Local verification cannot detect non-transportability: a cohomological theory of context preservation in agentic reasoning

• URL: http://arxiv.org/abs/2608.11252v1
• Date: Tue, 04 Aug 2026 21:09:50 GMT
• Title: Local verification cannot detect non-transportability: a cohomological theory of context preservation in agentic reasoning
• Abstract summary: Agentic AI systems routinely transport conclusions across biological, clinical and financial contexts.<n>We show that the emerging safeguard of local verification is structurally incomplete.<n>We quantify the distortion under unequal precision and supply the precision-whitened form that restores exactness.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic AI systems routinely transport conclusions across biological, clinical and financial contexts, and the emerging safeguard is local verification: checking at each step that the entity is representable in the chosen tool, that parameters are compatible, and that outputs cohere with the plan. We prove this class of safeguard is structurally incomplete. Modelling a covering of context space by its nerve and evidence by a real-valued 1-cochain, an agent chaining evidence performs path integration: its conclusion is path-independent if and only if the cochain is exact, and disagreement between valid reasoning paths is exactly the holonomy of a first Cech cohomology class. Hodge decomposition partitions evidence conflict into a gradient part (calibration), a curl part (local inconsistency, visible at triple overlaps) and a harmonic part. Our central result is that no family of simplex-supported consistency checks can distinguish omega from omega+h for harmonic h, which nonetheless generates non-zero disagreement between valid paths; detection requires a statistic on a cycle basis. The resulting procedure, Ksetra, estimates by coboundary projection and gates abstention on the harmonic component, which we give a mechanism: it arises from effect modification combined with overlap-specific population composition, and vanishes to machine precision when effect modification is absent. The degrees of freedom of an evidence network partition into calibration, coherence and transport, yielding an exact F-test for the existence of a global claim; we quantify its distortion under unequal precision and supply the precision-whitened form that restores exactness. Foreign exchange, where the arbitrage-free null makes the cochain exactly a coboundary, serves as a calibration bench: the test is correctly sized, fires on loop arbitrage, and ignores triangular arbitrage.

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)
• TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging [0.48086260459837454]
  We formulate merging as a finite descent problem in which checkpoints are local objects, alignment maps are transitions, and cycle products are residuals.<n>We prove a constant-edge no-go result, frozen-complex three-way and pre-family error-control theorems, and a refinement test for comparison-complex sensitivity.<n>A trained low-rank-adapter audit shows that naive factor averaging depends on the chosen GLr representative, whereas global factor synchronization and dense-delta SVD are stable.
  arXiv  Detail & Related papers  (2026-07-23T03:24:50Z)
• EnTrust: Modeling Inter-Modal Conflict for Trustworthy Multimodal Medical Image Analysis [41.67522319355107]
  EnTrust is a framework that treats inter-modal conflict as the primary source of predictive uncertainty.<n>It achieves state-of-the-art segmentation accuracy while reducing calibration error by 40% compared to the strongest baseline.
  arXiv  Detail & Related papers  (2026-06-19T12:43:50Z)
• What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility [48.10132234701036]
  We propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting.<n>Across multiple architectures and methods, our protocol identifies all failures with wide calibration margins.
  arXiv  Detail & Related papers  (2026-06-19T06:04:17Z)
• Finite Resources False Discovery Rate Control in Structured Hypothesis Spaces [47.16593717985932]
  We present a framework for controlling the false discovery rate when each hypothesis is evidenced only by a finite count of null draws.<n>We present two decision rules that are both robust to structural mis-specification, yet offer a distinct trade-off between exact FDR control and statistical power.
  arXiv  Detail & Related papers  (2026-06-13T16:56:52Z)
• Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels [47.16593717985932]
  We introduce a framework that unifies continuous domains, graphs, and hierarchies under a single algorithm through kernel choice alone.<n>We provide two decision rules which we prove to control the False Discovery Rate (FDR)<n>We validate our method on two sources: spatial locations derived from high-dimensional real-world datasets, and a differential gene expression task utilizing protein-protein interaction graphs.
  arXiv  Detail & Related papers  (2026-05-17T17:42:56Z)
• Multi-Agent System Identification with Nonlinear Sheaf Diffusion [0.8895677230505602]
  Local interaction laws governing multi-agent systems can be difficult to recover from trajectory data.<n>We show that unique recovery from an unconstrained function class is possible if and only if this cohomology vanishes.
  arXiv  Detail & Related papers  (2026-05-11T20:15:03Z)
• UnGAP: Uncertainty-Guided Affine Prompting for Real-Time Crack Segmentation [16.902729686979303]
  Uncertainty-Prompted Feature Modulator (UPFM) treats aleatoric uncertainty as an active visual prompt rather than a mere output.<n>UnGAP balances superior segmentation accuracy with real-time inference speed.
  arXiv  Detail & Related papers  (2026-05-04T09:18:57Z)
• Rare Event Analysis via Stochastic Optimal Control [39.211234628277744]
  We introduce a framework that casts committor estimation as an optimal control (SOC) problem.<n>We develop two complementary objectives: a direct backpropagation loss and a principled off-policy Value Matching loss.<n>On benchmark systems, the framework yields more accurate committor estimates, reaction rates, and equilibrium constants than existing methods.
  arXiv  Detail & Related papers  (2026-04-14T18:34:38Z)
• Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions [0.0]
  In genomics experiments, exchangeability often holds only within subsets of interventions that leave a target variable "unaffected"<n>Our contributions are: (i) a contamination-robust conformal coverage theorem that quantifies how misclassification of "unaffected" calibration examples degrades coverage via an explicit function $g(,n)$ of the contamination fraction and calibration set size; and (ii) a task-driven partial causal learning formulation that estimates only the binary descendant indicators $Z_a,i=mathbf1iinmathrmdesc(a)$ needed
  arXiv  Detail & Related papers  (2026-03-02T18:58:22Z)
• Operationally induced preferred basis in unitary quantum mechanics [0.0]
  The preferred-basis problem and the definite-outcome aspect of the measurement problem persist even if the detector is modeled unitarily.<n>A change of mathematical type constitutes the core of the 'cut': a structurally necessary interface from group-based kinematics to set-based counting.
  arXiv  Detail & Related papers  (2026-01-26T17:22:03Z)
• Depth-Sequence Transformer (DST) for Segment-Specific ICA Calcification Mapping on Non-Contrast CT [38.85617601239779]
  Conventional 3D models are forced to process downsampled volumes or isolated patches.<n>We reformulate the 3D challenge as a textbfParallel Probabilistic Landmark localization task along the 1D axial dimension.<n>We propose the textbfDepth-Sequence Transformer (DST), a framework that processes full-resolution CT volumes as sequences of 2D slices.
  arXiv  Detail & Related papers  (2025-07-10T23:12:12Z)
• Counterfactual Realizability [52.85109506684737]
  We introduce a formal definition of realizability, the ability to draw samples from a distribution, and then develop a complete algorithm to determine whether an arbitrary counterfactual distribution is realizable.<n>We illustrate the implications of this new framework for counterfactual data collection using motivating examples from causal fairness and causal reinforcement learning.
  arXiv  Detail & Related papers  (2025-03-14T20:54:27Z)
• Causal Discovery via Conditional Independence Testing with Proxy Variables [35.3493980628004]
  The presence of unobserved variables, such as the latent confounder, can introduce bias in conditional independence testing. We propose a novel hypothesis-testing procedure that can effectively examine the existence of the causal relationship over continuous variables.
  arXiv  Detail & Related papers  (2023-05-09T09:08:39Z)

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.