Args:
    query: the search query string.
    limit: maximum number of results (default 10, capped at 100).
    year: a single year or range, e.g. "2018", "2015-2022", "2016-", "-2015".
    fields_of_study: restrict to fields, e.g. ["Economics", "Business"].
    min_citation_count: drop papers with fewer citations than this.
    venue: restrict to venues, e.g. ["Marketing Science"].
    open_access_pdf: if True, only return papers that have an open-access PDF.

Thin wrapper over search_papers that maps a year_start/year_end pair to the
API's year-range string. See search_papers for the filter semantics.

Args:
    topic: the search query string.
    year_start: start year (inclusive).
    year_end: end year (inclusive).
    limit: maximum number of results (default 10, capped at 100).
    fields_of_study: restrict to fields, e.g. ["Economics", "Business"].
    min_citation_count: drop papers with fewer citations than this.

Args:
    paper_id: a Semantic Scholar paper ID, or a DOI, arXiv ID, etc.

Far more efficient than calling fetch_paper_details in a loop: a single
request returns all of them, which matters under the 1 request/second limit.

Args:
    paper_ids: Semantic Scholar paper IDs (or DOIs, arXiv IDs, etc.).

Use this as a second discovery channel: keyword search finds papers that
share vocabulary, while recommendations surface structurally similar papers
in OTHER empirical domains that keyword search misses. Seed it with the
paper IDs of the best on-target hits from a search.

Args:
    positive_paper_ids: IDs the results should resemble (at least one required).
    negative_paper_ids: IDs to steer recommendations away from (optional).
    limit: maximum number of recommendations (default 10, capped at 100).