Unverified50% confidenceBenchmarkExact time
In the configuration with eight players and two impostors using second-league bots, the trained network's crew win rate was 52.0%, with an average of 0.99 impostors ejected per round, whereas gpt-oss in the turn-based Q&A format won only 2 of 16 rounds (12.5%), ejected 0.06 impostors per round, and wrongly ejected 0.94 innocent crewmates.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the strictly comparable experiment with fifteen players and three impostors in the sixth league, the trained network's crew win rate over 300 rounds was 93.3%, while gpt-oss under the dialogue+intuition format won 16 of 20 rounds (80%), with a one-sided Fisher exact test p = 0.052.75% similarUnverifiedAfter adding the trained network's intuition to the eight-player configuration and using the turn-based Q&A format, gpt-oss as crew won 8 of 16 rounds, almost indistinguishable from the network baseline (p = 0.54).70% similarUnverifiedWhen sampling eight candidates without constraints from the model, 10.2% of inputs cannot produce any valid output under limited training data, and this proportion drops to 0.4% when using the full training data61% similarUnverified82.7% of reachable sites have a robots.txt; 25.1% block at least one search or answer crawler, and 10.2% block most of them; 26.0% block at least one training crawler, but only 2.6% block only training crawlers while keeping search and answer crawlers open; 2.5% carry Content-Signal directives, and 62.4% list a sitemap.61% similarUnverifiedIn the eight-player configuration, the win-rate gap between gpt-oss and the trained network had a one-sided Fisher exact test p = 0.0017, far beyond random fluctuation.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042913API
curl https://kongchang.com/api/v1/knowledge/claims/1042913MCP
get_claim(id=1042913)