Unverified50% confidenceEventExact time
The author once used 719 manuscripts from openai/math to extract a machine-readable map of proof techniques, extracting 40 signatures in total, which were blind-reviewed by Claude and Grok using a frozen scoring rubric.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe author lists practices that did not work for them: massive monolithic context files, feeding complete session logs to the next session, letting the agent decide task scope on its own, and trusting co-generated tests.62% similarUnverifiedPublishing hundreds of manuscripts does not mean every one is a verified mathematical breakthrough; the relevant results still require independent, rigorous review and are far from equivalent to solving complete conjectures.58% similarUnverified部分期刊正在试验要求作者提交写作过程的版本记录，或使用区块链技术对研究数据和写作过程进行溯源认证58% similarUnverifiedThe results of the paper's experiments were scored and evaluated by the original paper's authors themselves.58% similarUnverifiedSergey Yurkevich, one of the researchers who proposed the conjecture, endorsed the paper, enabling it to be submitted to the arXiv preprint platform.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1017268API
curl https://kongchang.com/api/v1/knowledge/claims/1017268MCP
get_claim(id=1017268)