Unverified50% confidenceBenchmarkExact time
Three annotators, following a written guideline, reached a Fleiss' kappa of 0.788 agreement on 816 data items.
1
Sources
50%
Confidence
Long-term
Relevance
11/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the REA demonstration, the rewritten function passed 3,205 test cases, and all 63 bytes of the compiled output were identical.60% similarUnverifiedOn the 14-clause evaluation set, gemma3:4b achieved 50% classification accuracy (13 of 14 clauses were judged yes) and 100% verbatim excerpt accuracy (all 14 quotes matched verbatim).57% similarUnverifiedThe full computation retained 605,349,215 occupied sets and 1,863,925,136 states, ultimately proving that 93 steps is optimal.56% similarUnverifiedThe complete system achieved an accuracy of 77.3% across six simulator-derived report fields.56% similarUnverifiedThe authors obtained 2,213 generation trajectories, 2,108 planning trajectories, and 2,013 rounds of validation improvement data from 4,003 candidates, which were used for supervised fine-tuning of Qwen3-8B-27B.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1158009API
curl https://kongchang.com/api/v1/knowledge/claims/1158009MCP
get_claim(id=1158009)