Exactness Matters for Physical Rule Enforcement

• URL: http://arxiv.org/abs/2605.08285v1
• Date: Fri, 08 May 2026 07:59:59 GMT
• Title: Exactness Matters for Physical Rule Enforcement
• Abstract summary: It remains unclear when stronger physical rule enforcement becomes reliable and when it becomes a source of distribution shift.<n>We study this question through operator exactness, meaning whether the repair map is the identity on the target manifold.<n> Controlled mismatch, screened cleanup, adaptive gating, and external-backbone checks show that the best approximate-regime operating point can be raw or near-identity.
• Score: 4.230349220081444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive scientific forecasters often enforce physical or structural constraints by repairing each predicted state before feeding it back into the model. However, it remains unclear when stronger physical rule enforcement becomes reliable and when it becomes a source of distribution shift. We study this question through operator exactness, meaning whether the repair map is the identity on the target manifold and is aligned with the target geometry. We compare raw forecasting, post hoc repair, and in-loop repair across periodic incompressible Navier--Stokes, non-periodic CFDBench flows, and a hierarchical-forecasting support task. In the exact periodic regime, Fourier projection substantially improves rollout accuracy. On the NS-128 benchmark, a strong Raw-FNO has a final-step rollout MSE at horizon 100 of $(9.390 \pm 6.290)\times 10^{-5}$, and post hoc and in-loop projection reduce it to $(1.130 \pm 0.165)\times 10^{-6}$ and $(5.370 \pm 0.113)\times 10^{-7}$. However, once an exact projection is unavailable and only approximate boundary-preserving cleanup is available, the ordering changes. Across cavity, tube, dam, and cylinder flow, stronger Poisson-based cleanup can reduce divergence while worsening rollout error; target-distortion MSE predicts this harm far better than a linear-system residual. Controlled mismatch, screened cleanup, adaptive gating, and external-backbone checks show that the best approximate-regime operating point can be raw or near-identity. Hierarchical forecasting gives the same broader pattern. Exact forecast reconciliation is a stable baseline, whereas blended top-down repair, a validation-tuned interpolation toward historical-proportion top-down reconciliation, is dataset-dependent. Thus, constraint enforcement should be benchmarked by operator--data alignment before enforcement strength.

Related papers

• MoRF-AST: Calibrated Probabilistic Virtual Sensing for Structural Monitoring under Changing Operating Conditions [10.208843473977094]
  This study proposes Modal Residual Flow Matching with Context-Conditioned Affine Spread Transport (MoRF-AST) for calibrated structural virtual sensing.<n>MoRF achieves a posterior-mean normalized root-mean-square error (NRMSE) of 7.20%, compared with 16.1% and 17.9% for two direct conditional flows.
  arXiv  Detail & Related papers  (2026-08-25T13:16:59Z)
• 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)
• SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers [1.4452289368758382]
  Single-Pass Adaptive Risk is a structured, calibrated, and efficient uncertainty estimate for human motion forecasters.<n>A deterministic backbone predicts the future mean, and a conjugate Bayesian last layer converts time-domain feature leverage into an analytic horizon-wise scale.<n>It ranks first on NLL and on the combined MPJPE+NLL criterion while retaining competitive point accuracy and efficient calibrated tubes.
  arXiv  Detail & Related papers  (2026-08-21T07:20:22Z)
• Online Distributional Prediction via Latent Cluster Geometry Under Drift and Corruption [14.35871574542677]
  We study online distributional prediction under drift and adversarial corruption.<n>A Gibbs quasi-posterior over these configurations yields an online predictor by posterior averaging.<n>We evaluate performance by cumulative Wasserstein-1 regret against the time-varying true law.
  arXiv  Detail & Related papers  (2026-06-17T07:41:41Z)
• Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference [48.78219918881965]
  We propose a principled framework for deriving task-specific strictly proper scoring rules by matching the local curvature of the downstream error metric.<n>We apply this to the Average Treatment Effect (ATE) estimation, deriving a closed-form loss and its corresponding canonical probability mapping.
  arXiv  Detail & Related papers  (2026-06-02T08:41:25Z)
• DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems [49.99655020662206]
  DADF is a distribution-aware debiasing framework for watch-time regression.<n>We evaluate DADF on public short-video benchmarks and a large-scale industrial ranking system.
  arXiv  Detail & Related papers  (2026-05-18T05:14:50Z)
• FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness [13.992146221170543]
  We introduce FragileFlow, a plug-in regularizer that identifies correct-but-fragile predictions and organizes their off-class probability mass into a class-wise vulnerable-risk matrix.<n>Experiments show that FragileFlow consistently improves the proposed theory-facing risk measures over matched baselines.
  arXiv  Detail & Related papers  (2026-05-09T11:25:07Z)
• Reinforcement Learning Trained Observer Control for Bearings-Only Tracking [0.9167082845109437]
  This paper develops a reinforcement learning based observer control policy for autonomous bearings-only tracking of a moving target.<n>The reward function is designed to address two conflicting objectives: minimising absolute target position estimation error and maintaining CKF estimation consistency.<n>The results show that the DQN policy at $= 0.7$ achieves the best trade-off between accuracy and robustness.
  arXiv  Detail & Related papers  (2026-05-04T00:55:14Z)
• Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy [0.0]
  We introduce Perturb-and-Correct (P&C), a method for constructing diverse predictors from a single pretrained network.<n>P&C applies random hidden layer perturbations with a least-squares correction in the subsequent affine layer, producing predictors that agree on calibration data while remaining free to disagree away from it.<n> Empirically, P&C achieves a strong ID/OOD tradeoff across MuJoCo dynamics prediction and CIFAR-10 OOD detection, matching or outperforming standard post-hoc baselines while requiring only a single pretrained model.
  arXiv  Detail & Related papers  (2026-05-02T22:48:11Z)
• Bias-Corrected Adaptive Conformal Inference for Multi-Horizon Time Series Forecasting [0.0]
  Adaptive Conformal Inference (ACI) provides distribution-free prediction intervals with coverage guarantees for time series under distribution shift.<n>When a base forecaster develops persistent bias after a regime change, ACI compensates by widening intervals symmetrically, producing unnecessarily conservative bands.<n>We propose Bias-Corrected ACI (BC-ACI), which augments standard ACI with an exponentially weighted online moving average (EWM) estimate of forecast bias.
  arXiv  Detail & Related papers  (2026-04-14T19:33:59Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting [3.5808917363708743]
  M-FISHER is a method for sequential distribution shift detection and stable adaptation in streaming data.<n>For detection, we construct an exponential martingale from non-conformity scores and apply Ville's inequality to obtain time-uniform guarantees on false alarm control.<n>For adaptation, we show that Fisher-preconditioned updates of prompt parameters implement natural gradient descent on the distributional manifold.
  arXiv  Detail & Related papers  (2025-10-04T15:31:26Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• Optimal Change-Point Detection with Training Sequences in the Large and Moderate Deviations Regimes [72.68201611113673]
  This paper investigates a novel offline change-point detection problem from an information-theoretic perspective. We assume that the knowledge of the underlying pre- and post-change distributions are not known and can only be learned from the training sequences which are available.
  arXiv  Detail & Related papers  (2020-03-13T23:39:40Z)

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.