# Memory Consolidation Flattens the Temporal Shape of User Facts

arXiv: https://arxiv.org/abs/2609.36457 · HTML: https://mlsanity.com/paper/2609.36457/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026)
- [From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents](https://mlsanity.com/paper/2604.20006/) (2026)
- [Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents](https://mlsanity.com/paper/2601.07468/) (2026)
- [Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge](https://mlsanity.com/paper/2606.26511/) (2026)
- [When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responses](https://mlsanity.com/paper/2608.01619/) (2026)
- [Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks](https://mlsanity.com/paper/2605.24060/) (2026)
- [Chronocept: Instilling a Sense of Time in Machines](https://mlsanity.com/paper/2505.07637/) (2025)
- [Manufactured Confidence: How Memory Consolidation Turns Hearsay into Confident Facts](https://mlsanity.com/paper/2606.29279/) (2026)
- [Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs](https://mlsanity.com/paper/2609.10413/) (2026)
- [Temporal Validity Change Prediction](https://mlsanity.com/paper/2401.00779/) (2024)
- [Fixed RAG Compression Collapses Measured Reader Scaling](https://mlsanity.com/paper/2606.21807/) (2026)
- [When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict](https://mlsanity.com/paper/2608.13921/) (2026)
- [MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval](https://mlsanity.com/paper/2609.03201/) (2026)

## Built on by (most cited first, 1 of 1)

- [Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams](https://mlsanity.com/paper/2610.04210/) (2026)

## Abstract (arXiv)

Long-term memory systems turn conversations into short stored notes. A note can keep a user fact while losing evidence about whether the fact still holds. For example, "I am driving a Peugeot" can become "The user drives a Peugeot," which drops the cue that the activity is ongoing. We call this aspectual flattening and measure it with LAPSE, a benchmark of matched user statements that differ only in temporal form. We find that memory writers flatten aspect selectively. Three writer models flattened the progressive statement but kept its simple-present match in 244 of 381 pairs, never the reverse. The asymmetry holds in all 11 model configurations tested and in the installed pipelines mem0, Graphiti, and Letta. The lost cue matters to later readers. In exploratory tests, changing only the stored verb shifted all three readers' estimates that a fact still holds. When readers could ask the user before acting, two of three acted without asking more often on flattened notes. Our planned memory-use task could not detect this, because readers there acted on almost every stored fact, even expired ones. Memory writing can thus remove evidence that later models use to decide whether to act.