Unverified50% confidenceBenchmarkExact time
In the setting with condition number 100, when the factors are generated before the readout scaling, RC-DS raises the average sparse factor recovery rate from 0.506 to 0.913, against a baseline of centered logit training under the same budget.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).67% similarUnverifiedDuring training, the held-out FID dropped from 33.7 to 27.0, FD-DINOv2 dropped from 570 to 218, and detector-based object accuracy improved from 65% to 90%.66% similarUnverifiedThe Function Recovery dimension uses a binary threshold of 0.75, where a token similarity score of 0.75 or above counts as passing.64% similarUnverifiedOn the RCAEval RE2-OB microservice root cause localization dataset, Decision-1 correctly identified the root cause service 85 times out of 90 cases, with 94% accuracy, exceeding the 82% of the 'maximum metric deviation' rule-based baseline (McNemar p=0.013).64% similarUnverified当训练窗口、门控窗口和报告窗口未严格分离时，PR-AUC达到0.72到0.76，严格分离后骤降至约0.51接近随机水平，这是数据泄漏的表现64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023668API
curl https://kongchang.com/api/v1/knowledge/claims/1023668MCP
get_claim(id=1023668)