Metraipolis › archive › dc_e7bc3feda210

NovaFabric: Tamper-Evident, Replayable Evidence for Autonomous AI Agent Runs — arXiv:2609.12582

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12582
License (as archived): CC0-1.0
Archived: 2026-10-16T03:08:41.233Z
SHA-256 of the archived text: f0c7500bf8aec455894a2c2dff24df365c1bfb77fed1ac152c574a454d7b96b3
Stable URL of this page: https://metraipolis.com/documento/dc_e7bc3feda210

How to cite

NovaFabric: Tamper-Evident, Replayable Evidence for Autonomous AI Agent Runs — arXiv:2609.12582 — arXiv (en), https://arxiv.org/abs/2609.12582 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e7bc3feda210 (Metraipolis archive dc_e7bc3feda210, sha256 f0c7500bf8aec455894a2c2dff24df365c1bfb77fed1ac152c574a454d7b96b3)

BibTeX

@misc{dce7bc3feda210,
  title = {NovaFabric: Tamper-Evident, Replayable Evidence for Autonomous AI Agent Runs — arXiv:2609.12582},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12582},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e7bc3feda210; sha256 f0c7500bf8aec455894a2c2dff24df365c1bfb77fed1ac152c574a454d7b96b3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12582. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When an autonomous AI agent does something consequential, what can be proven about what it did? Agent-observability platforms capture traces, but a trace is mutable: alterable undetected, with no recipe for re-executing it, silent on whether captured secrets were removed. Regulation (EU AI Act, ISO 42001, NIST AI RMF) presumes records an independent party can check. We present NovaFabric, producing audit-grade execution evidence: provider-neutral, tamper-evident, replayable, shareable. It records an agent run, without modifying agent logic, into a portable Run Capsule (fifteen-entity schema), sealed with a holistic DSSE signature, RFC 3161 timestamp, Merkle log and redaction attestation. Sealed runs are re-executable under a four-mode replay protocol and exportable as an Evidence Bundle for third-party verification with stock tooling (specified, not evaluated). The contribution is integration, not new cryptography: OpenTelemetry, DSSE/in-toto and W3C PROV. We evaluate eight research questions at measured scope. Mocked replay serves every model response from the capsule (no live model call, 10/10) but is offline w.r.t. models, not the network; only 2/10 tool-using workloads completed; the gap is missing tool-response substitution. Tampering is rejected across three tested classes. Declared-stream completeness is 0.652 (95% CI +/-0.064, ten scenarios). A repaired rule pack redacts 14/14 credential types, preserving 9/9 decoys; diff localises 140/140 mutations. Blast-radius queries: 45.5ms p99 over 10M edges (3.3x faster than a columnar baseline), 167.9ms over 100M (1 client, n=30). A 314-machine, ten-region run finds capsule REST ingest lossless but capped at 61.6 req/s (p99 26.8s) by per-worker serialisation. Six defects found in NovaFabric and its evaluation corpus: four fixed, one withdrawn, one open. Verification is conditional on a stated trusted computing base.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-14 in cs.DC).
Categorie arXiv: Cryptography and Security (cs.CR) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.12582 — 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 2026-10-16T03:03:05.104Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).