Metraipolis › archive › dc_847f2ea1663e

Two tests of phase-structure features for transition prediction — arXiv:2609.00335

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00335
License (as archived): CC0-1.0
Archived: 2026-10-17T06:41:08.895Z
SHA-256 of the archived text: a4c5b925b81f797f300f8c3db63cc08963795f68e9bc3f9c04e132563dd576ab
Stable URL of this page: https://metraipolis.com/documento/dc_847f2ea1663e

How to cite

Two tests of phase-structure features for transition prediction — arXiv:2609.00335 — arXiv (en), https://arxiv.org/abs/2609.00335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_847f2ea1663e (Metraipolis archive dc_847f2ea1663e, sha256 a4c5b925b81f797f300f8c3db63cc08963795f68e9bc3f9c04e132563dd576ab)

BibTeX

@misc{dc847f2ea1663e,
  title = {Two tests of phase-structure features for transition prediction — arXiv:2609.00335},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00335},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_847f2ea1663e; sha256 a4c5b925b81f797f300f8c3db63cc08963795f68e9bc3f9c04e132563dd576ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Following arXiv:2607.25507 , this report examines whether phase-derived features improve endpoint prediction over a combined baseline in two settings: a sealed contradiction comparison and a retrospective analysis of answer changes across matched pressure prompts. Study 1 froze a contradiction-category pipeline before sealed scoring. On 1,136 eligible primary cases, adding PC-2 produced a paired AUROC difference of +0.00087. The 99% bias-corrected accelerated interval included zero, and the prespecified +0.05 threshold was not met. A replication role with 1,063 cases showed a same-direction increment of +0.00019. The replication-direction condition passed, but both primary conditions failed, so advancement failed. Study 2 developed fifteen treatments on blocks b0-b4 using 1,415 eligible answer-change comparisons and twenty-repeat, five-fold grouped cross-validation. An execution on 9 September 2026 recomputed development statistics from saved prediction units and applied a three-condition gate; no treatment advanced. Layer 25 had the only positive mean-repeat PC-2 increment, approximately +0.00027, with a favorable sign in three of five seed blocks. These statistics measure development consistency, not whole-seed-block holdout performance. Agreement with earlier selection records does not establish an earlier notebook execution or that the rule was fixed before inspecting development results. The planned b5 selection and b6 evaluation were not completed through this gate. Neither study demonstrated the incremental benefit required by its applied advancement rule. The findings limit support for the evaluated feature constructions; they do not test the rotary score identity, its local pre-softmax bound, or the effectiveness of execution-boundary governance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.00335 — 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 2026-10-17T06:33:38.800Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).