Unverified50% confidenceBenchmarkExact time
Through 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
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.77% similarUnverifiedThe authors extend the experiments to longer training budgets, OLMo-style backbones, and sparse mixture-of-experts (MoE) models, observing consistent gains in all cases.74% similarUnverifiedTraining can be completed concentrated in a few supercomputing clusters, but inference is an ongoing expense, and lowering the cost per token of inference helps seize the initiative in AI product gross margins.74% similarUnverifiedAdversarial training (AT) improves model robustness by generating adversarial examples during training and including them in training, but it incurs enormous memory overhead and involves a trade-off between clean accuracy and robust accuracy.74% similarUnverifiedOne of the paper's core findings is that increasing training length may be exponentially more efficient than increasing the number of samples.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114590API
curl https://kongchang.com/api/v1/knowledge/claims/1114590MCP
get_claim(id=1114590)