Open-Web streams can reference real-world events without making them suitable for organization: a correctly linked event may serve only as background, while an event absent from the knowledge base may be central to an item. This distinction reveals an evaluation blind spot in multistage Web systems: pipelines determine not only how inputs are scored, but also which inputs receive scores at all. Using open-Web event admission as a case study, we examine three connected objects (the scored population, the selected operating point, and behavior on the complete input stream) through shared-subset comparisons, admission-loss decomposition, and controlled extraction-recovery interventions. We find that reported ranking differences depend on the scored population, scoring gaps exhibit distinct backbone-dependent failure modes, and recovering missing scores can increase false acceptance under an unchanged threshold. On Original-302, Qwen candidate validity scores 255 of 302 items while direct admission scores all 302; evaluating both on the shared subset narrows their AUC gap. For Mistral, span-safe recovery raises false acceptance from 73.1% to 92.5% with the threshold fixed. Across 602 human-annotated evaluation items within a 3,290-record resource, these findings establish a reporting framework that considers score availability, threshold selection, and complete-stream decisions together.

翻译：暂无翻译