Metraipolis › archive › dc_31cd85803fab
Split the Labor: Separating Evidence Interpretation from Decision Aggregation — arXiv:2608.14509
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14509
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:20:52.628Z
- SHA-256 of the archived text
479d98e74660ecd5d802d79826b20cf7b546b4c6e20ccf29771a4eb9e41cf47a- Stable URL of this page
https://metraipolis.com/documento/dc_31cd85803fab
How to cite
Split the Labor: Separating Evidence Interpretation from Decision Aggregation — arXiv:2608.14509 — arXiv (en), https://arxiv.org/abs/2608.14509 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31cd85803fab (Metraipolis archive dc_31cd85803fab, sha256 479d98e74660ecd5d802d79826b20cf7b546b4c6e20ccf29771a4eb9e41cf47a)
BibTeX
@misc{dc31cd85803fab,
title = {Split the Labor: Separating Evidence Interpretation from Decision Aggregation — arXiv:2608.14509},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14509},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31cd85803fab; sha256 479d98e74660ecd5d802d79826b20cf7b546b4c6e20ccf29771a4eb9e41cf47a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14509. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt. This conflates two operations with different requirements. Interpreting a source rewards capacity and context. Combining interpretations rewards fixed arithmetic, comparability across instances, and the option to return nothing. Once separated, the design problem becomes the interface between them. We propose a four-field evidence tuple (hypothesis, reliability bucket, rationale, provenance) and show that fixing it determines both halves. The separation also reveals a failure mode in how such systems combine, which we call count-scale drift. Thresholding a sum of unnormalized weights is exactly posterior thresholding, but at an operating point that slides with the number of sources consulted. The slide grows with reader reliability. When source reliabilities differ, the vote rule and the posterior order instances differently, and no threshold reconciles them. Pooling calibrated log-likelihood ratios addresses both problems. The fix is arithmetic rather than architectural, and applies to a class of rules beyond language models: score-summing triage engines, diagnostic panels scored by counting positives, and additive multi-signal detectors. We then instantiate the principle twice on one longitudinal corpus, once after outcomes resolve and once before. The same partition helps in both, at different granularities: over reading in the first, over learning capacity in the second. There, a small sequence encoder on an easy auxiliary objective plus a tree ensemble carrying the censored survival loss reaches 0.921 AUPRC against 0.805 for a hand-crafted baseline. We separate what transfers from what must be re-estimated per domain, and state five predictions that would falsify the framework, three negative results, and which comparisons remain confounded. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.14509 — 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 2026-10-19T02:02:02.828Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).