Unverified50% confidenceDecision RuleExact time
Ratified's answers come from graph traversal rather than model memory; no model writes Cypher, and a deterministic router picks one handwritten query for each question; if the traversal returns nothing, the card plainly says "the graph doesn't know."
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedOn the long-document question-answering task, both models got all four questions right, and both clearly stated 'not in the notes' for questions whose answers were absent from the notes.68% similarUnverifiedPrompt injection exploits not a vulnerability in the code parser, but the model's own insufficient awareness of the boundary between instructions and data67% similarUnverifiedThe model that writes the answer should not decide whether to answer; every message first goes through a separate cheap classification call that returns one of three labels: in-scope answer, out-of-scope refusal, or handoff to a human.64% similarUnverifiedA response with zero output tokens does not mean no inference occurred, because the model completed a full encoding and forward computation, only outputting structured options rather than generating verbatim.64% similarUnverifiedFairScreen's correct answers are computed from hidden structured records before applications are rendered; LLMs are not involved in labeling, and two policy implementations and a plain-text parser reached agreement across all 2,528 final variants.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063184API
curl https://kongchang.com/api/v1/knowledge/claims/1063184MCP
get_claim(id=1063184)