ResearchBenchmarksLong-context Memory Evaluation on LongMemEval-S (Seed 11)Long-context Memory Evaluation on LongMemEval-S (Seed 11)Follow0.06DeltaRegimes0.0570.05850.060.0615Jun 8, 2026Evaluation resultsMethodMethodLinksDeltaW->R Confirmation CountR->W Confirmation CountDiscordant CountConfirmation Rate (Base)Confirmation Rate (Post)Optimal Recall (Base)McNemar p-value (Post-hoc)Regimespromotes (total)=2promotes (total)=22026.060.0682107783740.109