Validating Repair Claims after Evidence Restoration in Compressed Prompts
Mathematical Modeling and Algorithm Application · 02.11.2026 · 10 (1) · 38-44
DOI: 10.54097/qpnkcr67 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Modeling and Algorithm Application, online erschienen am 02.11.2026. Verfasst von Ziye Yue und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
An answer that recovers after deleted evidence is restored does not, by itself, establish a reliable repair. The recovery may depend on sampling variation or on other changes to the prompt. We evaluate repair claims by fixing the restoration candidate and testing it against three distinct length-matched sham texts in fresh paired calls. An entry screen restricts search to questions that pass with the full context and fail after compression. With controlled deletion at a retention ratio of 0.5, protocol pass rates rose from 20.0% to 45.0% on 60 development items. On 100 held-out test items, they rose from 17.0% to 36.0%. Of 36 search candidates, 34 passed confirmation; one failed and one lacked enough matched texts to complete testing. All confirmed repairs were on GSM8K, with none on HotpotQA. During confirmation, target evidence was prepended and shams were appended, limiting the inference to a contrast involving both content and position. Search and confirmation together cost an estimated US$3.927; confirmation contributed 37.2%. The resulting record distinguishes candidates found during search from repairs supported by fresh control comparisons and makes the cost of that support explicit.
Zitieren
APA
Yue, Z., & Zhang, Y. (2026). Validating Repair Claims after Evidence Restoration in Compressed Prompts. Mathematical Modeling and Algorithm Application, 10(1), 38-44. https://doi.org/10.54097/qpnkcr67
Vancouver
Yue Z, Zhang Y. Validating Repair Claims after Evidence Restoration in Compressed Prompts. Mathematical Modeling and Algorithm Application. 2026;10(1):38-44. doi:10.54097/qpnkcr67
BibTeX
@article{Yue2026,
author = {Yue, Ziye and Zhang, Yuejin},
title = {Validating Repair Claims after Evidence Restoration in Compressed Prompts},
journal = {Mathematical Modeling and Algorithm Application},
year = {2026},
volume = {10},
number = {1},
pages = {38--44},
doi = {10.54097/qpnkcr67}
}
EUVIMED