Unverified50% confidenceBenchmarkExact time
When recombining rules seen during training, symbolic descriptions match or even exceed the example approach, reaching 99% versus 95% accuracy on new combinations.
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).72% similarUnverifiedIn single-latent ablation experiments, the proportion of cases where the sign predicted by gradients matched the true sign reached 91%–97%, whereas the direction of change suggested by probes was correct only 17%–35% of the time.71% similarUnverifiedIn memory tests, retaining the full context allowed the model to accurately locate specific details mentioned by students 95% of the time, whereas after summary compression the accuracy dropped sharply to 32%.71% similarUnverifiedIn the benchmark test, the heuristic peak rule achieved 93.3% overall accuracy, 100.0% impact recall, and 38.4% cadence false positives, requiring manual threshold tuning.69% similarUnverifiedIn the same reproduction experiment, ResNet-20 achieved a test accuracy of 90.4% and ResNet-56 achieved a test accuracy of 91.7%, with training accuracies of 97.4% and 99.0% respectively.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1028695API
curl https://kongchang.com/api/v1/knowledge/claims/1028695MCP
get_claim(id=1028695)