Metraipolis › archive › dc_cd29c51eabb9
MotionBench-XAI: Benchmarking What Shapes Shapley Explanations in Spatiotemporal Machine Learning — arXiv:2611.08797
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08797
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:41:16.167Z
- SHA-256 of the archived text
493b7395ace82e375a022d5eaf77ec5e773856e680ba3882ee77e7186310d202- Stable URL of this page
https://metraipolis.com/documento/dc_cd29c51eabb9
How to cite
MotionBench-XAI: Benchmarking What Shapes Shapley Explanations in Spatiotemporal Machine Learning — arXiv:2611.08797 — arXiv (en), https://arxiv.org/abs/2611.08797 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd29c51eabb9 (Metraipolis archive dc_cd29c51eabb9, sha256 493b7395ace82e375a022d5eaf77ec5e773856e680ba3882ee77e7186310d202)
BibTeX
@misc{dccd29c51eabb9,
title = {MotionBench-XAI: Benchmarking What Shapes Shapley Explanations in Spatiotemporal Machine Learning — arXiv:2611.08797},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08797},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd29c51eabb9; sha256 493b7395ace82e375a022d5eaf77ec5e773856e680ba3882ee77e7186310d202},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08797. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predicting outcomes from spatiotemporal data, such as assessing Parkinson's severity from human motion, often requires explainability in addition to accuracy. Practitioners need to know what drove the prediction, whether it be spatial (a body joint), temporal (a specific window), or both. Shapley values are attributions computed by treating input features as players in a cooperative game and measuring how the model output changes as coalitions of players are removed. Computing them involves choosing what counts as players, how absent players are imputed, and how the game is evaluated. How these choices affect explanation quality is poorly understood for spatiotemporal data, and real data carries no ground-truth attributions to check against. We present MotionBench-XAI, a benchmark built on i) five synthetic spatiotemporal datasets with exact ground-truth Shapley values, ii) three real datasets across clinical gait, electrocardiogram, and audio, iii) ten attribution methods across three player sets, and iv) three trained architectures. We show that grouping features into players, across time, space, or both, matters more than the choice of imputer. Generative imputers improve explanations only when their conditional models are accurate. On real data, the standard proxy metrics select contradictory best methods. We distill these findings into practical insights and provide an open-source pipeline. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.08797 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:33:47.141Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).