Metraipolis › archive › dc_cc1cae37e374
Self-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures — arXiv:2609.25052
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25052
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:46:01.100Z
- SHA-256 of the archived text
d4f0bbed3ca2a0ac8f3454039a76a7b33018be7dc279d8052cdb414d6aeebcf3- Stable URL of this page
https://metraipolis.com/documento/dc_cc1cae37e374
How to cite
Self-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures — arXiv:2609.25052 — arXiv (en), https://arxiv.org/abs/2609.25052 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc1cae37e374 (Metraipolis archive dc_cc1cae37e374, sha256 d4f0bbed3ca2a0ac8f3454039a76a7b33018be7dc279d8052cdb414d6aeebcf3)
BibTeX
@misc{dccc1cae37e374,
title = {Self-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures — arXiv:2609.25052},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25052},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc1cae37e374; sha256 d4f0bbed3ca2a0ac8f3454039a76a7b33018be7dc279d8052cdb414d6aeebcf3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25052. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
"An agent that writes its conclusions into a store it later retrieves from closes a loop usually reported as one-way contamination. Taking the loop to the infinite-tenure limit against an append-only store gives a different picture: because writing never deletes, the reachable state space has a hard upper edge at (n-1)/n, so the outcome is a choice between two edges rather than a decay. At f_0 = 0.9 the interval between the two modes holds 3.6% of 220 runs where a uniform spread would put 20.6%, and is strictly empty on the first 15; the pooled mean describes 8.2% of the runs it summarises, the median 68.2%. Everything the model contributes is carried by one measured primitive with no fitted parameter, the copy function \gamma(\phi): on 36 Wikidata facts, sign(\hat{\gamma} - \gamma_{crit}), with \gamma_{crit} = 1/k at r = 0, w = 1, predicts the direction of drift on 353 of 360 real-fact runs (39 of 40 synthetic in the same batch). Scale does not rescue the store: pooled frontier capture is 0.850, with claude-sonnet-4.5 captured on 20 of 20 seeds against our registered prediction of <0.5. What the interval tests is distinguishability rather than count: on the real facts, multi-valued runs have 6.4x its occupancy of the rest. It survives at f_0 in {0.1, 0.3, 0.5}, capture peaks at f_0 = 0.5, and of four interventions with criteria frozen first, timing dominates fraction at matched budget while a consistency gate drives every model to 0.993. The resampling unit is the seed, at a design effect of 3.75 on a pooled level: under a 44-seed control the ordering supporting claim 4 collapses from Spearman +0.98 at three seeds to +0.31-0.80 at forty-four, while claim 2's ordering is exact there (+1.00, p = 0.017). All 87 graded rows are in Appendix W, 37 of them graded withdrawn, failed, self-correcting, undecidable or an acknowledged limit, against 50 that are not."
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.25052 — 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 2026-10-08T13:18:38.193Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).