Metraipolis › archive › dc_179a42ffa346
Auditable Hierarchical Inference with Multimodal Evidence and Bayesian Active Inquiry — arXiv:2610.38774
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38774
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:24:53.036Z
- SHA-256 of the archived text
6b9ca450182c334874767d550e7eecf7eeed37cec01a822b630e4419cde2d8d3- Stable URL of this page
https://metraipolis.com/documento/dc_179a42ffa346
How to cite
Auditable Hierarchical Inference with Multimodal Evidence and Bayesian Active Inquiry — arXiv:2610.38774 — arXiv (en), https://arxiv.org/abs/2610.38774 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_179a42ffa346 (Metraipolis archive dc_179a42ffa346, sha256 6b9ca450182c334874767d550e7eecf7eeed37cec01a822b630e4419cde2d8d3)
BibTeX
@misc{dc179a42ffa346,
title = {Auditable Hierarchical Inference with Multimodal Evidence and Bayesian Active Inquiry — arXiv:2610.38774},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38774},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_179a42ffa346; sha256 6b9ca450182c334874767d550e7eecf7eeed37cec01a822b630e4419cde2d8d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38774. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most multimodal classifiers assume that all useful evidence is available upfront, whereas clinical inquiry is sequential. We present a synthetic evaluation framework separating objective multimodal inference from active inquiry. An objective model maps synthetic tongue, bilateral multipressure pulse, and acoustic observations to eight syndrome families. A provenance-bearing Knowledge Core and training-only answer model support Bayesian narrowing over 33 fine terms using 25 typed questions, while seven safety questions remain outside the diagnostic posterior. Weak shared symptom factors limit fine-term influence on objective phenotypes, and an objective-only probe tests leakage. In a preregistered 600-case synthetic evaluation, objective family accuracy was 87.0%. Cost-sensitive expected information gain (cost-EIG) raised family accuracy to 95.5% and exact fine-term accuracy to 42.5%, versus 92.7% and 33.0% for an unoptimized fixed-order baseline. Selective family accuracy reached 96.9% at 95.3% coverage. However, cost-EIG asked more questions on average than fixed order (9.795 versus 9.352). Missing-audio routing retained 94.0% family accuracy, and a workflow invariant enforced abstention when all objective modalities were absent. Permuting fine-term answer likelihoods reduced family accuracy to 78.7%. Five of six frozen checks passed, but the question-efficiency hypothesis failed. Comparisons are descriptive because only aggregate, not paired case-level, outputs were retained. These results establish a reproducible synthetic workflow, not clinical diagnostic or treatment validity. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.38774 — 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 2026-11-01T02:12:44.134Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).