Scientific Retrieval & Recommendation

Purpose

Retrieve relevant documents, datasets, and resources from large scientific and domain-specific archives.

Key Datasets

• Financial Reports SEC (JanosAudran/financial-reports-sec): SEC 10-K filings with 20 sections and sentiment labels
• Historical Newswire (dell-research-harvard/newswire): Historical news article corpus for digital humanities research

Protocol

1. Query analysis — Parse information need, identify key concepts and constraints
2. Source selection — Choose appropriate databases and archives
3. Search execution — Multi-strategy search (keyword, semantic, citation-based)
4. Relevance ranking — Score and rank results by relevance, authority, recency
5. Result synthesis — Organize and present findings with metadata