Metraipolis › archive › dc_9afdba6d08be
Attraction-Ranking Mismatch in Out-of-Distribution Detection: Theory and Evidence from Hamiltonian Feature Dynamics — arXiv:2611.06021
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06021
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:22:06.749Z
- SHA-256 of the archived text
c80d5ee8df6a661492339a45dfe966139535c0aa379982203d2801a08fc8ebec- Stable URL of this page
https://metraipolis.com/documento/dc_9afdba6d08be
How to cite
Attraction-Ranking Mismatch in Out-of-Distribution Detection: Theory and Evidence from Hamiltonian Feature Dynamics — arXiv:2611.06021 — arXiv (en), https://arxiv.org/abs/2611.06021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9afdba6d08be (Metraipolis archive dc_9afdba6d08be, sha256 c80d5ee8df6a661492339a45dfe966139535c0aa379982203d2801a08fc8ebec)
BibTeX
@misc{dc9afdba6d08be,
title = {Attraction-Ranking Mismatch in Out-of-Distribution Detection: Theory and Evidence from Hamiltonian Feature Dynamics — arXiv:2611.06021},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06021},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9afdba6d08be; sha256 c80d5ee8df6a661492339a45dfe966139535c0aa379982203d2801a08fc8ebec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Attracting features toward learned in-distribution (ID) regions is an intuitive strategy for out-of-distribution (OOD) detection, but does such attraction improve detection? We investigate this question using class-conditioned Hamiltonian dynamics as a controlled testbed and identify an attraction-ranking mismatch: improving individual class-affinity scores need not improve the relative ordering of ID and OOD samples. Our analysis separates misalignment between the driving field and the detection score from ranking failure that persists even when they are aligned. An exact AUROC decomposition and a local boundary analysis identify relative score changes at the ID-OOD ranking boundary as the source of first-order AUROC change under regularity conditions. Experiments demonstrate that a score-aligned rule can improve performance on a held-out source validation split yet consistently degrade it after transfer, even without a single winning-class change. A separate perturbation study finds that near-boundary relative score changes track the direction of small AUROC changes in the tested settings. Finally, centroid approximation and shared scales connect the zero-step score to a static centroid family that includes the existing CTM detector. Together, these results explain why class attraction is insufficient to justify feature refinement and motivate evaluating its effect on the ranking boundary. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2611.06021 — 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 2026-11-05T18:15:49.009Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).