# Evidence-State Response Calibration

Retrieval-augmented generation does not improve every task, since irrelevant evidence can distract a generator, and measuring each candidate retriever's gain directly repeats generation for every configuration. EviCast splits a retriever's net utility into the generator's response to controlled evidence states and that retriever's offline distribution over those states; the response is measured once on a small calibration set and reused. On 14 HotpotQA retrieval configurations, one calibration used 96 generation calls, made 14 of 14 correct deployment decisions with a 2.75 F1-point forecast error, and cut diagnostic generation calls by 80% relative to per-configuration direct measurement.

Retrieval-augmented generation does not improve every task, since irrelevant evidence can distract a generator, and measuring each candidate retriever's gain directly repeats generation for every configuration. EviCast splits a retriever's net utility into the generator's response to controlled evidence states and that retriever's offline distribution over those states; the response is measured once on a small calibration set and reused. On 14 HotpotQA retrieval configurations, one calibration used 96 generation calls, made 14 of 14 correct deployment decisions with a 2.75 F1-point forecast error, and cut diagnostic generation calls by 80% relative to per-configuration direct measurement.