Metraipolis › archive › dc_5dff4bd9fd8d
Operationalising Weaker Faithfulness: Recovery, Ambiguity and Computational Limits — arXiv:2610.31724
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31724
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T20:13:52.455Z
- SHA-256 of the archived text
f11c543552327c5d9da3bb2860ad6870036fda32255ed20b167b13971ceec701- Stable URL of this page
https://metraipolis.com/documento/dc_5dff4bd9fd8d
How to cite
Operationalising Weaker Faithfulness: Recovery, Ambiguity and Computational Limits — arXiv:2610.31724 — arXiv (en), https://arxiv.org/abs/2610.31724 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5dff4bd9fd8d (Metraipolis archive dc_5dff4bd9fd8d, sha256 f11c543552327c5d9da3bb2860ad6870036fda32255ed20b167b13971ceec701)
BibTeX
@misc{dc5dff4bd9fd8d,
title = {Operationalising Weaker Faithfulness: Recovery, Ambiguity and Computational Limits — arXiv:2610.31724},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31724},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5dff4bd9fd8d; sha256 f11c543552327c5d9da3bb2860ad6870036fda32255ed20b167b13971ceec701},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31724. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Variables can predict an outcome jointly while each is individually independent of it, causing structure learners to discard informative links. We investigate how to operationalise weaker faithfulness through two approaches: selective protection in an adjacency learner and explicit retention of alternative directed graph explanations. Matched experiments show that changes at both an early candidate-removal stage and later pruning can be necessary. In noisy XOR with a descendant (N = 10,000, 20 matched samples), combining reactivation and protection raises complete parent-pair recovery from 0/20 for either change alone to 20/20, while adding false edges. A confirmation study shows that the family estimator can preserve explanations lost by orienting the protected learner's selected skeleton: in one weaker signal XOR condition (N = 10,000) it retains the entire reference family in 48/50 samples, compared with 0/50 for the skeleton adapter. These gains are conditional. Protection can add only error, weaker effects produce false exclusions, and an ordinary faithful-chain comparison favours the PC learner. Complete nonempty family outputs decline at six/eight variables, and all 400 twelve/twenty-variable searches remain unfinished at the reporting cutoff. Neural controls show engineered retention, while the family estimator returns no accepted graph within its application budget. This operationalisation identifies two deletion stages that must be coordinated in the motivating example and shows when direct family search preserves explanations lost by selecting one skeleton. Finite evidence and computation remain substantial barriers to reliable general inference. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Methodology (stat.ME) ; Machine Learning (cs.LG); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.31724 — 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 2026-10-26T19:49:03.450Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).