Unverified50% confidenceBenchmarkExact time
In a synthetic logistic regression classifier experiment, after 80 steps of gradient-ascent-based repair, the unlearning loss rose from 0.0545 to 0.1649, yet the trigger attack success rate remained 100%.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn dependency tasks, memory raised the success rate from a leakage-verified baseline of 0.00 to 0.55–1.00.78% similarUnverifiedAfter introducing an explicit resolver to handle information supersession relationships, stale-memory failures dropped to zero and overall accuracy jumped from 33% to 78%.76% similarUnverifiedIn the final round of experiments, the composite evaluation score improved by 0.0903, and zero-score conversations decreased by 40%.70% similarUnverifiedEvidence-driven pre-improvement validation improved precision from 58.6% to 72.3%, and reduced unsupported objectives per round from 1.93 to 0.50.70% similarUnverifiedThe power-law exponent between test loss and compute is approximately 0.05, meaning that every 10x increase in compute yields approximately a 12% improvement in model performance.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998826API
curl https://kongchang.com/api/v1/knowledge/claims/998826MCP
get_claim(id=998826)