Metraipolis › archive › dc_594af094fc38

Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate — arXiv:2608.16621

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16621
License (as archived)
CC0-1.0
Archived
2026-10-18T17:45:09.866Z
SHA-256 of the archived text
7431a140c23a0fcc1a0cbd929ea4212912b59803dd5c7e9716cd4c7166e09339
Stable URL of this page
https://metraipolis.com/documento/dc_594af094fc38

How to cite

Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate — arXiv:2608.16621 — arXiv (en), https://arxiv.org/abs/2608.16621 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_594af094fc38 (Metraipolis archive dc_594af094fc38, sha256 7431a140c23a0fcc1a0cbd929ea4212912b59803dd5c7e9716cd4c7166e09339)
BibTeX
@misc{dc594af094fc38,
  title = {Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate — arXiv:2608.16621},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16621},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_594af094fc38; sha256 7431a140c23a0fcc1a0cbd929ea4212912b59803dd5c7e9716cd4c7166e09339},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16621. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time. Put plainly, instead of re-deriving what a corpus means on every question, the work is done once when a document arrives and is thereafter merely consulted -- a compiler, not an interpreter, of meaning. An alternative is to compile that meaning once, at ingest time, into a compact, queryable semantic substrate and maintain it as the corpus evolves. The central objection is maintenance cost: rebuilding a truncated singular value decomposition (SVD) on every change appears prohibitive, and a change of embedding model seems to force a full re-embedding. We argue and show empirically that maintenance cost scales with the amount of change, not corpus size. On a controlled synthetic pilot (dimension 256, rank 32, a corpus grown from 3,000 to 9,000 documents over 50 update events), incremental low-rank updates were 33.7 times cheaper per update than full re-SVD and 23.8 times cheaper cumulatively, while the incremental subspace tracked the full recomputation to within floating-point precision (maximum principal-angle drift below 1e-11 degrees; recall@10 = 1.0). An orthogonal Procrustes virtual axis update recovered 0.95 mean cosine to truly re-embedded vectors by re-embedding only about 10 percent of the corpus. The results support maintaining, rather than repeatedly reconstructing, a semantic substrate.

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); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.16621 — 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 2026-10-18T16:29:13.883Z 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).