Unverified50% confidenceReleaseExact time
SciLitBench is the first benchmark covering the entire literature review pipeline, containing fine-grained annotation data of 42,981 retrieval records, 1,012 full texts, and 888 included papers
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe author reviewed approximately 1,500 detection calls, manually mined false positives, adjusted bounding boxes, and then retrained the model.63% similarUnverifiedThe SciMDEval expert-level evaluation benchmark contains 907 manually annotated high-difficulty questions62% similarUnverifiedIn actual testing, one Deep Research call invoked 104 agents for targeted research, completing fact-checking based on 22 sources and 59 claims.57% similarUnverifiedA test Skill consists of a directory structure, a description file, and specific execution scripts.56% similarUnverifiedThe evaluation comprised 108 checks across three major modules: backend API and full pipeline at 65 points, frontend pages and real interaction at 25 points, and build and packaging at 10 points.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893417API
curl https://kongchang.com/api/v1/knowledge/claims/893417MCP
get_claim(id=893417)