CORTEXA
← Browse
arxivcs.LGcs.AI2026-07-07

At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics

Truong Xuan Khanh

On modular arithmetic, a network's embedding keeps compressing for tens of thousands of steps after it has already generalized. Reading effective rank at the grokking transition overstates the converged value by 3-5x on an MLP, and by 1.3-1.5x on a transformer trained to convergence; on the MLP it also erases which cells compress at all. Compression lags the accuracy transition by an amount on the order of the time-to-grok, at least 10,000 steps, rather than coinciding with it. A one-variable ablation shows what sets the lag size: adding LayerNorm to an otherwise identical transformer moves the fraction of compression done by the grok step from 0.87 to 0.25, and a pre-registered control rules out scale invariance as the mechanism. We package this as an audit that separates onset from compression, flags censoring, excludes boundary cells that never fully generalize, and checks that the reference floor has plateaued, with an adversarial suite that caught a false-confidence bug in our own branch. A secondary, MLP-specific depth law linking norm budget to converged floor fails a generality test on a transformer and flips sign under free weight decay. Code and the toolkit are released.

View free PDFSource page

Related papers

arxivcs.LGcs.AI2026-07-24

CEL: Comprehensive Counterfactual Explanations Library and Benchmark

Oleksii Furman, Łukasz Lenkiewicz, Marcel Musiałek, Maciej Zięba

Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's prediction to a desired outcome. While early methods primarily focused on minimal feature changes, recent w…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-31

TAVI-TEC: An AI-Based Tool for Procedural Planning of Transcatheter Aortic Valve Implantation

Alessandra Zerillo, Stefano Cannata, Diego Bellavia, Daniele Ciriello, Simone Manini, Salvatore Pasta, et al.

Computed tomography angiography (CTA) is crucial for preprocedural TAVI planning, providing the anatomical information required for prosthesis sizing and vascular access assessment. As the volume of TAVI procedure increases, improving efficiency and standardizing annotations is b…

View free PDFSource page
arxivmath.OCcs.AIcs.LG2026-07-23

Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$

Dawei Li, Xiaotian Jiang, Mingyi Hong

Barzilai--Borwein (BB) method has shown strong practical performance in continuous optimization, yet its convergence dynamics remains poorly understood. In particular, a central unresolved question is whether BB converges superlinearly for almost every strictly convex quadratic p…

View free PDFSource page
arxivcs.LGcs.AIcs.CV2026-07-31

SERUM: State Extraction and Refinement for User Modeling

Andy J. Phu, James Mooney, Karin de Langis, Khanh Chi Le, Dongyeop Kang

Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow. However, building these models from raw, unstructured screen activity remains an open challenge. We present SERUM, a multi-pass framework that extracts finite…

View free PDFSource page
arxivcs.LGcs.AIcs.CV2026-07-31

A Human-Centered Validation of the Explainability-Performance Coefficient

Christian Oliva, Luis F. Lago-Fernández

The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI). However, objectively evaluating explanation fidelity and aligning XAI metrics with human-centered understanding remain critical open…

View free PDFSource page