Unverified50% confidenceFactExact time
Standard Mamba performs unidirectional causal scanning along the sequence direction, so each position can only aggregate information preceding it; this inductive bias originates from autoregressive tasks such as language modeling, and when transferred to PDE spatial field modeling it introduces direction-dependent bias.
1
Sources
50%
Confidence
Long-term
Relevance
11/9/2026
First Seen
Sources
Related Entities
Related Claims
Unverified模型实际提交顺序几乎形成从左到右的三角形,源于Mamba状态空间模型的因果方向性偏置74% similarUnverifiedTypical representatives of state space models include S4, Mamba and others, which write the recurrence as a continuous differential equation or discrete linear recurrence and achieve efficient parallel training with the help of convolution or selective scan.73% similarUnverifiedMamba reduces sequence modeling complexity to linear time through an input-dependent selective mechanism and a hardware-aware parallel scan algorithm, while retaining the ability to model long-range dependencies.71% similarUnverifiedLand surface forecasting systems based on Mamba-series structured state space models absorb non-stationary confounding events into the state transition matrix, leading to persistent prediction bias.70% similarUnverifiedSelective scan is the core operation of the Mamba family of SSMs, and its discretization parameter Δ, input matrix B and output matrix C all change dynamically with each token.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1150259API
curl https://kongchang.com/api/v1/knowledge/claims/1150259MCP
get_claim(id=1150259)