Unverified50% confidenceFactExact time
In recent years, top AI conferences have successively introduced reproducibility checklists, requiring authors to declare whether code and data are public.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedTop conferences such as NeurIPS and ICML have introduced reproducibility checklists requiring authors to submit code and describe experimental setups.75% similarUnverifiedAI基准测试均有公开的学术论文和排行榜(如Papers With Code),任何声称超越某基准的数据都可公开查证75% similarUnverifiedExisting reproducibility checklists are primarily based on encouragement and self-reporting; authors only need to check whether code is provided, and not providing code does not directly lead to rejection.74% similarUnverifiedGrounding checks verify whether model outputs have traceable support, with common practices including requiring cited sources and verifying that the sources exist, cross-checking key fields for consistency, and rejecting unsupported claims.71% similarUnverifiedReading AI-generated test code is essentially doing requirement traceability, mapping each original requirement to a specific assertion.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1105325API
curl https://kongchang.com/api/v1/knowledge/claims/1105325MCP
get_claim(id=1105325)