AIMay 27

BuddyBench: A Privacy-Constrained Multi-Task Benchmark for Pediatric Social-Communication Personalization

arXiv:2605.2808929.2h-index: 1
AI Analysis

This benchmark addresses the lack of privacy-preserving, multi-task datasets for personalizing pediatric social-communication interventions, but is domain-specific and incremental in combining existing data types.

BuddyBench introduces a privacy-constrained multi-task benchmark linking drill-level learning trajectories, clinical assessments, and treatment endpoints for pediatric social-communication personalization, enabling knowledge tracing, recommendation, prediction, and causal inference tasks with baselines showing signal across tasks.

BuddyBench introduces a privacy-constrained multi-task benchmark for pediatric social-communication personalization. Unlike existing neurodevelopmental repositories that primarily emphasize imaging, genetics, or cross-sectional clinical phenotyping, BuddyBench links drill-level learning trajectories, standardized clinical assessments, BuddyPlan self-report, and randomized-treatment endpoints within a unified benchmark schema. BuddyBench combines two cohorts: ND-03 is an observational cohort with dense drill coverage for Tasks1-2 (n = 189), and ND-02 is a randomized controlled trial cohort for Tasks3-4 (n = 86 ITT). Together, they support knowledge tracing, next-drill recommendation, clinical prediction, and causal inference, linking behavioral personalization to clinical evaluation. We additionally introduce BuddyBench-Sim, a synthetic companion dataset for reproducible evaluation. Baselines show signal across tasks while keeping pediatric clinical records protected.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes