Unverified50% confidenceBenchmarkExact time
On 32 SV-COMP tasks, raw verifier feedback raised the average correct model determinations from 12.7 to 22.0, but at the same time increased incorrect determinations from 1 to 7.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn code repair tasks, the success rate using a static validator was 26.3%, rising to 29.2% after introducing predictive selection, and reaching 31.2% after world model adaptation71% similarUnverifiedIn the experiments, the task resolution rate was 17% for zero-shot generation, 27% for generic self-correction, 23% for error-only feedback, and 90% for diagnostic counterexample feedback (A-CEGIS).69% similarUnverifiedOn invalid propositions, using verifier feedback yielded 23/39 accepted counterexamples, while generic feedback without a checker yielded only 15/39.68% similarUnverifiedThe oracle router knows in advance which cases the small model will get wrong, sends only the wrong requests to the large model, and achieves accuracy comparable to always using the large model at only 29% of the cost.68% similarUnverifiedThe 7 models that passed the surrogate test had a change rate of 15.9%, while the 6 models that did not pass had a rate as high as 25.8%, indicating that better-performing models are less susceptible to interference but still more so than the effect of prompt modification.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106290API
curl https://kongchang.com/api/v1/knowledge/claims/1106290MCP
get_claim(id=1106290)