# Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2607.20560 · HTML: https://mlsanity.com/paper/2607.20560/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 10 of 10)

- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records](https://mlsanity.com/paper/2503.04176/) (2025)
- [TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios](https://mlsanity.com/paper/2505.12891/) (2025)
- [Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic](https://mlsanity.com/paper/2506.08243/) (2025)
- [The Cost of Delay in Status Updates and their Value: Non-linear Ageing](https://mlsanity.com/paper/1812.09320/) (2018)
- [Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning](https://mlsanity.com/paper/2601.13387/) (2026)
- [Chronocept: Instilling a Sense of Time in Machines](https://mlsanity.com/paper/2505.07637/) (2025)
- [Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph Summarization](https://mlsanity.com/paper/2510.16715/) (2025)
- [Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval](https://mlsanity.com/paper/2601.05549/) (2026)
- [The 17% Gap: Quantifying Epistemic Decay in AI-Assisted Survey Papers](https://mlsanity.com/paper/2601.17431/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all retrieved facts as equally valid regardless of temporal provenance, leading to temporal hallucination, where plausible but obsolete facts corrupt the output. A clinical lab reading from yesterday is actionable; the same reading from six months ago is noise. We present Chronofy, a three-layer neuro-symbolic framework implementing the Temporal-Logical Decay Architecture (TLDA) that embeds temporal validity directly into the representation, retrieval, and reasoning layers of RAG systems. Layer 1 reserves a dedicated temporal subspace within Matryoshka embeddings to make fact age structurally irremovable from the representation. Layer 2 integrates learnable exponential decay functions into graph-based retrieval, where the decay coefficient βj is grounded in Bayesian decision theory as an approximation of twice the latent process mean-reversion rate. Layer 3 applies Signal Temporal Logic (STL) robustness functions to evaluate the temporal validity of retrieved knowledge, not LLM output confidence, and enforces the possibilistic weakest-link principle to bound output confidence by the most decayed evidence in the reasoning chain. We evaluate Chronofy on temporal knowledge graph forecasting benchmarks, the TimE temporal QA benchmark, and a domain-specific sensitivity analysis, demonstrating that explicit temporal decay modeling improves retrieval precision, reduces temporal hallucination, and enables principled data re-acquisition triggers when temporal context is insufficient.