Skip to content
All tags

#academic-search

2 posts
ai deep-dive Search and Scraping in Practice

Building an Academic Search Pipeline: The Roles of arXiv, OpenAlex, Crossref, Semantic Scholar, and PubMed

An academic-search pipeline cannot simply concatenate five APIs: use arXiv or PubMed for domain discovery, align OpenAlex and Semantic Scholar records through DOI, PMID, and arXiv IDs, then use Crossref and PubMed relationships to check the version of record, corrections, and retractions.

#academic-search#literature-review#arxiv#openalex#crossref#semantic-scholar#pubmed
ai deep-dive Search and Scraping in Practice

Writing Search Queries for Agents: Keywords, Semantic Descriptions, Decomposition, and Rewriting

An agent should not send the user's sentence unchanged to every search service. Classify the need as exact lookup, keyword, semantic, or fielded search; move source, date, language, and field constraints into native provider parameters; then rewrite according to zero-result, overbroad, stale, or source-mismatch symptoms.

#web-search#ai-agent#query-rewriting#semantic-search#academic-search