Certified, Not Explained: Exact Token Erasure in Gated Vision State Space Models

Vision models built on Mamba are often explained through their selective step size Delta, on the assumption that a token the scan does not admit cannot influence the prediction. We test that in a concept bottleneck model for lung-nodule malignancy built on a single gated, bidirectional selective state-space block. The answer becomes an interpretability framework: a guarantee, a procedure that checks it, and a pre-registered audit of what it explains. For a fixed gate pattern, masking the input of the causal convolution of the block and giving closed tokens zero weight at readout makes the concept and task logits exactly invariant to the closed tokens. Gating Delta is neither necessary nor sufficient. On LIDC-IDRI, a path-by-path knockout over 15 cross-validated models agrees with this in every run: the largest logit change is exactly 0 whenever the conditions hold and between 4.1 and 6.7 when they do not. The gated model reaches a pooled out-of-fold AUROC of 0.8425 +/- 0.0085, level with an ungated Mamba bottleneck (0.8428). The guarantee belongs to the masked model, not to the gate as an explanation. Post-hoc rankers, which inherit the guarantee on this model, order tokens better than the gate. Gate maps from a model trained on permuted labels are as close to the real maps as two real-label seeds are to each other. Under retraining, the tokens of the gate carry more task information than random tokens and, on shifted crops, more than central ones, but no more than the tokens chosen by hidden attention. We therefore read the gate as a certified support set produced by mask supervision. Splitting the Oracle Impurity Score into own-concept and cross-concept parts reveals differences the aggregate score misses. Partitioning the readout reduced leakage slightly under an earlier recipe, and the final model sits at, rather than below, the level implied by correlations among the true concepts.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20897
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Certified, Not Explained: Exact Token Erasure in Gated Vision State Space Models

Sadia Parveen, Tehseen Zia
arXiv (Cornell University)
Explainable Artificial Intelligence (XAI)
preprint

Certified, Not Explained: Exact Token Erasure in Gated Vision State Space Models

Sadia Parveen, Tehseen Zia
preprint en

Abstract

Vision models built on Mamba are often explained through their selective step size Delta, on the assumption that a token the scan does not admit cannot influence the prediction. We test that in a concept bottleneck model for lung-nodule malignancy built on a single gated, bidirectional selective state-space block. The answer becomes an interpretability framework: a guarantee, a procedure that checks it, and a pre-registered audit of what it explains. For a fixed gate pattern, masking the input of the causal convolution of the block and giving closed tokens zero weight at readout makes the concept and task logits exactly invariant to the closed tokens. Gating Delta is neither necessary nor sufficient. On LIDC-IDRI, a path-by-path knockout over 15 cross-validated models agrees with this in every run: the largest logit change is exactly 0 whenever the conditions hold and between 4.1 and 6.7 when they do not. The gated model reaches a pooled out-of-fold AUROC of 0.8425 +/- 0.0085, level with an ungated Mamba bottleneck (0.8428). The guarantee belongs to the masked model, not to the gate as an explanation. Post-hoc rankers, which inherit the guarantee on this model, order tokens better than the gate. Gate maps from a model trained on permuted labels are as close to the real maps as two real-label seeds are to each other. Under retraining, the tokens of the gate carry more task information than random tokens and, on shifted crops, more than central ones, but no more than the tokens chosen by hidden attention. We therefore read the gate as a certified support set produced by mask supervision. Splitting the Oracle Impurity Score into own-concept and cross-concept parts reveals differences the aggregate score misses. Partitioning the readout reduced leakage slightly under an earlier recipe, and the final model sits at, rather than below, the level implied by correlations among the true concepts.

arXiv (Cornell University)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon