arXiv AI

Selective Impairment of Motor Recovery from Typing Errors in Parkinson's Disease: A Survival Analysis

arXiv:2607. 24796v1 Announce Type: cross Abstract: Parkinson's disease (PD) affects multiple, dissociable stages of motor and cognitive control.

arXiv Machine Learning
Jul 14

From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint

arXiv:2605. 15862v2 Announce Type: replace Abstract: Understanding adaptive biomechanical systems requires distinguishing observable performance, static multivariate representation, longitudinal displacement, and internal approximation of observed change.

By Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit
arXiv Machine Learning
Sep 10

Detecting and explaining clinical-omics inconsistencies to improve patient cohort stratification: an application to Parkinson's disease

arXiv:2507.03656v2 Announce Type: replace Abstract: Discrepancies between clinical diagnoses and omics profiles within a characterized cohort may reflect misdiagnosis, hidden subgroups or prodromal d...

By Jos\'e A. Pardo-P\'erez, Tom\'as Bernal, Jaime \~Niguez, Ana Luisa Gil-Mart\'inez, Laura Iba\~nez, Jos\'e T. Palma, Juan A. Bot\'ia, Alicia G\'omez-Pascual
arXiv Machine Learning
Aug 10

Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language Models

arXiv:2608. 06429v1 Announce Type: cross Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to produce the observed behavior.

By Yong Yang, Roger Newman-Norlund, Xiang Guan, Saeed Ahmadi, Regan Willis, Nadra Salman, Kalil Warren, Sophie Arheix-Parras, Srihari Nelakuditi, Leonardo Bonilha, Christopher Rorden, Rutvik H. Desai, Julius Fridriksson
arXiv Machine Learning
Sep 17

No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback

The study examines how two small instruction‑tuned language models, Qwen2.5‑1.5B and Llama‑3.2‑1B, respond to user pushback on TriviaQA. When initially correct, the models flip to a wrong answer in about 42–43% of cases, with the effectiveness of different pushback styles varying by model. Attempts to decode capitulation from the pre‑response residual stream fail under a rigorous validation protocol, revealing overfitting and a measurement hazard that underestimates capitulation by 18–24 percentage points.

By Saad Aamir, Muhammad Awais Bin Adil