空控制是必要但不充分的:评估科学发现与可解释性的接受防护机制
Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability
AI总结:
该研究针对自动科学发现系统的接受防护机制,开发四类操作并结合三种评估标准,发现存在接受缺口,提出需同时评估测试接受内容与确立的科学结果。
摘要:
自动发现系统会提出科学解释并测试哪些解释应被接受。通过一项测试是否就能确立预期主张?我们开发了四种可执行的物理描述修改操作:识别冗余(L1)、粗粒化动力学(L2)、迁移结构(L3)以及从守恒失衡中推断缺失量(L4)。我们通过空接受(NAR)、正接受(PAR)和结果一致性(CAR)这三种可解释性设置来评估这些操作。一个将每个状态映射到零的约简能完美预测自身未来,它在129个公开混沌系统上通过了96%的闭合性测试,却未保留任何动力学变化。一项独立的可观测性保留测试全程拒绝了它。在受控基准测试中,组合标准接受了24个真实约简中的全部24个,拒绝了72个空约简中的全部72个。其他操作可区分对称性与冗余、验证迁移的正确性,并拒绝虚假的守恒失衡。在语言模型和ESM-2蛋白质模型中,当提出的对应关系被随机旋转时,线性CKA保持不变,而局部干预能区分真实映射与测试的空映射。在稀疏自编码器中,富集操作拒绝了全部16个被测试的空约简,而独立的剪枝操作支持了45%的可评估富集特征,相比之下匹配对照组仅支持0.5%。这些结果揭示了两个接受缺口:描述性测试可能接受科学上空洞的候选,且被接受的候选可能缺乏独立验证的结果。可靠的自动发现需要同时评估测试所接受的内容及其确立的科学结果。代码和数据:this https URL
英文摘要:
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: https://real-project-aether.github.io/project-aether/.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。