Unverified50% confidenceFactExact time
Taking a GitHub repository page as an example, the complete HTML may exceed 200KB, but the extracted structured text is usually only 2 to 5KB, equivalent to a few hundred Tokens.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGitHub issue #7714 calculated that injecting the same state into the context window consumes 5,764 tokens, while the semantic content itself requires only 3,587 tokens, meaning a 37.8% token overhead per LLM call.66% similarUnverifiedThe entire site uses a fully static architecture, hosting the viewer on GitHub Pages and creating a separate repository for each vehicle model to store data in order to work around GitHub's single-repository size limit, with total content of approximately 6 GB.65% similarUnverifiedThe web frontend of Git repositories (such as cgit and gitweb) generates a separate URL for each commit, each file history version, diff view, and blame view, constituting a nearly infinite crawlable page space.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033233API
curl https://kongchang.com/api/v1/knowledge/claims/1033233MCP
get_claim(id=1033233)