Unverified60% confidenceFactExact time
The Open Science Collaboration's replication study of 100 psychology experiments found that only about 36% of results were successfully replicated.
2
Sources
60%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
UnverifiedPM conclusion statistics: 24 rejections and 18 passes (including partial acceptance and limited acceptance); the number one reason for rejection is insufficiently hard evidence (missing screenshots, incorrectly written reports, tests that did not take effect), rather than business logic.68% similarUnverifiedSome researchers have systematically attempted to reproduce papers that passed checklist review and found that the success rate did not improve significantly.67% similarUnverified斯坦福大学的AgentBench基准测试（2023年）量化证明，在复杂多步骤任务中纯ReAct范式的成功率往往不超过30%67% similarUnverifiedEven the best-performing models can only recover 30% of the evaluated evidence and 25% of the limitations descriptions.66% similarUnverifiedA 2019 survey of NeurIPS papers found that fewer than 25% of papers provided code and configurations sufficient to fully reproduce their results.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/554678API
curl https://kongchang.com/api/v1/knowledge/claims/554678MCP
get_claim(id=554678)