Unverified50% confidenceFactExact time
reconcile.py reads its own ledger, aggregates the number of requests, successes, retries, prompt_tokens, and completion_tokens, and tallies the distribution of completion hashes.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMeasures to deal with duplicate chunks include exact deduplication via content hashing, near-duplicate clustering based on embedding similarity, establishing normalization policies, and weighting by source metadata at query time, none of which require changing the model.59% similarUnverified重排模型会对查询和每个候选文档进行更精细的相关性打分，将最相关的文档排在前列，从而提升检索质量59% similarUnverifiedSimilar Issue search works by generating a normalized sentence vector for each stored Issue, computing and ranking the cosine similarity between a new report and them, and returning the five most similar ones along with their original GitHub links.57% similarVerifiedIn the knowledge retrieval stage, the user's question is converted into a query vector via an embedding model, similarity is computed against the text chunk vectors in the knowledge base (typically using cosine similarity), and the top-K segments are returned by ranking.57% similarUnverifiedMulti-query retrieval uses an LLM to automatically generate 3–5 semantically equivalent but differently phrased variant queries for the same question, retrieves results for each separately, and takes the union to improve recall.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034852API
curl https://kongchang.com/api/v1/knowledge/claims/1034852MCP
get_claim(id=1034852)