Metraipolis › archive › dc_44d119adfb47
CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence — arXiv:2608.12555
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12555
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:17:11.553Z
- SHA-256 of the archived text
7a32d5b55e73a6e3ea51ebd2910efeaae119be4f7acd942cae12e1be432b851d- Stable URL of this page
https://metraipolis.com/documento/dc_44d119adfb47
How to cite
CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence — arXiv:2608.12555 — arXiv (en), https://arxiv.org/abs/2608.12555 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44d119adfb47 (Metraipolis archive dc_44d119adfb47, sha256 7a32d5b55e73a6e3ea51ebd2910efeaae119be4f7acd942cae12e1be432b851d)
BibTeX
@misc{dc44d119adfb47,
title = {CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence — arXiv:2608.12555},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12555},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44d119adfb47; sha256 7a32d5b55e73a6e3ea51ebd2910efeaae119be4f7acd942cae12e1be432b851d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12555. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome. We introduce the Causal Attribution Score (CAS), a compact score architecture for causal explanation. CAS starts from an identified interventional coalition game, allocates the joint intervention contrast with causal Shapley contributions, and converts those raw outcome-scale effects into Local CAS, Signed Local CAS, and two complementary Global CAS summaries. The innovation is not a new Shapley formula, but a local-to-global causal reporting layer with an explicit intervention target. In the known-truth benchmark, eight repeated primary-interaction simulations (n = 2,200 each, three actions) gave mean Local CAS MAE of 0.107 for coalition-aware CAS, compared with 0.173 for one-at-a-time normalisation and 0.213 for a global normalised absolute ATE vector. The paired advantage over one-at-a-time normalisation increased from -0.003 under additivity to 0.091 under strong interactions. On both empirical DoubleML datasets, 401(k) eligibility/net financial assets (n = 9,915) and Pennsylvania reemployment bonus/unemployment duration (n = 5,099), predictive SHAP/TreeSHAP rankings differed materially from Feature-CAS rankings of treatment-effect modifiers. In Pennsylvania, dep1 (exactly one dependent) moved from predictive global rank 13 to Feature-CAS rank 2 and was the leading local Feature-CAS modifier. These results isolate the added value of separating what predicts the outcome from what explains heterogeneity in an estimated causal effect. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.12555 — 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 2026-10-19T04:13:06.525Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).