Metraipolis › archive › dc_666a608b7233

Leaf Values as Coordinates: Exact Contrastive Explanation for Gradient-Boosted Ensembles — arXiv:2608.19127

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19127
License (as archived)
CC0-1.0
Archived
2026-10-18T13:45:36.505Z
SHA-256 of the archived text
28502acaf4020a5ceb61feecff8fe9243931eef529a5495ead3ab9cb2fc8cc1e
Stable URL of this page
https://metraipolis.com/documento/dc_666a608b7233

How to cite

Leaf Values as Coordinates: Exact Contrastive Explanation for Gradient-Boosted Ensembles — arXiv:2608.19127 — arXiv (en), https://arxiv.org/abs/2608.19127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_666a608b7233 (Metraipolis archive dc_666a608b7233, sha256 28502acaf4020a5ceb61feecff8fe9243931eef529a5495ead3ab9cb2fc8cc1e)
BibTeX
@misc{dc666a608b7233,
  title = {Leaf Values as Coordinates: Exact Contrastive Explanation for Gradient-Boosted Ensembles — arXiv:2608.19127},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19127},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_666a608b7233; sha256 28502acaf4020a5ceb61feecff8fe9243931eef529a5495ead3ab9cb2fc8cc1e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A gradient-boosted ensemble predicts by summing one leaf value per tree. Read those values as coordinates rather than as intermediate results, and every instance becomes a point in R^M on which the model acts linearly: the score is the sum of the coordinates. This small change of view makes contrastive explanation exact. The difference between two instances is a vector that is identically zero wherever they share a leaf, so the gap between a rejected applicant and an accepted one is carried by a handful of coordinates, each traceable to a real split in a real tree. Nothing is fitted, sampled, or assumed additive in features -- the additivity is already there, in the right space. We build a recourse method on this representation and evaluate it on five tabular datasets under repeated cross-validation. Its recommendation reconstructs the model's own decision to 6.2 x 10^-15, so an auditor can re-check the arithmetic without the model. On the credit datasets it is Pareto-non-dominated on effort against realism. And when recommendations are restricted to changes the subject could actually make -- not their age, not a settled delinquency -- it retains 58% of its validity where the strongest baseline retains 41%, a distinction the standard evaluation cannot see because it never asks whether a recommendation can be carried out.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.19127 — 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 2026-10-18T13:41:18.004Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).