SEAM: Global consistency beyond local accuracy in scientific machine learning

• URL: http://arxiv.org/abs/2608.05702v1
• Date: Thu, 06 Aug 2026 07:45:23 GMT
• Title: SEAM: Global consistency beyond local accuracy in scientific machine learning
• Abstract summary: We introduce Scientific Explanation-Admissibility Machines (SEAM), a generator-agnostic framework that makes local-to-global consistency question computable across regions, sensors, regimes, and model components.<n>SEAM detects incompatible explanations even when local predictions are accurate, and attributes failures to specific channels and overlaps.<n>It adds a global explanation-consistency audit to existing solvers and learning models, testing whether their local explanations form a coherent scientific account.
• Score: 3.1861308132183375
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific machine learning commonly validates models at the level of a subdomain, a benchmark split, or an explanation for one prediction. Yet such local checks cannot establish whether the resulting explanations can be assembled into one globally admissible explanation. We introduce Scientific Explanation-Admissibility Machines (SEAM), a generator-agnostic framework that makes this local-to-global consistency question computable across regions, sensors, regimes, and model components. The finite explanation-sheaf instantiation SEAM-$Ω$ represents each region by a structured explanation with state, closure, and observation channels together with optional contract metadata; compares neighboring explanations on their overlaps; and converts disagreement into a channel-resolved obstruction. This obstruction locates inconsistency and tests competing declared accounts by restricting each repair to the revisions that one account permits. Exact feasibility refutes or retains an account; when exact repair is unavailable, residual-aware regularized records provide a separately labeled empirical attribution. The framework also separates inconsistency from non-identifiability and monitors learned generators under distribution shift. We establish theorems for minimum-cost intervention and conservation-contract detectability, together with companion results for identifiability and closure recoverability. Across nineteen experiments involving synthetic partial differential equation systems and out-of-distribution Fourier neural operator (FNO) monitoring, SEAM detects incompatible explanations even when local predictions are accurate, and attributes failures to specific channels and overlaps. SEAM adds a global explanation-consistency audit to existing solvers and learning models, testing whether their local explanations form a coherent scientific account.

Related papers

• Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing [0.0]
  An image editor may satisfy every plausibility constraint separately even when no single latent explanation fits the complete output.<n>We formalize this local-to-global failure using a common witness grade and witness nerve.
  arXiv  Detail & Related papers  (2026-09-03T15:09:52Z)
• GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification [17.595478415811687]
  Multimodal classification typically assumes all modalities are available, yet real-world inputs are often incomplete.<n>We propose GAUGE, a lightweight counterfactual gating framework for incomplete multimodal classification.<n>GAUGE scores the counterfactual effect of replacing every unit with a reference representation through prediction-aware Taylor evidence scores.
  arXiv  Detail & Related papers  (2026-08-06T05:07:14Z)
• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• Spectral Audit of In-Context Operator Networks [11.073238833758564]
  We introduce a Jacobian-based spectral audit for in-context operator learning.<n>Our results suggest that prediction accuracy and local operator fidelity are distinct properties of learned neural operators.
  arXiv  Detail & Related papers  (2026-06-01T16:04:21Z)
• When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection [56.362776482614976]
  We study anomaly detection in a setting where constraints are given as logical rules over learned visual concepts.<n>We propose a neural rule evaluator that compiles each constraint into a directed acyclic graph and learns feature-aware subtree gates.<n>Across CLEVRER, OpenImages, and VidOR, the resulting evaluator improves rule-level anomaly AUROC over independent-events and same-image semantic-training baselines.
  arXiv  Detail & Related papers  (2026-05-25T02:52:36Z)
• Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation [0.0]
  ESG and climate risk data remain fragmented across heterogeneous Scope 1, Scope 2, and Scope 3 reporting environments.<n>This paper proposes a deterministic climate risk intelligence framework integrating single source of truth orchestration, temporal anomaly detection, imbalance aware ensemble learning, and explainability oriented governance.
  arXiv  Detail & Related papers  (2026-05-23T13:33:00Z)
• LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition [55.572260012037084]
  We introduce LC-ERD (Logic-Consistent Endogenous Reward Decomposition), a framework framing self-alignment as latent structure mining.<n>We derive a Variational Logic Potential by aggregating consensus from the model's Latent Logic Expertise.<n>Experiments show LC-ERD delivers a robust self-evolution path, uncovering trade-offs between logic consistency and accuracy.
  arXiv  Detail & Related papers  (2026-05-19T07:27:50Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• Discovery of Hidden Miscalibration Regimes [52.452902154360565]
  Models may be systematically overconfident on some kinds of inputs and underconfident on others.<n>We define the corresponding miscalibration field and propose a diagnostic framework for estimating it.<n>Our approach learns a calibration-aware representation of the input space and estimates signed local miscalibration by kernel smoothing in the learned geometry.
  arXiv  Detail & Related papers  (2026-05-13T13:07:50Z)
• Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation [5.191980417814362]
  LLM agents excel when environments are mostly static and the needed information fits in a model's context window.<n>ReAct-style agents are especially brittle in this regime.<n>We propose EoG, a framework in which an LLM performs bounded local evidence mining and labeling (cause vs symptom) while a deterministic controller manages, state, and belief propagation to compute a minimal explanatory frontier.
  arXiv  Detail & Related papers  (2026-01-25T17:27:19Z)
• Change Detection for Local Explainability in Evolving Data Streams [72.4816340552763]
  Local feature attribution methods have become a popular technique for post-hoc and model-agnostic explanations. It is often unclear how local attributions behave in realistic, constantly evolving settings such as streaming and online applications. We present CDLEEDS, a flexible and model-agnostic framework for detecting local change and concept drift.
  arXiv  Detail & Related papers  (2022-09-06T18:38:34Z)

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.