Science One Framework: A verifiable autonomous research

What happened

Large language models (LLMs) are increasingly being deployed not just as coding assistants but as autonomous agents capable of conducting end-to-end scientific research workflows. , Sakana’s AI-Scientist, AutoResearchClaw, DeepScientist, AI-Researcher) can review literature, formulate hypotheses, execute experiments and write complete manuscripts that are comparable to human-authored papers. However, as the surface-level quality of these AI-generated manuscripts improves, a critical structural problem has emerged: verifiability.

A misdescribed method claims one algorithm in the paper while the code implements another. Each is a claim whose chain back to its evidence is broken; the CoE Audit makes these breaks measurable. To demonstrate that verifiable AI research is possible without sacrificing problem-solving performance, we designed the Science One Framework. , Sakana AI's AI Scientist v2, AutoResearchClaw, DeepScientist, AI-Researcher), we developed the CoE Audit.

This post-hoc evaluation protocol acts as an automated forensic reviewer, running four strict integrity checks on the generated artifacts (paper, solution, code and references): We applied the CoE Audit to 75 papers generated across five systems-optimization tasks (Prism, Cloudcast, EPLB, LLM-SQL, and transaction scheduling) from the Automated Design of Research Systems (ADRS) benchmark. The Science One Framework significantly outperformed existing baselines in verifiability.

Why it matters

Because current autonomous research pipelines generate text iteratively, errors introduced at any stage are amplified. Some existing systems can generate non-existent citations, exhibit misalignments between the described methods and the actual code, and report experimental scores that are not fully reproducible from the provided code. In our paper, we tackle this problem by introducing Chain-of-Evidence (CoE), a new verifiability framework for AI-driven research.

We instantiate CoE with the Science One Framework, an autonomous research prototype that natively builds and maintains evidence chains, and the CoE Audit, a set of automated evaluation metrics that measures the integrity of AI-generated papers against their underlying code and evidence.

Our results show that baseline systems hallucinate up to 21% of their references and frequently misalign their code and text, whereas the Science One Framework achieves zero phantom references and fully verifiable scores while achieving state-of-the-art performance on frontier benchmarks like MLE-Bench and Parameter-Golf. The CoE is a conceptual framework that defines what makes a research artifact trustworthy, much as ACID defines what makes a database transaction reliable.

Rather than prescribing how to build a research agent, the framework specifies the properties its outputs must have. It follows a single principle with two halves: every claim in a research artifact must carry a recorded evidence chain (completeness), and each chain must genuinely support the claim it is attached to (correctness).

A claim may be a reference, a reported number, a method description, or a conclusion, that must link back to corresponding evidence, such as a peer-reviewed paper, an experimental log line, the code that actually ran, or the results table. A hallucinated reference points to a paper that does not exist. An unreproducible score does not reappear when the code is re-run.

What to watch

The CoE Audit applies the same independent protocol to every system, re-checking each reference against live scholarly databases, and under it, Science One Framework led on all four integrity checks. None of its references were phantom: every one pointed to a real, retrievable paper, compared to hallucination rates as high as 21% in baselines, because the Problem Investigator retrieves every reference rather than generating it from memory.

It also achieved perfect score verification and the highest method-code alignment. In contrast, baseline systems frequently described sophisticated algorithms (like "hybrid neuro-symbolic solvers") when their submitted code was a simple, deterministic heuristic. To test its generalization, we deployed the Science One Framework on six highly complex external tasks: