arXiv cs.AI· Tianyu Wu (Project Aether)·· 12 小时前AI 评分34
零假设对照必要但不充分：评估科学发现与可解释性中的接受守卫
Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability
AI 导读
研究提出四种可执行操作（识别冗余 L1、粗粒化动力学 L2、迁移结构 L3、从守恒失衡推断缺失量 L4），并用零接受率（NAR）、正接受率（PAR）和后果一致性（CAR）评估。
正文 · 原文
Abstract:Automated discovery systems propose scientific explanations and test which to accept. Does passing a test establish the intended claim? We develop four executable operations for changing physical descriptions: identifying redundancies (L1), coarse-graining dynamics (L2), transferring structure (L3), and inferring missing quantities from conservation imbalances (L4). We evaluate these operations and three interpretability settings through null acceptance (NAR), positive acceptance (PAR), and consequence agreement (CAR).
A reduction mapping every state to zero predicts its own future perfectly. It passes closure on 96% of 129 public chaotic systems despite retaining no dynamical variation. An independent observable-preservation test rejects it throughout. On controlled benchmarks, the combined criteria accept 24/24 genuine reductions and reject 72/72 nulls. The other operations distinguish symmetries from redundancies, validate transfers, and reject spurious conservation imbalances. In language and ESM-2 protein models, linear CKA remains unchanged when a proposed correspondence is randomly rotated, whereas localized interventions distinguish genuine mappings from tested nulls. In sparse autoencoders, enrichment rejects all 16 tested nulls, yet independent ablation supports 45% of evaluable enriched features, compared with 0.5% of matched controls.
These results reveal two acceptance gaps: descriptive tests can accept scientifically empty candidates, and accepted candidates can lack independently verified consequences. Reliable automated discovery requires evaluating both what a test accepts and the scientific consequences it establishes. Code and data: this https URL.
| Comments: | accpeted in 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: XAI4Science: Knowledge Discovery and Trust through Interpretable Foundation Models |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.22445 [cs.AI] |
| (or arXiv:2610.22445v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22445 arXiv-issued DOI via DataCite |
Submission history
From: Tianyu Wu [view email]
[v1]
Thu, 15 Oct 2026 15:13:57 UTC (472 KB)
来源：arXiv cs.AI · arxiv.org