Metraipolis › archive › dc_f22abb68eb07

What Changed? Drift Detection with Real, Virtual, and Incomparable Diagnosis — arXiv:2609.27865

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.27865
License (as archived): CC0-1.0
Archived: 2026-10-08T09:13:05.507Z
SHA-256 of the archived text: 0ddfc7f3dfa37a28ac1606d274347bf715cb4ec2071b1bce202e08a448223353
Stable URL of this page: https://metraipolis.com/documento/dc_f22abb68eb07

How to cite

What Changed? Drift Detection with Real, Virtual, and Incomparable Diagnosis — arXiv:2609.27865 — arXiv (en), https://arxiv.org/abs/2609.27865 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f22abb68eb07 (Metraipolis archive dc_f22abb68eb07, sha256 0ddfc7f3dfa37a28ac1606d274347bf715cb4ec2071b1bce202e08a448223353)

BibTeX

@misc{dcf22abb68eb07,
  title = {What Changed? Drift Detection with Real, Virtual, and Incomparable Diagnosis — arXiv:2609.27865},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27865},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f22abb68eb07; sha256 0ddfc7f3dfa37a28ac1606d274347bf715cb4ec2071b1bce202e08a448223353},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27865. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sharing a deep encoder does not, by itself, fix the central confound of task-comparison scores. We show that cross-evaluated heads on a frozen shared representation inherit the extrapolation confound of shallow exchange scores: pure input rotations with fixed labels inflate a deep exchange score from about 0 to 0.80, while representation-novelty scores are blind in the complementary direction (flat under label permutations that change the task completely). Transplanting a conditional two-discriminator discrepancy into the embedding space resolves both blind spots: the functional axis stays within +-0.001 under rotations and tracks label-permutation drift mass monotonically. Built into a mixture-of-heads lifecycle, the two-axis gate attains better decision quality with fewer heads than exchange or novelty triggers at a matched training budget. On generalized category discovery, the same chunk-level functional axis separates semantic novelty from photometric shift with AUROC 0.98-0.99 where per-input OOD scores (MSP, Energy, Mahalanobis, KNN) sit near chance for that distinction. All findings replicate across frozen ImageNet-21k ViT-B/16 and self-supervised DINOv2 backbones on CIFAR-100, and extend to residual adapter pools with recurrence, where a null-calibrated novelty trigger never fires on mechanism changes while the two-axis gate handles them with full recurrence reuse. We state explicitly the common-factoring condition under which embedding-space conclusions transfer to the original mechanism.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.27865 — 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 2026-10-08T08:13:26.723Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).