arXiv AI

Intervention anchors and scientific verification in synthetic vascular predictive representations

The paper introduces intervention anchors to bind latent directions to named interventions in synthetic vascular predictive models. It demonstrates that capacity‑matched least‑squares predictors are equivalent under fixed output transforms, while anchor‑only observers only recover interpretations within known perturbation signatures. Extensive synthetic audits across multiple configurations and fault classes confirm prediction equivalence, identify reconstruction violations, and illustrate the need for calibration stability and verified transport when changing representation bases.

arXiv AI

Oct 2

On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models

The paper introduces a formal framework and benchmark for time‑series world models (TSWMs) that separates state, actions, and exogenous inputs, and defines a new metric called mechanism consistency to evaluate whether model predictions move in the expected direction when actions change. Experiments on eight public datasets show that using a frozen latent prediction space and gated output fusion improves prediction accuracy, while prediction error and mechanism consistency often diverge, with the best‑performing models sometimes failing to exhibit consistent directional responses. Adding a directional supervision loss significantly boosts mechanism consistency without affecting mean‑absolute error, providing a practical recipe for building more reliable TSWMs.

By Haochen Zhang, Jiaheng Guo, Zhen Xu, Zachary Plotkin, Nicholas Konz, Zhen Tan, Tianlong Chen

diffusion benchmarks

arXiv AI

Aug 21

Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating

arXiv:2607. 19020v2 Announce Type: replace-cross Abstract: Clinical decision support degrades as treatment protocols evolve, but the obstacle to updating a deployed model is governance as much as accuracy: once retraining touches every parameter, no one can say afterwards where the update acted.

By Fatema Ferdous Tamanna, K. M. Merajul Arefin, Md. Abdul Masud

arXiv AI

Sep 11

Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents

The paper introduces Cros, a risk‑constrained stopping layer for sequential clinical diagnosis agents that determines when to stop testing and make a diagnosis. Cros combines state‑wise error ranking, policy design on disjoint development splits, and exact tests of selective diagnostic error to provide finite‑sample guarantees. On a MIMIC‑derived abdominal‑pain benchmark, Cros achieves higher state‑error AUROC and lower selective error rates compared to baseline stopping methods, though its performance varies across development resplits.

By Yuexin Wu, Vasile Rus

agents benchmarks safety

arXiv AI

Aug 24

Anatomy-Informed Neural Networks: Encoding Anatomic Priors in Loss and Architecture, with an SE(3) Formulation of Guidewire-Induced Aortoiliac Deformation

The paper introduces Anatomy-Informed Neural Networks (AINN), which embed soft and hard anatomical priors into the loss function and network architecture to prevent anatomically impossible predictions. AINN is applied to a clinical scenario of aortoiliac deformation caused by a guidewire, modeling vessel and wire dynamics in SE(3) and training with a Wasserstein-2 loss from 2D angiograms. The study verifies the kinematics and loss against ground truth but does not yet train a network, outlining future work to apply the model to real CT data.

By David P. Stonko

agents

arXiv Machine Learning

Sep 24

Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models

The paper introduces CELLAUDIT, a method for auditing whether inputs claimed to influence predictive models actually do so. By testing if an input can enter the computation, whether predictions depend on it, and if that dependence improves observed responses, the authors evaluate agent-generated predictors on a morphology‑transcriptomics benchmark (BBBC047). Their findings show that many models claim compound contributions that are not supported by the data, and that falsification‑guided revisions can recover genuine input effects while improving performance.

By Mengran Li, Bo Li, Chengyang Zhang, Yang Yan, Jinfeng Xu, Zhenchao Tang

agents benchmarks

arXiv AI

Oct 15

ScienceBuddy-PV: A Verifier-Governed Recursive Improvement Protocol for Panvascular Intervention Research

arXiv:2610.14523v1 Announce Type: new Abstract: ScienceBuddy-PV adapts the ScienceBuddy recursive-in-recursive design to panvascular intervention research through a structured evidence ledger, device...

By Lingsen You, Yujun Guo, Xinyu Zhong, Zijie Feng, Wentong Wang, Li Shen, Junbo Ge

agents reinforcement-learning safety

Hugging Face Trending Papers

Sep 22

Testing-Driven Reliability Audit of Trajectory-Based Early Outcome Prediction for LLM Agents: Target-Specific Calibration Transfer Persists Within a Single Benchmark

Predicting early outcomes based on trajectory can decrease the expenses associated with agent evaluation by terminating a run once the outcome becomes sufficiently predictable, assuming that the predi...

llms agents benchmarks

arXiv AI

Oct 26

Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography

arXiv:2605.10871v3 Announce Type: replace-cross Abstract: We present Attractor-Vascular Coupling Theory (AVCT), a theory-guided framework for deriving interpretable blood pressure (BP) predictors fro...

By Timothy Oladunni, Farouk Ganiyu Adewumi

arXiv Machine Learning

Sep 21

Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization

arXiv:2609.21197v1 Announce Type: new Abstract: Sparse longitudinal CT follow-up limits lesion-size forecasting when only a few prior observations are available. We constructed a five-visit DLT-deriv...

By Lingfei Kong

benchmarks

arXiv Machine Learning

Aug 14

Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology

arXiv:2608. 13518v1 Announce Type: new Abstract: Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint.

By Yunsung Chung, Yingshuo Liu, Abboud F. Hassan, Han Feng, Mary M. Maleckar, Nassir Marrouche, Jihun Hamm

rag benchmarks

arXiv Machine Learning

Aug 12

HIPNO: Symmetry-Aware Physics-Informed Neural Operators for Noninvasive Hemodynamic Inference

arXiv:2608. 10011v1 Announce Type: cross Abstract: Continuous hemodynamic monitoring guides treatment decisions in surgery and intensive care.

By Yunbei Pan, Jiahang Sha, Simon A. Lee, Maxime Cannesson, Wei Wang, Jeffrey N. Chiang

arXiv AI

Oct 15

Audit Before You Update: Recording Artifacts and the Limits of Bounded Model Updates in MIMIC-IV ICU Prediction

The paper investigates how to evaluate bounded model updates for ICU prediction models using the MIMIC‑IV database. After auditing the data for recording artifacts and cleaning it, the authors compare a bounded update that retrains only treatment‑context and fusion parameters with full fine‑tuning across two model families and two targets, finding that bounded updates are non‑inferior or superior in most cases but depend on target, model family, and learning‑rate tuning. The study also shows that audits should precede update evaluation and that the update boundary should be chosen per target.

By Fatema Ferdous Tamanna, K. M. Merajul Arefin, Md. Abdul Masud

fine-tuning

Related stories