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

arXiv: https://arxiv.org/abs/2610.14523 · HTML: https://mlsanity.com/paper/2610.14523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 6 of 6)

- [CADICA: a new dataset for coronary artery disease detection by using invasive coronary angiography](https://mlsanity.com/paper/2402.00570/) (2024)
- [Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge](https://mlsanity.com/paper/2502.05330/) (2025)
- [ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents](https://mlsanity.com/paper/2609.17523/) (2026)
- [ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments](https://mlsanity.com/paper/2609.19134/) (2026)
- [JEPA-Anything: Learning Predictive Models across Different Worlds](https://mlsanity.com/paper/2609.20800/) (2026)
- [An immune world model for multiscale forecasting and therapeutic hypothesis generation](https://mlsanity.com/paper/2609.14709/) (2026)

## Abstract (arXiv)

ScienceBuddy-PV adapts the ScienceBuddy recursive-in-recursive design to panvascular intervention research through a structured evidence ledger, device-vessel ontology, abstention contract and retained failure bank. Recursive harness optimization and outer-loop model learning, including reinforcement learning, are specified but not executed. We audit a fixed component, rather than the complete agent system, using separate ARCADE syntax and stenosis tasks (1,000 training, 200 validation and 300 test images per task). A shared task-masked convolutional model was trained once per representation setting; its parameters and the heuristic support gate were then held fixed, with the stenosis threshold selected on validation data. On the locked test sets, syntax Dice was 0.475 (95% CI 0.459-0.490) and stenosis Dice was 0.231 (95% CI 0.214-0.249). Stenosis pixel AUROC was 0.957 and AUPRC was 0.180 at prevalence 0.00975. The gate accepted 76.7% of stenosis-frame outputs versus 100% for a score-only comparator. In a constructed mask audit, it accepted 44.3% of reference candidates and rejected 55.7%, exposing the cost of abstention. Acceptance does not establish correctness or clinical safety. This public-data component audit makes support and abstention measurable and provides a reproducible protocol for future collaborative agent studies. It does not demonstrate recursive improvement, patient-level validity or clinical device recommendations.