Metraipolis › archive › dc_ddecc2e97465

Reciprocity Can Erase Direction:tructural Boundaries and Controlled Utility of Magnetic Graph Networks — arXiv:2611.04295

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04295
License (as archived)
CC0-1.0
Archived
2026-11-04T21:39:57.283Z
SHA-256 of the archived text
dc38e5bbec990fe08b728bdce0ba791ef9f296dc26ff10111a4f2fedb978d42f
Stable URL of this page
https://metraipolis.com/documento/dc_ddecc2e97465

How to cite

Reciprocity Can Erase Direction:tructural Boundaries and Controlled Utility of Magnetic Graph Networks — arXiv:2611.04295 — arXiv (en), https://arxiv.org/abs/2611.04295 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ddecc2e97465 (Metraipolis archive dc_ddecc2e97465, sha256 dc38e5bbec990fe08b728bdce0ba791ef9f296dc26ff10111a4f2fedb978d42f)
BibTeX
@misc{dcddecc2e97465,
  title = {Reciprocity Can Erase Direction:tructural Boundaries and Controlled Utility of Magnetic Graph Networks — arXiv:2611.04295},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04295},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ddecc2e97465; sha256 dc38e5bbec990fe08b728bdce0ba791ef9f296dc26ff10111a4f2fedb978d42f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04295. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Magnetic graph networks encode direction through phase, but a learned graph can erase the intended directional mechanism before prediction. We characterize this failure for support-based magnetic Laplacians. Exact identities relate imaginary energy and distance from zero phase to amplitude-weighted reciprocity. Top-$k$ selection forces complete collapse when the observed-node count satisfies $m\leq k+1$, and dense support imposes a lower bound on reciprocal-arc fraction. We then construct paired propagation examples with identical node features and symmetric amplitudes but opposite labels, giving a provable chance-level limit for direction-erasing representations. In 72 fixed neural fits, support phase achieved test AUROC 1.0000 on a unilateral ring but 0.5000 on reciprocal ring and complete supports; continuous score phase and a real directed comparator achieved 1.0000 throughout. All models solved the direction-free control. These are oracle-direction mechanism tests, not evidence of learned clinical direction. In the preserved public DeepDRiD development study, continuous phase was active but its robustness difference from zero phase was only $+0.0036$ (descriptive 95\% interval $-0.0014$ to $+0.0095$) on validation patients used for checkpoint selection. The contribution is a structural and experimental framework for distinguishing erased direction from unestablished task utility. It provides a precise circumstance in which magnetic phase preserves useful information, without asserting universal or clinical superiority.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04295 — 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 2026-11-04T21:35:49.659Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).