Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners

• URL: http://arxiv.org/abs/2607.25532v1
• Date: Tue, 28 Jul 2026 10:17:59 GMT
• Title: Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners
• Abstract summary: We show that an in-context learner rationally routes predictions through $S$, not $C$, and fails silently when deployed at a new hospital with different equipment.<n>We derive a closed-form characterisation, $mathrmCSR propto _S/_C$, confirmed at $r = 0.997$ for linear ICL and $r = 0.979$ for TabPFN.<n>We introduce two lightweight mitigations: environment-stratified context construction and S-swap augmentation, that require only weak environment labels and no knowledge of the causal partition
• Score: 10.912482254600478
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Consider a model trained at a single hospital to predict patient recovery, where the measured feature $X$ bundles the patient's true health signal ($C$) with a systematic artefact from that hospital's equipment ($S$). Within that hospital, the artefact correlates with outcomes through unmeasured confounders such as patient demographics; an in-context learner rationally routes predictions through $S$, not $C$, and fails silently when deployed at a new hospital with different equipment. We formalise this as \emph{spurious routing in composite representations}: when a feature $X = [C;\,αS;\,η]$ encodes a causal signal $C$ and a spurious signal $S$ in distinct subspaces, the ICL cannot determine which drives predictions. We prove that under ridge ICL, a linear in-context learner, this routing is unavoidable regardless of context size; TabPFN, a state-of-the-art pretrained tabular ICL model, shows qualitatively consistent behaviour empirically. We derive a closed-form characterisation, $\mathrm{CSR} \propto ρ_S/ρ_C$, confirmed at $r = 0.997$ for linear ICL and $r = 0.979$ for TabPFN. Contrary to intuition, larger context sharpens commitment to the dominant in-context signal, amplifying spurious routing by up to $1.74\times$; in the high-spurious corner, more expressive models show greater vulnerability empirically ($+2.22$ CSR gap at high entanglement). We introduce two lightweight mitigations: environment-stratified context construction and S-swap augmentation, that require only weak environment labels and no knowledge of the causal partition. S-swap reduces spurious routing by $74\%$ for linear ICL and $98.8\%$ for TabPFN, with TabPFN's causal sensitivity increasing $8.4\times$ simultaneously: the model does not become agnostic, it reroutes through the causal signal.

Related papers

• SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models [53.86918766240095]
  Delta-Rule recurrent models maintain a fixed-size state, enabling $O(1)$ inference memory but potentially becoming unstable under extreme-context extrapolation.<n>We propose textbfState Anomaly Neutralization (SANE), which applies adaptive $tanh$ compression at chunk boundaries while preserving the intra-chunk parallel structure.
  arXiv  Detail & Related papers  (2026-08-23T10:41:07Z)
• Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions [51.50375419691955]
  Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty.<n>We study how many samples are necessary and sufficient to learn an $varepsilon$-optimal robust policy under the average-reward criterion.
  arXiv  Detail & Related papers  (2026-08-06T19:49:48Z)
• From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios [10.912482254600478]
  Given a model that is already trained, which features does it rely on causally versus spuriously?<n>We introduce the textbfNormalised Sensitivity Ratio(NSR), a post-hoc, model-agnostic diagnostic for this question.
  arXiv  Detail & Related papers  (2026-07-28T10:26:09Z)
• Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection [0.0]
  We introduce textbfPrism, a framework for structural symmetry diagnosis in complex networks.<n>Prism computes the emphduality defect $(L,P) = |LP - PL|_F / |L|_F$ -- a scalar measuring how far the network deviates from structural self-consistency.
  arXiv  Detail & Related papers  (2026-05-18T04:20:05Z)
• What Do EEG Foundation Models Capture from Human Brain Signals? [64.48249643001402]
  Modern EEG foundation models learn directly from raw signals via self-supervised pretraining.<n>We decompose into three sub-questions: emphwhat does the model learn, emphwhat does the model use, and emphhow much can be explained<n>The audit covers three foundation models (CSBrain, CBraMod, LaBraM), five clinical tasks (MDD, Stress, ISRUC-Sleep, TUSL, Siena), and a 6-family 63-feature lexicon.
  arXiv  Detail & Related papers  (2026-05-12T01:57:53Z)
• Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals [0.0]
  Training-free token reduction methods for Vision Transformers employ different scoring mechanisms, yet they share a closely matched cliff-like collapse at high compression.<n>We develop a diagnostic framework with two tools, ranking consistency $_s$ and off-diagonal correlation $_textoff$, that decomposes the collapse into (1)a signal-agnostic error amplifier inherent to layer-wise reduction.<n>We construct CATIS as a constructive validation: unary signals raise the trigger threshold, triage suppresses the gain.
  arXiv  Detail & Related papers  (2026-04-17T23:26:27Z)
• Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements [66.94250413799232]
  We study mean estimation of a random vector $X$ in a distributed parameter-server-worker setup.<n>Key challenges are adversarial measurements and asynchrony.<n>Results provide a unified finite-time characterization of robustness, identifiability, and statistical efficiency in distributed linear estimation with adversarial workers.
  arXiv  Detail & Related papers  (2026-04-07T11:45:55Z)
• Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions [1.2891210250935148]
  In safety-critical classification, the cost of failure is often asymmetric.<n>We decompose MI into a per-class vector $C_k(x)=_k2/ (2_k)$, with $_k=mathbbE[p_k]$ and $_k2=mathrmVar[p_k]$ across posterior samples.
  arXiv  Detail & Related papers  (2026-02-24T18:05:51Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• In-context Learning for Mixture of Linear Regressions: Existence, Generalization and Training Dynamics [34.458004744956334]
  We prove that there exists a transformer capable of achieving a prediction error of order $mathcalO(sqrtd/n)$ with high probability.<n>We also analyze the training dynamics of transformers with single linear self-attention layers, demonstrating that, with appropriately parameters, gradient flow optimization over the population mean square loss converges to a global optimum.
  arXiv  Detail & Related papers  (2024-10-18T05:28:47Z)
• Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition [71.33787410075577]
  We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses. We propose a new algorithm that attains an $widetildeO(dsqrtHS3K + sqrtHSAK)$ regret with high probability.
  arXiv  Detail & Related papers  (2024-03-07T15:03:50Z)
• Toward Adversarial Robustness via Semi-supervised Robust Training [93.36310070269643]
  Adrial examples have been shown to be the severe threat to deep neural networks (DNNs) We propose a novel defense method, the robust training (RT), by jointly minimizing two separated risks ($R_stand$ and $R_rob$)
  arXiv  Detail & Related papers  (2020-03-16T02:14:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.