English

Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study

Computation and Language 2026-04-22 v2 Information Retrieval

Abstract

Search-engine date filters are widely used to enforce pre-cutoff retrieval in retrospective evaluations of search-augmented forecasters. We show this approach is unreliable across two major search engines: auditing Google Search's before: filter and DuckDuckGo's date-range filter, we find that at least one retrieved page contains major post-cutoff leakage for 71% of questions on Google and 81% on DuckDuckGo, and the answer is directly revealed for 41% and 55%, respectively. Using gpt-oss-120b to forecast with these leaky documents, we demonstrate inflated prediction accuracy (Brier score 0.10 vs. 0.24 with leak-free documents). We characterize recurring leakage mechanisms, including updated articles, related-content modules, unreliable metadata, and absence-based signals, and argue that date-restricted search on these engines is insufficient for credible retrospective evaluation. We recommend stronger retrieval safeguards or evaluation on frozen, time-stamped web snapshots.

Keywords

Cite

@article{arxiv.2602.00758,
  title  = {Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study},
  author = {Ali El Lahib and Ying-Jieh Xia and Zehan Li and Yuxuan Wang and Xinyu Pi},
  journal= {arXiv preprint arXiv:2602.00758},
  year   = {2026}
}

Comments

9 pages, 2 figures. Accepted to ACL 2026

R2 v1 2026-07-01T09:29:29.862Z