Metraipolis › archive › dc_b4e04de778f7
One Mistake, Three Layers: Persistence Rules Under Depth Correlation — arXiv:2611.03968
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03968
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:50:54.395Z
- SHA-256 of the archived text
55b5097c9cc5c87b05f36bd53cb43d9bf68016e3e06b7578dc536e682bb2998f- Stable URL of this page
https://metraipolis.com/documento/dc_b4e04de778f7
How to cite
One Mistake, Three Layers: Persistence Rules Under Depth Correlation — arXiv:2611.03968 — arXiv (en), https://arxiv.org/abs/2611.03968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b4e04de778f7 (Metraipolis archive dc_b4e04de778f7, sha256 55b5097c9cc5c87b05f36bd53cb43d9bf68016e3e06b7578dc536e682bb2998f)
BibTeX
@misc{dcb4e04de778f7,
title = {One Mistake, Three Layers: Persistence Rules Under Depth Correlation — arXiv:2611.03968},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03968},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b4e04de778f7; sha256 55b5097c9cc5c87b05f36bd53cb43d9bf68016e3e06b7578dc536e682bb2998f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Probing frozen representations layer by layer is now standard practice, but reporting when a signal first becomes decodable requires a rule for reading a depth curve, and the obvious rule is wrong. On synthetic curves with known ground truth, requiring a probe score to exceed a null-calibrated threshold for three consecutive stages reports an onset nineteen stages early under transformer-like depth correlation, with every resample returning an onset. The failure follows from correlation between neighboring layers, a hazard known in neuroimaging but not, to our knowledge, checked for depth curves. We give an estimator whose error rate is calibrated rather than assumed. Null trajectories are built by permuting labels within each evaluation unit and holding each permutation fixed across depth, preserving the correlation structure the rule must survive; thresholds are per-layer order statistics; and the persistence requirement is calibrated rather than chosen. Applied to pocket information in a frozen co-folding trunk, stratifying 1,820 post-cutoff targets by protein-family and pocket familiarity, the five-stage rule fires on 4 to 7 per cent of null trajectories against a nominal 5 per cent and the three-stage rule on 12 to 17: the synthetic failure reproduces on real data. Pocket membership is decodable above threshold at all 48 blocks in all four regimes, so the onset cannot discriminate them; the pre-declared accumulation depth does, and is latest for familiar families with structurally novel pockets in every feature set. That regime is also the weakest, by a margin surviving controls for length, pocket measure and alignment depth. Separately, a widely used public co-folding checkpoint loads against its own code with 128 trunk parameters missing; those would be randomly initialized, and every representation extracted would be partly noise while appearing normal. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2611.03968 — 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 2026-11-04T21:38:49.685Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).