Commit History
19 days ago
-
Rewrite evaluation with independent relevance labels
samwjya +1: Claude Opus 5.5The old pseudo-relevance used OpenAlex's own top-k as ground truth, so OpenAlex always scored 1.0. Now: LLM-judged graded labels over pooled results, NDCG normalized over all judged papers, six systems compared. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>b35072c
-
cleaning, remove bm25
samwjyadf1df12
-
add paper link
samwjyaa32e9c3
-
evalute.py
samwjyab85685c