# Making AI Scientists Auditable from Evidence to Claim

arXiv: https://arxiv.org/abs/2606.18874 · HTML: https://mlsanity.com/paper/2606.18874/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 58 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory](https://mlsanity.com/paper/2510.02373/) (2025)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026)
- [Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting](https://mlsanity.com/paper/1707.01926/) (2017)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement](https://mlsanity.com/paper/2512.18950/) (2025)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents](https://mlsanity.com/paper/2505.23559/) (2025)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systems](https://mlsanity.com/paper/2601.08815/) (2026)
- [ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration](https://mlsanity.com/paper/2605.03042/) (2026)
- [MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation](https://mlsanity.com/paper/2507.21953/) (2025)
- [SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation](https://mlsanity.com/paper/2510.07733/) (2025)
- [TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking](https://mlsanity.com/paper/2602.03224/) (2026)
- [Deep Literature Survey Automation with an Iterative Workflow](https://mlsanity.com/paper/2510.21900/) (2025)
- [SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?](https://mlsanity.com/paper/2510.03120/) (2025)
- [TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems](https://mlsanity.com/paper/2603.15408/) (2026)
- [DeepSurvey-Bench: Evaluating Academic Value of Automatically Generated Scientific Surveys](https://mlsanity.com/paper/2601.15307/) (2026)
- [AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents](https://mlsanity.com/paper/2603.23910/) (2026)
- [CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models](https://mlsanity.com/paper/2512.14118/) (2025)
- [Pruning Minimal Reasoning Graphs for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2602.04926/) (2026)
- [SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation](https://mlsanity.com/paper/2602.11238/) (2026)
- [DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability](https://mlsanity.com/paper/2605.29522/) (2026)

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

- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)

## Abstract (arXiv)

AI research systems can report improved results without establishing that the tested implementation matches the method described in their conclusions. We introduce Xcientist, a research harness that connects literature review, component-based idea generation, experiment validation and reporting. An evidence graph retains source passages, methods, baselines and evaluation conditions; component records track design revisions; and validation contracts specify the implementation, comparisons and artifacts required at each stage. We define claim drift as an unresolved mismatch between an accepted claim and its attributed sources, code or experiments. A retrospective audit across agent memory, traffic forecasting and physics-informed learning found audit claim drift rates of 3.6--16.7% for Xcientist, lower than those of each of three comparison systems in all nine task-by-relation comparisons. This measure includes both confirmed mismatches and unverifiable claims; most of the difference arose from fewer unverifiable records. The case studies also document performance gains, unsuccessful revisions and limits on component attribution. This technical report describes the system, its implementation and the records needed to check how a proposed idea became a tested method and a final claim.