这篇论文把读证据和汇总决策拆开，用四字段元组和一对数似然比池化解决了投票漂移，实验比手工基线高了不少。
该论文提出将证据解释与决策聚合分开处理，并定义了一个四字段证据元组（假设、可靠性分桶、理由、来源）。作者指出，直接对未归一化权重求和做阈值会引发“数尺漂移”（count-scale drift），即运行点随证据条数滑动。改用校准后的对数似然比池化可同时解决漂移和排序不一致问题。在纵向语料上，小序列编码器加树集成达到 0.921 AUPRC，而手工基线为 0.805。论文还列出五个可证伪预测和三个阴性结果。
Split the Labor: Separating Evidence Interpretation from Decision Aggregation
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.