Metraipolis › archive › dc_eed34532c04b
One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail — arXiv:2608.14683
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14683
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:39:49.588Z
- SHA-256 of the archived text
de7a8d7f58b8e87ef9e47409232ea4c2e824e425421358a9fdf0873c5e1354d5- Stable URL of this page
https://metraipolis.com/documento/dc_eed34532c04b
How to cite
One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail — arXiv:2608.14683 — arXiv (en), https://arxiv.org/abs/2608.14683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eed34532c04b (Metraipolis archive dc_eed34532c04b, sha256 de7a8d7f58b8e87ef9e47409232ea4c2e824e425421358a9fdf0873c5e1354d5)
BibTeX
@misc{dceed34532c04b,
title = {One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail — arXiv:2608.14683},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14683},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eed34532c04b; sha256 de7a8d7f58b8e87ef9e47409232ea4c2e824e425421358a9fdf0873c5e1354d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Given a patient's clinical findings, a diagnostic system ranks possible diseases and must decide when to endorse its first prediction or defer it for review. This decision is usually made by thresholding the top score. Selective prediction over ranked outputs begins with two checks. First, the ranker must produce enough correct top-ranked predictions to make the target feasible. Across 2,000 patient records stratified by disease prevalence, eight small open-weight LLMs achieve at most 4.6% Recall@1 on ultra-rare diseases. At 10% coverage, even a perfect confidence ranking of their existing predictions therefore cannot reach 50% selective accuracy. More accurate models pass the same check, showing that the limit is regime-specific. Second, the confidence signal must match the decision being made. For fixed-candidate rankers, the top-two margin cancels components shared across candidates. On phenotype-only Exomiser, it selects 10% of cases at 29.0% accuracy, compared with 13.3% overall, while the top score provides no reliable gate. Yet that cancellation can remove information needed to detect whether the candidate list contains an answer. SciFact retrieval and biomedical entity linking confirm this distinction. Finally, we prove that unlabelled scores alone cannot determine whether switching to the margin will help. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.14683 — 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 2026-10-18T19:02:44.041Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).