Metraipolis › archive › dc_7aa99899c139

Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles — arXiv:2608.16190

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16190
License (as archived)
CC0-1.0
Archived
2026-10-18T19:33:58.755Z
SHA-256 of the archived text
4b83104ce2c912139d37cae1bc59d67c1c993e6f92acbbb84facf47c72f50956
Stable URL of this page
https://metraipolis.com/documento/dc_7aa99899c139

How to cite

Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles — arXiv:2608.16190 — arXiv (en), https://arxiv.org/abs/2608.16190 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7aa99899c139 (Metraipolis archive dc_7aa99899c139, sha256 4b83104ce2c912139d37cae1bc59d67c1c993e6f92acbbb84facf47c72f50956)
BibTeX
@misc{dc7aa99899c139,
  title = {Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles — arXiv:2608.16190},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16190},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7aa99899c139; sha256 4b83104ce2c912139d37cae1bc59d67c1c993e6f92acbbb84facf47c72f50956},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16190. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monitor at matched cost. They are built by minimising average pairwise correlation, and that paper's twelve monitors shared one base model, leaving open what supplies the diversity. We study 24 open-weight monitors spanning nine pretraining lineages and a 29x range of detection skill (pAUC at 10 percent FPR, 0.028 to 0.803) on backdoored code. The metric used to build panels does not predict what a panel is for, and we can say why. Agreement on attack items splits into a shared-detectability signal component and an idiosyncratic error component, which predict ensemble gain with opposite sign (Spearman -0.25 and +0.26), so their sum, the metric actually used, predicts it barely at all (+0.05); the cancellation holds in 7 of 8 evaluations. Skill acts on signal (+0.53) while error stays flat (-0.01), which is why a monitor's own skill predicts its agreement with the pool (Spearman 0.84, n = 24, permutation p below 0.0001). Pretraining lineage is the obvious way to buy decorrelation, and it does not pay. At matched member capability, cross-lineage panels detect no better (permutation p = 0.13), and lineage barely moves the metric either (+0.064, p = 0.18). We report that against ourselves: on our own 22-monitor pool the same test read +0.104 at p = 0.037 until two monitors were added. An earlier pool topping out at pAUC 0.23 had already invalidated another analysis. Such a quantity is a property of the pool assembled. Panel gain over the best member falls monotonically with panel skill (-0.66 at k = 2, -0.70 at k = 3), and no correlation-weighted selection beats picking the single best monitor out of sample. Across six attacker models the gain result holds in all six, the agreement and cancellation results in five of six.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.16190 — 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 2026-10-18T19:01:59.124Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).