Metraipolis › archive › dc_320bddf34497

Whose record is this? Diagnosing and authorizing record use in personalized multimodal models — arXiv:2609.04801

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04801
License (as archived): CC0-1.0
Archived: 2026-10-16T22:20:55.534Z
SHA-256 of the archived text: 9c3247763a7d459d8ba7b8b69fb4d53059994f7219da023e5b7488d73493ccc6
Stable URL of this page: https://metraipolis.com/documento/dc_320bddf34497

How to cite

Whose record is this? Diagnosing and authorizing record use in personalized multimodal models — arXiv:2609.04801 — arXiv (en), https://arxiv.org/abs/2609.04801 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_320bddf34497 (Metraipolis archive dc_320bddf34497, sha256 9c3247763a7d459d8ba7b8b69fb4d53059994f7219da023e5b7488d73493ccc6)

BibTeX

@misc{dc320bddf34497,
  title = {Whose record is this? Diagnosing and authorizing record use in personalized multimodal models — arXiv:2609.04801},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04801},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_320bddf34497; sha256 9c3247763a7d459d8ba7b8b69fb4d53059994f7219da023e5b7488d73493ccc6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04801. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contextualized visual personalization can retrieve a true record yet apply it to the wrong visual subject. We formalize when a record may condition an answer as \emph{record authorization}: subject presence ($P$), record-edge validity ($E$), and answer support ($S$) must all hold. We call violations visual memory misbinding (VMM). We construct RecordAuth-Diag, a 3,690-case matched diagnostic suite that changes one image--record edge while holding the query, question, record text, and image multiset fixed. Card removal and nonce relabeling attribute these failures to supplied records. Raw-bank failures span Qwen-, Phi-, and Gemma-family interfaces: Gemma-3-4B-IT reaches 63.69\% local unauthorized use at 25.75\% clean recall. CoViP remains at 26.02\%, versus 22.49\% for its Qwen backbone at similar clean recall. Typed pre-generation authorization reduces Qwen card exposure on RecordAuth-Diag from 43.63\% to 3.06\%, while positive recall changes from 86.26\% to 60.90\%. Full $P\wedge E\wedge S$ validation uses 560 localized DAVIS cases: top-1 relevance and typed authorization have comparable release (28.93\% and 28.39\%) but 6.79\% and 0.89\% unsafe release, respectively. Of the 33 additional unsafe cases removed, 27 are support, 4 edge, 2 clean, and 0 boundary cases. Thus the observed increment is an $E\wedge S$ decision dominated by support, not an edge check alone. Appearance supplies $E$ evidence only conditional on $P$; authenticated subject tokens instantiate the missing presence witness as a sufficiency control. The claims concern the evaluated contracts, not natural prevalence, consent, or visual identity

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.04801 — 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 2026-10-16T22:18:11.392Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).