Unverified50% confidenceBenchmarkExact time
Under matched training conditions with training sample sizes from 10^5 to 10^6, ΦasmaNet shows advantages in comparisons against baseline models such as MLP, 1D-ResNet, and Transformer-encoder.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
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.72% similarUnverifiedTraining only the classification head (freezing the entire backbone) suits scenarios with a sample size in the hundreds to thousands and with classes semantically close to ImageNet, but the model's ability to adapt to domain shift is almost zero.71% similarUnverifiedThrough controlled experiments (the same MLP architecture, the same hyperparameter search space, and the same number of training epochs, with only the input representation differing), the paper shows that Assur-derived features have a geometric-mean 1.8x advantage in sample efficiency, covering training budgets from 50 to 10,000 mechanisms.71% similarUnverifiedOn 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.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134732API
curl https://kongchang.com/api/v1/knowledge/claims/1134732MCP
get_claim(id=1134732)