Imagen de Portada

Cross-Entropy Is Load-Bearing: A Pre-Registered Scope Test of the K-Way Energy Probe on Bidirectional Predictive Coding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Cacioli, Jon-Paul
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning I.2.6
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

K-Way Energy Probes for Metacognition Reduce to Softmax in Discriminative Predictive Coding Networks
por: Cacioli, Jon-Paul
Publicado: (2026)

Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B
por: Cacioli, Jon-Paul
Publicado: (2026)

Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning
por: Cacioli, Jon-Paul
Publicado: (2026)

Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries
por: Cacioli, Jon-Paul
Publicado: (2026)

Repetition Without Exclusivity: Scale Sensitivity of Referential Mechanisms in Child-Scale Language Models
por: Cacioli, Jon-Paul
Publicado: (2026)

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
por: Kumar, Sachin
Publicado: (2026)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
por: Fadli, Samih
Publicado: (2025)

On the Role of Pre-trained Embeddings in Binary Code Analysis
por: Maier, Alwin, et al.
Publicado: (2025)

Load and Renewable Energy Forecasting Using Deep Learning for Grid Stability
por: Sarkar, Kamal
Publicado: (2025)

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
por: Adapala, Sai Teja Reddy
Publicado: (2025)

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels
por: Lorup, Alexander Boesgaard
Publicado: (2026)

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
por: Zhang, Gongbo, et al.
Publicado: (2026)

Reversible GNS for Dissipative Fluids with Consistent Bidirectional Dynamics
por: Huang, Mu, et al.
Publicado: (2025)

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
por: Panuganti, Rajkiran
Publicado: (2026)

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
por: Hedar, Abdel-Rahman, et al.
Publicado: (2024)

Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?
por: Innocenti, Francesco, et al.
Publicado: (2024)

Weber's Law in Transformer Magnitude Representations: Efficient Coding, Representational Geometry, and Psychophysical Laws in Language Models
por: Cacioli, Jon-Paul
Publicado: (2026)

GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets
por: Wu, Qiming, et al.
Publicado: (2024)

Universal Transformers Need Memory: Depth-State Trade-offs in Adaptive Recursive Reasoning
por: Sapunov, Grigory
Publicado: (2026)

Towards Understanding Sycophancy in Language Models
por: Sharma, Mrinank, et al.
Publicado: (2023)

Characterizing Pattern Matching and Its Limits on Compositional Task Structures
por: Chang, Hoyeon, et al.
Publicado: (2025)

Fusion-Based Neural Generalization for Predicting Temperature Fields in Industrial PET Preform Heating
por: Alsheikh, Ahmad, et al.
Publicado: (2025)

Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions
por: Elkins, Katherine, et al.
Publicado: (2025)

Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
por: Kohlberger, Björn Roman
Publicado: (2026)

Resource for Error Analysis in Text Simplification: New Taxonomy and Test Collection
por: Vendeville, Benjamin, et al.
Publicado: (2025)

JANUS: Structured Bidirectional Generation for Guaranteed Constraints and Analytical Uncertainty
por: Racicot, Taha
Publicado: (2026)

Entropy Causal Graphs for Multivariate Time Series Anomaly Detection
por: Febrinanto, Falih Gozi, et al.
Publicado: (2023)

A Hierarchical Error Framework for Reliable Automated Coding in Communication Research: Applications to Health and Political Communication
por: Zhao, Zhilong, et al.
Publicado: (2025)

Manipulating Predictions over Discrete Inputs in Machine Teaching
por: Wu, Xiaodong, et al.
Publicado: (2024)

The Drill-Down and Fabricate Test (DDFT): A Protocol for Measuring Epistemic Robustness in Language Models
por: Baxi, Rahul
Publicado: (2025)

Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
por: He, Langzhou, et al.
Publicado: (2026)

Inference Time Causal Probing in LLMs
por: Khorasani, Sadegh, et al.
Publicado: (2026)

Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
por: Ribeiro, José, et al.
Publicado: (2022)

LLM attribution analysis across different fine-tuning strategies and model scales for automated code compliance
por: Shi, Jack Wei Lun, et al.
Publicado: (2026)

SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use
por: Patel, Hitesh Laxmichand, et al.
Publicado: (2025)

What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
por: Zhang, Xinyu
Publicado: (2026)

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
por: Cho, Seonglae, et al.
Publicado: (2026)

In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification
por: Liu, Ming
Publicado: (2026)

No Free Swap: Protocol-Dependent Layer Redundancy in Transformers
por: Garcia, Gabriel
Publicado: (2026)

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries
por: Dragoi, Marius, et al.
Publicado: (2025)