Metraipolis › archive › dc_8a02e14e6219

Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression — arXiv:2608.06953

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06953
License (as archived)
CC0-1.0
Archived
2026-10-19T09:46:53.408Z
SHA-256 of the archived text
69c855ca2c2a5e7800588960bd1774a8a08b046af143e1b25883f95d70172abb
Stable URL of this page
https://metraipolis.com/documento/dc_8a02e14e6219

How to cite

Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression — arXiv:2608.06953 — arXiv (en), https://arxiv.org/abs/2608.06953 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a02e14e6219 (Metraipolis archive dc_8a02e14e6219, sha256 69c855ca2c2a5e7800588960bd1774a8a08b046af143e1b25883f95d70172abb)
BibTeX
@misc{dc8a02e14e6219,
  title = {Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression — arXiv:2608.06953},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06953},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a02e14e6219; sha256 69c855ca2c2a5e7800588960bd1774a8a08b046af143e1b25883f95d70172abb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06953. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent memory systems compress what they store, and compression is built to drop qualifiers, so a claim's epistemic standing tends not to survive being written to memory. We ask what governs whether it does. Matched notes carry the identical claim and identical stance and differ only in where that stance sits; one model compresses both under the same budget among the same filler notes, and a blind reader that never sees the condition scores the result. Across 60 claims in seven registers, writing the stance as a labelled field rather than a bracketed aside raises retention by about 15 points on two models (37 claims to 2 on one, 30 to 8 on the other; permutation p=0.00005), and a pre-registered replication on Haiku, its prediction and decision rule committed before the run, gives +15.6 points, 38 claims to 1. Ablating the format on both models gives the same net effect from different parts: labels help on both (+9.7 and +12.8) and length helps on neither, but wording the stance as a full sentence is the largest component on one model (+12.5) and worth nothing on the other (+0.6). Either model alone would have licensed a confident and different mechanism, so we claim only the intersection: make the stance explicit, not merely longer, and expect the best way of being explicit to depend on the model. A deterministic readout with no model reproduces the two-cell direction and five of seven ablation contrasts, but not length or labels, which we therefore do not claim on one instrument. Fifty hand labels (kappa=0.75) agree on direction; we print their seven disagreements in full. We also report nine withdrawn claims, three of them former title claims of this paper.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.06953 — 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 2026-10-19T09:46:37.228Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).