Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered

DelSA outperforms existing methods on ChronoFake, while remaining competitive on PolitiFact and GossipCop. It comes from a paper posted to arXiv on 28 October 2026. Fake news undermines public trust and the integrity of online information ecosystems. Temporally disordered fake news is especially elusive because it rearranges factual events into a false chronology. Individual events may remain factually valid even when their temporal relations are misrepresented. When similar events involving the same entity recur, retrieval may return semantically plausible evidence from the wrong period. Consequently, independent event verification may rely on locally coherent but temporally mismatched evidence and incorrectly validate the article. We call this the \textit{evidence coherence trap}. Because existing benchmarks rarely isolate this setting, we construct ChronoFake, a source-disjoint benchmark of 30,706 articles derived from temporally anchored real events. It distinguishes temporal manipulation from valid narration, including flashbacks. To address this, we propose DelSA, a \underline{D}ocument S\underline{el}ection \underline{S}elf-Updating \underline{A}gent that iteratively refines evidence selection during training and applies a frozen rulebook for one-pass evidence selection at inference. DelSA uses an LLM to characterize candidate evidence, while a verifier-trained reranker balances local relevance against timeline consistency. Finally, the classifier compares the article-implied chronology extracted by the LLM with the evidence-derived chronology to reveal global temporal conflicts.

Why it counts

DelSA outperforms existing methods on ChronoFake, while remaining competitive on PolitiFact and GossipCop.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.