Unverified50% confidenceCautionExact time
The BUG:/DOC:/ENH: prefixes commonly found in Issue titles cause data leakage, because the model would directly "copy the answer" from the title prefix rather than learn from the report content, so these prefixes must be removed before training.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedExpanding abbreviations prior to retrieval is problematic because the same code may represent entirely different meanings in different departments, and blind expansion can cause confusion between homonymous codes with different meanings59% similarVerifiedThe root cause of Prompt Injection is that large models cannot structurally distinguish between "system instructions" and "user data," as both are presented as natural language text at input time.59% similarUnverifiedPlacing the run number at the beginning of the prompt rather than the end can break Ollama's prefix cache hits, forcing full processing of the input from scratch.58% similarUnverifiedLLMs inject entities that do not exist at all or terms irrelevant to the topic when generating query expansion terms; these hallucinated terms increase ranking noise and can harm retrieval effectiveness.58% similarUnverifiedLLM-generated code often appears well-named, fully commented, and clearly structured, which can lower reviewers' vigilance and make hidden logical defects or security issues harder to detect.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009435API
curl https://kongchang.com/api/v1/knowledge/claims/1009435MCP
get_claim(id=1009435)