Unverified50% confidenceBenchmarkExact time
On the Sudoku-Extreme benchmark, EBRs achieve 99.9% accuracy while using 345 times less inference compute than the next-best model, with training compute kept at a comparable level.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/9/2026
First Seen
Valid until: 2/7/2027
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).72% similarUnverifiedIn the class-incremental drift scenario, the accuracy drop of EWC and naive fine-tuning reaches as high as 16.2%–28.5%, far exceeding the 1.8%–5.8% of experience replay.69% similarUnverifiedWhen using the multi-agent verification process, MARCH's accuracy was suppressed to 4.4%, whereas when the same model was directly asked which solution was better, accuracy reached 43.7%.67% similarUnverifiedWhen recombining rules seen during training, symbolic descriptions match or even exceed the example approach, reaching 99% versus 95% accuracy on new combinations.67% similarUnverifiedOn the LibriSpeech test-clean/test-other datasets, Oído's on-device computation achieves a word error rate of 3.70% / 8.23%, differing from the full-precision version by only 0.12 percentage points.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1150159API
curl https://kongchang.com/api/v1/knowledge/claims/1150159MCP
get_claim(id=1150159)