用证据门控机制管控AI科研流程，防止结论虚报。
ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
- 将研究问题、证据、结论等设为持久化状态，全程可追溯。
- 九个版本实验验证，自托管案例中论文可复现性达100%。
- 适合追求可审计科研的学者与工业界研发团队。
AI辅助科研将构思、实现、评估和论文撰写压缩为一个交互式闭环，虽提升效率，但也增加了发表风险——论点易陈述而难验证。本文提出ResearchLoop，一种面向计算型科研的证据门控控制平面。该系统将研究问题、任务契约、证据对象、声明账本、结项记录和论文绑定视为持久项目状态，并以仓库驱动的运行时实现。本技术报告完整提供了协议规范、状态模型、转换规则、声明准入算法及洞察累积机制。实验涵盖九个版本（V0–V9），包括自托管案例研究、组件消融的受控任务套件实验、数学奥林匹克评测，以及使用官方生成代码测试工具评估的SciCode边界实验。所有文稿、清单和验证报告均保留在项目仓库中。
原文摘要 · Abstract (English)
AI-assisted research compresses ideation, implementation, evaluation, and manuscript writing into a single interactive loop. This compression is useful, but it also creates a publication risk: paper claims can become easier to state than to audit. We present ResearchLoop, an evidence-gated control plane for AI-assisted computational research. ResearchLoop treats research questions, task contracts, evidence objects, claim ledgers, closeouts, and paper bindings as durable project state, realized here as a repository-backed runtime. This technical report provides the complete protocol specification, state model, transition rules, claim-admission algorithm, and insight-compounding mechanism. It also reports the full experimental record spanning nine versions (V0--V9), including a self-hosting case study, a controlled task-suite study with component ablations, a mathematical olympiad evaluation, and a supplementary SciCode boundary experiment evaluated with the official generated-code harness. All artifacts, manifests, and verification reports are preserved in the project repository.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。