Unverified50% confidenceFactExact time
Retesting with the same 20 files, 18 compiled directly; after one more iteration letting the sessions receive compiler error messages, it reached 19.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedIn the first group of 20 files, 11 compiled on the first pass, and 9 failed.73% similarUnverifiedThis benchmark uses 10 original short documents of 200 to 250 words each, with 18 planted anomalies, 37 scoring entries in total (18 dirty and 19 clean), testing 13 models with 74 prompts per model.71% similarUnverifiedAPI request retries on streaming failures could reach as many as 21 times; non-streaming fallbacks now share the same retry budget as the original request.70% similarUnverifiedA developer reviewed 27 prompts accumulated over one year, of which 22 failed the reproducibility test (i.e., others using the prompts could not obtain the same output as the author).70% similarUnverified数据回放中每类保留约20个样本即可获得明显的遗忘抑制效果69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011186API
curl https://kongchang.com/api/v1/knowledge/claims/1011186MCP
get_claim(id=1011186)