Future-supervised reranker self-reports wins on all 12 confirmation tasks over SARAF
Self-reported by Yong-Hoon Choi and two co-authors: a lightweight MLP reranker supervised with realized futures at training time and using only past information at inference improves Pattern retrieval on six benchmarks and beats the protocol-matched SARAF rule on all 12 confirmation tasks.
ImportanceLocalEvidenceE2 unreplicated
A lightweight MLP reranker that trains on realized futures as supervision while using only past information at inference self-reports, by Yong-Hoon Choi and two co-authors, improved Pattern retrieval on six benchmarks and beat the protocol-matched SARAF rule on all 12 confirmation tasks.
Previously, similarity retrieval used historical samples directly without reranking; the last-value anchored L2 rule still wins in some domains, and historical relevance is domain-dependent.
These are self-reported results, not independently verified; the paper by Yong-Hoon Choi and two co-authors was first posted August 24 and updated to v2 on September 16 (arXiv:2608.23221).