Metraipolis › archive › dc_0a8a803db2df

Candidate Retention for Abductive Learning — arXiv:2609.39561

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.39561
License (as archived): CC0-1.0
Archived: 2026-10-07T12:45:30.646Z
SHA-256 of the archived text: 8e8b3b15bcd3b8338871c99f164c02a53acde04553fa58a3ab24603a18e8c2b1
Stable URL of this page: https://metraipolis.com/documento/dc_0a8a803db2df

How to cite

Candidate Retention for Abductive Learning — arXiv:2609.39561 — arXiv (en), https://arxiv.org/abs/2609.39561 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0a8a803db2df (Metraipolis archive dc_0a8a803db2df, sha256 8e8b3b15bcd3b8338871c99f164c02a53acde04553fa58a3ab24603a18e8c2b1)

BibTeX

@misc{dc0a8a803db2df,
  title = {Candidate Retention for Abductive Learning — arXiv:2609.39561},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39561},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0a8a803db2df; sha256 8e8b3b15bcd3b8338871c99f164c02a53acde04553fa58a3ab24603a18e8c2b1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39561. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Abductive learning combines neural perception with symbolic reasoning, using explanations generated by abduction to supervise the perception model. Multiple valid explanations of the same symbolic target can assign conflicting labels to the same inputs. Common policies select a single candidate as a pseudo-label, which may reinforce mistaken assignments, or weight all candidates, which may spread supervision across competing labels. These risks motivate selecting a retained subset to balance supervision sharpness and model-mass coverage. To guide this choice, we bound the coordinate-level supervision error using retained uncertainty, discarded model mass, and model mismatch. For a fixed model and training pair, only the first two terms depend on the retained set. We propose Abductive Candidate Retention (ACR), which uses these terms to guide greedy additions, accepting a candidate when its recovered mass exceeds the increase in retained uncertainty. Experiments show that ACR improves concept accuracy over single-candidate baselines and A3BL in most evaluated aggregated mod-addition settings. Objective ablations support the joint use of uncertainty and posterior mass.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.39561 — 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 2026-10-07T12:14:14.103Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).