Unverified50% confidencePredictionExact time
The current work most likely covers only deterministic tensor operations over integers or exact rational numbers, while floating point and randomness remain open problems to be tackled.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedThe experiment has clear boundaries: a single task (invoice extraction), a single model family, and only 4 repetitions per size point; the 95% confidence interval for 25% is very wide, algorithmic padding is not entirely equivalent to hand-written bloat, and the conclusions should be regarded as a measurement starting point with a clear mechanism rather than a universal constant.70% similarUnverifiedThe paper is currently restricted to discrete-time, finite-state stochastic processes; extensions to continuous-state/continuous-time processes and estimation methods for real data remain open gaps.70% similarUnverified实际部署中因并行计算的浮点非确定性可能产生细微差异并随链式生成放大70% similarUnverifiedIf the number of attempts per accepted task drifts above 2, it means the prompt is guessing rather than working, and no amount of free capacity can fix that.69% similarUnverified纯LLM探索模式在确定性任务上成功率难以保障，因每次推理存在随机性68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063454API
curl https://kongchang.com/api/v1/knowledge/claims/1063454MCP
get_claim(id=1063454)