Metraipolis › archive › dc_7a2d594533e5

Quipu: A Governed Bitemporal Knowledge Graph Store — arXiv:2608.16813

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16813
License (as archived)
CC0-1.0
Archived
2026-10-18T17:47:26.214Z
SHA-256 of the archived text
8a7257f640bd498486e224afd27a9b7d057f30f3d16a2ff929eecacdcc05f79c
Stable URL of this page
https://metraipolis.com/documento/dc_7a2d594533e5

How to cite

Quipu: A Governed Bitemporal Knowledge Graph Store — arXiv:2608.16813 — arXiv (en), https://arxiv.org/abs/2608.16813 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a2d594533e5 (Metraipolis archive dc_7a2d594533e5, sha256 8a7257f640bd498486e224afd27a9b7d057f30f3d16a2ff929eecacdcc05f79c)
BibTeX
@misc{dc7a2d594533e5,
  title = {Quipu: A Governed Bitemporal Knowledge Graph Store — arXiv:2608.16813},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16813},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a2d594533e5; sha256 8a7257f640bd498486e224afd27a9b7d057f30f3d16a2ff929eecacdcc05f79c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16813. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or none, treat every writer's facts as equally trustworthy, and leave governance to dashboards and middleware. These four defaults are individually convenient and jointly untenable under agent workloads. We present Quipu, an embeddable store that inverts all four: no fact enters except through a gate whose predicates evaluate the pending post-state; data, trust labels, verdicts, and the rules themselves are bitemporal; named graphs are the unit of authority and trust, composed under a lattice whose one invariant is that composition never widens; and the governance specification $\Sigma$, the trace, and signed verdicts are facts in the store they govern, making the audit $T \models \Sigma$ a query. We evaluate with Census, a deterministic multi-writer lifecycle whose single seeded run scores every research question against planted ground truth: the gated store ends with 0 of 6 planted defects versus 6 of 6 ungated; all 7 composition probes uphold the lattice contract; 50 of 50 satisfied verdicts re-derive faithfully as of their instant while all 50 would be misreported under a latest-only rule set; and the SARC reference checker agrees with the in-store audit verdict-for-verdict, differing only on coverage semantics. A recorded trace from a governed writer surfaces a live enforcement gap the audit names with its remediation. On DEMM-Bench, an external decision-evidence sufficiency benchmark, a content-only reading of the exported records answers all 512 property-level governance questions correctly with zero overclaim under all eight degradation conditions, while container-presence baselines overclaim on up to 87.5% of them -- and the run surfaced, and led us to close, a gap in what a denial's verdict attests.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.16813 — 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 2026-10-18T16:29:13.893Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).