da19adcdf; sha256 c0d0e3130b121f0b113f41520df1791424dee850b5854db5e2474f60f0e2ee57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36170. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI coding agents fail in two coupled ways. They spend most of their context window rediscovering where things live, and they assert success without evidence when the work gets hard. Repository indexes address the first with cheap context, and orchestration frameworks with adversarial review address the second with accountability. Both describe the same object, the structure of the codebase, at two timescales: what is true of the code now, and what was verified to be true, at which revision, by whom. Assay makes that observation operational. Every claim an agent makes (tests pass, no secrets, behavior preserved) is bound to the Merkle hash of the dependency cone of the code it covers, so the claim is stale exactly when that code or anything it depends on changes. We show the binding is sound and minimal, and that the blast radius of a change is precisely the set of claims it invalidates. On the graph we place a risk-proportional evidence obligation, a bounded review protocol with separation of duties, and a merge gate that consults no model: coverage, freshness, signatures, exit codes, plausibility, evidence monotonicity (the mechanical form of "do not delete the failing test"), and review status. Assay is a dependency-free Python tool with an MCP server. On five public repositories a 600-token brief costs 14x to 114x less than an exploration proxy, warm rebuilds are up to 5x faster than cold ones, cone binding re-verifies 7.9% to 81.9% of claims where repository binding re-verifies all of them while per-module binding misses 23% to 68% of required invalidations, and the gate blocks 9 of 9 scripted adversarial behaviours while admitting the honest ones. Every number in this paper is generated by the released scripts.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-30 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.36170 — 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 2026-10-07T17:31:51.995Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).