Evaluation v0: ranked feed vs simple baselines

This page calls GET /api/v1/evaluation/compare so you can inspect the same candidate pool under three orderings: materialized ranking, citation-sorted, and date-sorted. Nothing here measures whether researchers would find the papers useful; it only shows distributional checks on short lists. For Emerging, this compares the materialized paper_scores order, not the bounded ML scorer reorder.

Run label filter: shadow-generalization-product-candidate-ranking-v1