Metraipolis › archive › dc_6756aa406fa6
Equally Good, Yet Different: Benchmarking Rashomon sets in AutoML packages — arXiv:2609.36970
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36970
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:30:13.471Z
- SHA-256 of the archived text
7b9683dc6c02897656dfd7fa8ade0dcd6bd1130dbdd285ef32239ae80972833e- Stable URL of this page
https://metraipolis.com/documento/dc_6756aa406fa6
How to cite
Equally Good, Yet Different: Benchmarking Rashomon sets in AutoML packages — arXiv:2609.36970 — arXiv (en), https://arxiv.org/abs/2609.36970 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6756aa406fa6 (Metraipolis archive dc_6756aa406fa6, sha256 7b9683dc6c02897656dfd7fa8ade0dcd6bd1130dbdd285ef32239ae80972833e)
BibTeX
@misc{dc6756aa406fa6,
title = {Equally Good, Yet Different: Benchmarking Rashomon sets in AutoML packages — arXiv:2609.36970},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36970},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6756aa406fa6; sha256 7b9683dc6c02897656dfd7fa8ade0dcd6bd1130dbdd285ef32239ae80972833e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36970. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The Rashomon effect describes the existence of multiple near-optimal models that achieve comparable performance while offering fundamentally different explanations. This creates a critical vulnerability in AutoML: x-hacking, the selective post-hoc choice of a model based on its explanation rather than predictive merit. No existing AutoML framework exposes this risk. We introduce ARSA ML, an open-source Python framework that quantifies Rashomon set structure and predictive multiplicity within AutoML pipelines. Using ARSA ML, we benchmark AutoGluon and H2O across 28 binary classification datasets, and conduct a post-hoc x-hacking analysis revealing a consistent structural asymmetry: AutoGluon produces larger, diverse sets with stable explanations, while H2O generates compact sets with markedly higher prediction divergence and explanation instability -- making H2O users considerably more exposed to x-hacking. This gap persists across all evaluated metrics and epsilon thresholds, pointing to a fundamental difference in each framework's model-building strategy. ARSA ML is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.36970 — 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 2026-10-07T16:59:48.275Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).