# The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning

arXiv: https://arxiv.org/abs/2604.17114 · HTML: https://mlsanity.com/paper/2604.17114/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 14 of its 61 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/1902.07669/) (2019)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.04187/) (2024)

## Built on by (most cited first, 2 of 2)

- [ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning](https://mlsanity.com/paper/2605.22734/) (2026)
- [Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility](https://mlsanity.com/paper/2609.16252/) (2026)

## Abstract (arXiv)

Frontier large language models generate clinically accurate outputs, but their citations are often fabricated. We term this the Provenance Gap. We tested five frontier LLMs across 36 clinician-validated scenarios for three rare neuromuscular disease pairs. No model produced a clinically relevant PubMed identifier without prompting. When explicitly asked to cite, the best model achieved 15.3% relevant PMIDs; the majority resolved to real publications in unrelated fields. We present HEG-TKG (Hierarchical Evidence-Grounded Temporal Knowledge Graphs), a system that grounds clinical claims in temporal knowledge graphs built from 4,512 PubMed records and curated sources with quality-tier stratification and 1,280 disease-trajectory milestones. In a controlled three-arm comparison using the same synthesis model, HEG-TKG matches baseline clinical feature coverage while achieving 100% evidence verifiability with 203 inline citations. Guideline-RAG, given overlapping source documents as raw text, produces zero verifiable citations. LLM judges cannot distinguish fabricated from verified citations without PubMed audit data. Independent clinician evaluation confirms the verifiability advantage (Cohen's d = 1.81, p < 0.001) with no degradation on safety or completeness. A counterfactual experiment shows 80% resistance to injected clinical errors with 100% detectability via citation trace. The system deploys on-premise via open-source models so patient data never leaves institutional infrastructure.