Metraipolis › archive › dc_6af48029ccfa

A Historical Corpus Is Not a Historical System: Auditing Hindsight Leakage in Stateful Data Discovery — arXiv:2609.12766

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12766
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:17.581Z
SHA-256 of the archived text
f290b0825d6ed05369ed31d96079ce58f74f3c00f923d9bc76d15433a70420a0
Stable URL of this page
https://metraipolis.com/documento/dc_6af48029ccfa

How to cite

A Historical Corpus Is Not a Historical System: Auditing Hindsight Leakage in Stateful Data Discovery — arXiv:2609.12766 — arXiv (en), https://arxiv.org/abs/2609.12766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6af48029ccfa (Metraipolis archive dc_6af48029ccfa, sha256 f290b0825d6ed05369ed31d96079ce58f74f3c00f923d9bc76d15433a70420a0)
BibTeX
@misc{dc6af48029ccfa,
  title = {A Historical Corpus Is Not a Historical System: Auditing Hindsight Leakage in Stateful Data Discovery — arXiv:2609.12766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6af48029ccfa; sha256 f290b0825d6ed05369ed31d96079ce58f74f3c00f923d9bc76d15433a70420a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Offline replay should estimate what a discovery system could retrieve at a historical point, yet freezing the corpus leaves interaction memory unconstrained. We formalize point-in-time (PIT) discovery through historical state $(D_t, \theta_t, M_{< i})$ and introduce a paired replay that changes only memory availability. The protocol constructs PIT and full-stream Future views from behavior-only traces and audits selected entries with a Temporal Violation Rate. Across three table-text domains, two stream regimes, two retrievers, and five seeds (216,000 rows), Future inflated Asset Recall@100 by 2.62-5.24 points; all 12 paired intervals excluded zero. With behavior-only trace memory, PIT underperformed the no-memory Stateless condition; Future masked 32.7-48.4% of that harm. For a simulated positive-feedback cache, PIT added 4.65-18.96 points over Stateless while Future added another 4.11-9.58 points. On five timestamped FreshStack topics, Future exceeded PIT by 2.72 points [1.75, 3.71]. Historical evaluation must version and validate memory with the corpus.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.12766 — 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 2026-10-16T03:44:07.304Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).