Structural Rigidity and the 57-Token Predictive Window: A Physical Framework for Inference-Layer Governability in Large Language Models

• URL: http://arxiv.org/abs/2604.03524v1
• Date: Sat, 04 Apr 2026 00:08:17 GMT
• Title: Structural Rigidity and the 57-Token Predictive Window: A Physical Framework for Inference-Layer Governability in Large Language Models
• Abstract summary: Current AI safety relies on behavioral monitoring and post-training alignment.<n> empirical measurement shows these approaches produce no detectable pre-commitment signal.<n>We present an energy-based governance framework connecting transformer inference dynamics to constraint-satisfaction models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current AI safety relies on behavioral monitoring and post-training alignment, yet empirical measurement shows these approaches produce no detectable pre-commitment signal in a majority of instruction-tuned models tested. We present an energy-based governance framework connecting transformer inference dynamics to constraint-satisfaction models of neural computation, and apply it to a seven-model cohort across five geometric regimes. Using trajectory tension (rho = ||a|| / ||v||), we identify a 57-token pre-commitment window in Phi-3-mini-4k-instruct under greedy decoding on arithmetic constraint probes. This result is model-specific, task-specific, and configuration-specific, demonstrating that pre-commitment signals can exist but are not universal. We introduce a five-regime taxonomy of inference behavior: Authority Band, Late Signal, Inverted, Flat, and Scaffold-Selective. Energy asymmetry (Σ\r{ho}_misaligned / Σ\r{ho}_aligned) serves as a unifying metric of structural rigidity across these regimes. Across seven models, only one configuration exhibits a predictive signal prior to commitment; all others show silent failure, late detection, inverted dynamics, or flat geometry. We further demonstrate that factual hallucination produces no predictive signal across 72 test conditions, consistent with spurious attractor settling in the absence of a trained world-model constraint. These results establish that rule violation and hallucination are distinct failure modes with different detection requirements. Internal geometry monitoring is effective only where resistance exists; detection of factual confabulation requires external verification mechanisms. This work provides a measurable framework for inference-layer governability and introduces a taxonomy for evaluating deployment risk in autonomous AI systems.

Related papers

• Curved Inference II: Sleeper Agent Geometry - Extending Interpretability Beyond Probes [0.0]
  This paper extends Anthropic's Sleeper Agents research, which showed artificial backdoors persist through safety training & can be detected by linear probes with >99% accuracy.<n>We introduce a naturalistic methodology using multi-turn context windows that simulates realistic deceptive reasoning without artificial triggers or supervised backdoor insertion.<n> Geometric structure reliably predicts semantic classification, with statistically significant differences in surface area across five prompt strategies & two model families.
  arXiv  Detail & Related papers  (2026-08-25T03:51:20Z)
• Orthogonal JEPA: Factorized Predictive States for Latent World Models [95.20158869896393]
  We introduce method, a latent world-modeling framework based on predictive factorization.<n>We show that method can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure.<n>Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability.
  arXiv  Detail & Related papers  (2026-08-20T13:59:57Z)
• The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models [47.471225029744424]
  Joint-Embedding Predictive Architectures (JEPAs) are the dominant design for latent world models.<n>We show that the choice of anti-collapse regulariser determines whether a JEPA's training objective, a prediction loss plus a weighted embedding regulariser, is a valid Active Inference (AIF) variational free energy.
  arXiv  Detail & Related papers  (2026-07-15T08:59:36Z)
• Monitoring Data-aware Temporal Properties (Extended Version) [56.386411908764494]
  We consider anticipatory monitoring of linear-time properties enriched with an arbitrary SMT theory over finite traces.<n>Anticipatory monitoring in this setting is highly challenging, as the monitoring state depends on both the trace prefix seen so far and all its possible finite continuations.<n>We present and formally prove the correctness of a novel foundational framework for monitoring properties in an expressive fragment offMT.
  arXiv  Detail & Related papers  (2026-05-14T10:23:11Z)
• Noise Titration: Exact Distributional Benchmarking for Probabilistic Time Series Forecasting [1.5939955861266883]
  We propose a paradigm shift toward interventionist, exact-statistical benchmarking.<n>We transform forecasting from a black-box sequence matching game into an exact distributional inference task.<n>We find that state-of-the-art zero-shot models behave consistently with the context-parroting mechanism.
  arXiv  Detail & Related papers  (2026-03-23T17:14:11Z)
• Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures [0.0]
  We introduce governability -- the degree to which a model's errors are detectable before output commitment and correctable once detected.<n>We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models.<n>We propose a Detection and Correction Matrix classifying model-task combinations into four regimes: Governable, Monitor Only, Steer Blind, and Ungovernable.
  arXiv  Detail & Related papers  (2026-03-22T21:50:28Z)
• The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI [0.0]
  This paper introduces a novel auditing framework to quantify latent trait estimation under ordinal uncertainty.<n>The research audits nine leading models across dimensions including Optimization Bias, Sycophancy, and Status-Quo Legitimization.
  arXiv  Detail & Related papers  (2026-02-19T06:56:01Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• CircuChain: Disentangling Competence and Compliance in LLM Circuit Analysis [0.0]
  We introduce CircuChain, a diagnostic benchmark designed to disentangle instruction compliance from physical reasoning competence in electrical circuit analysis.<n>A multi-stage verification pipeline, combining symbolic solvers, SPICE simulation, and an LLM-based error taxonomy, enables fine-grained attribution of failures to convention errors.<n>The strongest model evaluated exhibits near-perfect physical reasoning but a high rate of convention violations when Trap conditions deliberately invert natural sign patterns.
  arXiv  Detail & Related papers  (2026-01-29T06:13:44Z)
• Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence [46.548276232795466]
  Polysemanticity is pervasive in language models and remains a major challenge for interpretation and model behavioral control.<n>We map the polysemantic topology of two small models to identify feature pairs that are semantically unrelated yet exhibit interference within models.<n>We intervene at four loci (prompt, token, feature, neuron) and measure induced shifts in the next-token prediction distribution, uncovering polysemantic structures that expose a systematic vulnerability in these models.
  arXiv  Detail & Related papers  (2025-05-16T18:20:42Z)
• Toward Certified Robustness Against Real-World Distribution Shifts [65.66374339500025]
  We train a generative model to learn perturbations from data and define specifications with respect to the output of the learned model. A unique challenge arising from this setting is that existing verifiers cannot tightly approximate sigmoid activations. We propose a general meta-algorithm for handling sigmoid activations which leverages classical notions of counter-example-guided abstraction refinement.
  arXiv  Detail & Related papers  (2022-06-08T04:09:13Z)
• No Need to Know Physics: Resilience of Process-based Model-free Anomaly Detection for Industrial Control Systems [95.54151664013011]
  We present a novel framework to generate adversarial spoofing signals that violate physical properties of the system. We analyze four anomaly detectors published at top security conferences.
  arXiv  Detail & Related papers  (2020-12-07T11:02:44Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)

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.