Metraipolis › archive › dc_c57d33ef024b

Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own… — arXiv:2610.32245

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.32245
License (as archived): CC0-1.0
Archived: 2026-10-26T19:50:31.002Z
SHA-256 of the archived text: 55f66feaa40a43a0ce02be9350ac92a5023b3c5f67aac00234a015462126a93f
Stable URL of this page: https://metraipolis.com/documento/dc_c57d33ef024b

How to cite

Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own… — arXiv:2610.32245 — arXiv (en), https://arxiv.org/abs/2610.32245 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c57d33ef024b (Metraipolis archive dc_c57d33ef024b, sha256 55f66feaa40a43a0ce02be9350ac92a5023b3c5f67aac00234a015462126a93f)

BibTeX

@misc{dcc57d33ef024b,
  title = {Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own… — arXiv:2610.32245},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32245},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c57d33ef024b; sha256 55f66feaa40a43a0ce02be9350ac92a5023b3c5f67aac00234a015462126a93f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32245. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI systems that discover scientific relations now generate candidate "laws" at scale, but the bottleneck has shifted from generation to vetting: which candidates deserve belief? We show that a deployed self-improving science agent - one that has admitted 252 relations through held-out prediction courts - already computes the quantity that answers this question: the Minimum Description Length compression ratio used for model selection doubles, when read under discrete accounting, as an unsupervised epistemic grader. The compression-ranked top band of the agent's ledger recovers exactly the canonical laws among its discoveries (vis-viva across seven planets, Balmer/Rydberg) plus cross-measurement identities - enrichment $p=3.6\times10^{-12}$ under a hypergeometric test - with zero counterexamples and physically coherent band structure. The same lens retroactively reveals that 86% of the ledger compresses nothing ($\mathrm{cr}\approx 1$): the agent had been recording statistical regularities, including a learned predictor with held-out $R^2=0.541$ admitted through the prediction gate, under a narrative of compression as the unified value of knowledge - a narrative that was never true for them. We formalize the resulting dual-axis bookkeeping - prediction value ($R^2$) and compression value (cr) as nearly decoupled axes of knowledge - demonstrate its robustness to quantization, and register forward falsifiable predictions. The episode is, to our knowledge, the first measured instance of a discovery agent auditing its own knowledge ledger by an internal measure and finding itself over-claiming.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.32245 — 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 2026-10-26T19:45:33.299Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).