aiqbench analysis
This research introduces SPAR, a wearable system leveraging frozen time-series foundation models and transformers to classify boxing techniques with explainable feedback at multiple levels. By attributing performance metrics to specific joint movements and kinetic chains, the study addresses the critical gap between simple action classification and actionable skill assessment in sports analytics. The approach demonstrates how interpretable machine learning can bridge the divide between raw sensor data and practical coaching insights for athletes.
Skill Profiling with Attributable Reasoning (SPAR): A Wearable Analysis System for Boxing
arXiv:2609.30753v1 Announce Type: cross Abstract: A punch is a ballistic, full-body action driven by a kinetic chain running from the legs through the trunk to the arm, where a small sequencing error separates a scoring strike from a miss. Wearable sensors can capture this movement in the gym, but most deployable systems only classify which punch was thrown rather than assess how well it was thrown. We present Skill Profiling with Attributable Reasoning (SPAR), an eight-IMU garment and pressure-insole system that classifies each punch as expert or novice and treats an explanation of that prediction as feedback. Feedback is only useful if the person receiving it can act on it, so SPAR explains the prediction at three tiers, a per-joint attribution for the analyst, a counterfactual over kinetic-chain layers for the coach, and a plain-language narrative of the two for the athlete. Across 17 participants and 4,713 punches, SPAR reaches a leave-one-participant-out AUC of 0.842 (95% CI [0.769, 0.907] over participants). A frozen time-series foundation model encodes the joint-angle and plantar-force series, and a small transformer trained on the cohort classifies the encoding. We audit the two quantitative tiers and report six themes from a thematic analysis of interviews with six practicing boxing coaches.
Abstract:A punch is a ballistic, full-body action driven by a kinetic chain running from the legs through the trunk to the arm, where a small sequencing error separates a scoring strike from a miss. Wearable sensors can capture this movement in the gym, but most deployable systems only classify which punch was thrown rather than assess how well it was thrown. We present Skill Profiling with Attributable Reasoning (SPAR), an eight-IMU garment and pressure-insole system that classifies each punch as expert or novice and treats an explanation of that prediction as feedback. Feedback is only useful if the person receiving it can act on it, so SPAR explains the prediction at three tiers, a per-joint attribution for the analyst, a counterfactual over kinetic-chain layers for the coach, and a plain-language narrative of the two for the athlete. Across 17 participants and 4,713 punches, SPAR reaches a leave-one-participant-out AUC of 0.842 (95% CI [0.769, 0.907] over participants). A frozen time-series foundation model encodes the joint-angle and plantar-force series, and a small transformer trained on the cohort classifies the encoding. We audit the two quantitative tiers and report six themes from a thematic analysis of interviews with six practicing boxing coaches.
Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
arXiv:2609.30753 [cs.HC]
(or arXiv:2609.30753v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2609.30753 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 296 words
Related coverage
Automating Performance Bottleneck Identification with the TraceLens Agent
AMD · Sep 30, 2026
Links #3: 2026/06 Part 1
LessWrong · Jun 15, 2026
Performance Profiling on AMD GPUs – Part 5: Profiling-Driven Kernel Optimization with an AI Code-Assist Tool
AMD · Jul 16, 2026
Transform Video Into Instantly Searchable, Actionable Intelligence with AI Agents and Skills
NVIDIA · May 13, 2026