Unverified50% confidenceBenchmarkExact time
On the capability-matched IOI task, when faithfulness is below 85%, the standard-trained model's circuit size leads or is on par with the robust model.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn controlled single-run pre-training comparison experiments, the model trained on the Edu-QuRating-curated mixture achieved higher overall observed accuracy across nine benchmarks than the FineWeb-Edu baseline model, with performance gains concentrated on specific tasks.76% similarUnverifiedIn the first round of optimization, the changes proposed by the Agent focused on directional convolutions, deep supervision, and training strategies, improving mIoU from 0.817 to 0.82.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961075API
curl https://kongchang.com/api/v1/knowledge/claims/961075MCP
get_claim(id=961075)