Split the Labor: Separating Evidence Interpretation from Decision Aggregation

[2608.14509] Split the Labor: Separating Evidence Interpretation from Decision Aggregation Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.14509 (cs) [Submitted on 14 Aug 2026] Title: Split the Labor: Separating Evidence Interpretation from Decision Aggregation Authors: Zhelun Wu View a PDF of the paper titled Split the Labor: Separating Evidence Interpretation from Decision Aggregation, by Zhelun Wu View PDF HTML (experimental) Abstract: 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. Comments: Atlassian. 22 pages, 2 figures Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2608.14509 [cs.AI] (or arXiv:2608.14509v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.14509 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhelun Wu [ view email ] [v1] Fri, 14 Aug 2026 17:24:55 UTC (40 KB) Full-text links: Access Paper: View a PDF of the paper titled Split the Labor: Separating Evidence Interpretation from Decision Aggregation, by Zhelun Wu View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CL cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Split the Labor: Separating Evidence Interpretation from Decision Aggregation#458261
• Labour Force Survey Five-Quarter Longitudinal Dataset, October 1999 - December 2000#272761
• Labour Force Survey Five-Quarter Longitudinal Dataset, July 1998 - September 1999#272764
• Labour Force Survey Five-Quarter Longitudinal Dataset, December 1995 - February 1997#296154
• Labour Force Survey Five-Quarter Longitudinal Dataset, December 1995 - February 1997#272730