CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning Aug 14, 2026

Correct Is Not Governed: Provenance Integrity in Agentic Workflows

arXiv Security Archived Aug 14, 2026 ✓ Full text saved

arXiv:2608.12761v1 Announce Type: cross Abstract: Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the wrong authority, an unsupported completion claim, or work made stale by a later change. We define governed execution as work whose decisions, completion, and response to change are supported by inspectable provenance. We present Matrix, a deterministic causal-state layer that re

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Artificial Intelligence [Submitted on 13 Aug 2026] Correct Is Not Governed: Provenance Integrity in Agentic Workflows Jesus Salas Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the wrong authority, an unsupported completion claim, or work made stale by a later change. We define governed execution as work whose decisions, completion, and response to change are supported by inspectable provenance. We present Matrix, a deterministic causal-state layer that records authority and fact dependencies, verifies completion evidence, and selectively invalidates affected work. Across controlled comparisons, governed and direct workflows often reached the same outcomes, but only the governed path consistently preserved governing evidence, refused unsupported closure, and limited recovery to dependent tasks. A role-separated transfer challenge then failed: a deterministically enforced completeness contract severely over-blocked synthetic packets produced outside its authoring context. These results do not establish Matrix as a general accuracy enhancer; they support its primary role as an institutional integrity layer for making agentic work auditable and independently verifiable. Comments: 19 pages, 2 figures Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) Cite as: arXiv:2608.12761 [cs.AI]   (or arXiv:2608.12761v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2608.12761 Focus to learn more Submission history From: Jesus Salas [view email] [v1] Thu, 13 Aug 2026 03:12:13 UTC (58 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.CR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
    💬 Team Notes
    Article Info
    Source
    arXiv Security
    Category
    ◬ AI & Machine Learning
    Published
    Aug 14, 2026
    Archived
    Aug 14, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗