Metraipolis › archive › dc_0cc8daf0cc98

Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives — arXiv:2609.17572

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17572
License (as archived)
CC0-1.0
Archived
2026-10-15T15:04:19.726Z
SHA-256 of the archived text
ad2ea3a2e5d9dec88674d8c8934ac42c2d13038a992a0317a8e2d8c3be4e27aa
Stable URL of this page
https://metraipolis.com/documento/dc_0cc8daf0cc98

How to cite

Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives — arXiv:2609.17572 — arXiv (en), https://arxiv.org/abs/2609.17572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0cc8daf0cc98 (Metraipolis archive dc_0cc8daf0cc98, sha256 ad2ea3a2e5d9dec88674d8c8934ac42c2d13038a992a0317a8e2d8c3be4e27aa)
BibTeX
@misc{dc0cc8daf0cc98,
  title = {Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives — arXiv:2609.17572},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17572},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0cc8daf0cc98; sha256 ad2ea3a2e5d9dec88674d8c8934ac42c2d13038a992a0317a8e2d8c3be4e27aa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Auditing vision-language models (VLMs) for societal bias requires distinguishing direct algorithmic valuation disparities from confounders embedded within archival metadata. In this study, we audit Contrastive Language-Image Pretraining (CLIP) models using historical artwork metadata from the Metropolitan Museum of Art Open Access collection (N = 1,500 total objects; N = 743 attributed works: Male n = 534, Female n = 209; n = 618 anonymous). We establish a quantitative audit framework evaluating zero-shot CLIP logit differential scores across three semantic prompt pairs (masterpiece, quality, and influence). Unadjusted evaluations demonstrate high score convergence without a statistically significant main gender effect under OpenAI CLIP (mu_F = -0.0067 vs mu_M = -0.0035, p = 0.1829) or OpenCLIP (mu_F = 0.0171 vs mu_M = 0.0237, p = 0.1224). Two One-Sided Tests (TOST) confirm statistical equivalence across Cohen's d >= 0.25 bounds (pTOST < 0.005). Multivariate OLS regression controlling for artwork medium, creation era, and aspect ratio (R^2 < 0.02) confirms that artist gender has no statistically significant conditional effect (p > 0.20). High residual embedding variance (R^2 < 2%) indicates that global zero-shot valuation metrics operate near an embedding noise floor, showing that broad zero-shot prompt logit differentials are a coarse measurement instrument rather than proving absolute model fairness. We highlight two key caveats: (i) macro-level score equivalence reflects metric insensitivity to fine-grained visual-semantic features and does not preclude localized micro-level visual biases, and (ii) excluding 41.2% unattributed holdings reflects institutional survival bias. These results demonstrate the necessity of multivariate confound control, equivalence testing, and archival provenance auditing when assessing AI fairness in cultural heritage collections.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.17572 — 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 2026-10-15T14:08:19.047Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).