arXiv cs.AI· Patrick Cooper, Avyay Sadhu, Alvaro Velasquez·· 12 小时前AI 评分26
DeFAb：基于可废止溯因的扎根科学发现数据集
DeFAb: A Dataset for Grounded Scientific Discovery through Defeasible Abduction
AI 导读
DeFAb 是构建自 Gene Ontology 精选生物学知识的数据集与符号验证框架，模型负责填补理论缺口或提出规则例外，验证器检查每次修改的后果。简单符号修复即可解决发布评测面板中全部 336 个任务，暴露出该修订测试的局限：绑定单一实体的例外可能成功，却未识别出适用于其他案例的模式。
正文 · 原文
Abstract:A theory can accommodate a counterexample by adding an exception. The harder problem is deciding how far the exception should extend and which predictions should survive. We present DeFAb, a dataset and symbolic verification framework built from curated biological knowledge in the Gene Ontology. Models fill gaps in a theory or propose exceptions to its rules. A verifier checks the consequences of each edit, allowing different solutions to receive credit. Simple symbolic repairs solve all 336 tasks in the released evaluation panel. This result exposes a limitation of the revision test. An exception tied to one entity can succeed without identifying a pattern that applies to other cases. We develop a contextual task that requires an exception to reach the relevant cases and preserve predictions elsewhere. Two planned studies compare training with verified and rejected examples, and revision with and without feedback about consequences. DeFAb makes the scope of a proposed explanation testable, providing a controlled step toward studying theory revision in scientific reasoning.
| Comments: | 12 pages, 3 figures |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Logic in Computer Science (cs.LO) |
| MSC classes: | 68T27, 68T30, 68T05, 03B70 |
| ACM classes: | I.2.3; I.2.4; I.2.6; I.2.7 |
| Cite as: | arXiv:2606.18557 [cs.AI] |
| (or arXiv:2606.18557v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.18557 arXiv-issued DOI via DataCite |
Submission history
From: Patrick Cooper [view email]
[v1]
Wed, 17 Jun 2026 00:13:40 UTC (272 KB)
[v2]
Fri, 23 Oct 2026 02:03:13 UTC (55 KB)
来源：arXiv cs.AI · arxiv.org