Unverified50% confidenceBenchmarkExact time
On the MathlibMPR benchmark, LeanGraphSearch additionally increases coverage of fully annotated proof paths by up to 3.7% of problem groups.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAlthough Elasticsearch supports dynamic mapping, it triggers mapping conflict errors and can even cause data loss when the same field is written with different types across different logs.60% similarUnverifiedIn multi-step tool-calling chains, errors can propagate and amplify between reasoning nodes, making root-cause analysis difficult.56% similarUnverifiedThe core judgment of LeanGraphSearch is: proof discovery is essentially a structure-aware search problem, not merely a text similarity ranking problem.55% similarUnverifiedThe reliability of offsets depends on how the tokenizer maps to character indices; if token indices are returned rather than character indices, an extra alignment step is needed, especially in multi-byte character scenarios.55% similarUnverifiedGraphEcho systematically varies two dimensions—the number of paths and the source of evidence—while keeping the evidence content fixed.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042031API
curl https://kongchang.com/api/v1/knowledge/claims/1042031MCP
get_claim(id=1042031)