Unverified50% confidenceBenchmarkExact time
The study tests two binary classification tasks: determining the ideological direction of rulings (baseline F1 without removal approximately 0.68) and distinguishing constitutional from non-constitutional laws (baseline F1 approximately 0.92).
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe authors conducted a small-scale, reproducible pilot experiment on a publicly available rule test set to demonstrate the difference between warrant metrics and existing metrics.66% similarUnverifiedThe chi-square test is suitable for comparing differences in citation occurrence rates between two groups of prompts, while the Mann-Whitney U test is more appropriate for comparing mean citation counts.62% similarUnverifiedThe paper identifies limitations of existing evaluation paradigms by name, including answer accuracy, citation existence, general attribution, LegalHalBench-style statutory relevance, and CitaLaw-style sentence-citation alignment.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931167API
curl https://kongchang.com/api/v1/knowledge/claims/931167MCP
get_claim(id=931167)