A PubMed shelf that answers back
Searches keep stacking papers into your project; every answer is drawn from those passages, with title and year on each claim.
Papers, answers and searches are kept per project.
Plain terms or boolean. Leave empty to skip searching and only ask about papers you already have.
Answered only from passages in this project's library. Leave empty on a search-only run.
Older papers are left out of the search.
The shelf is bare for now
A run lands here: what is new since last time, how many matched in total, the project's library, papers per year, the answer with its evidence, and the project's recent searches.
How the library grows
- Search. Your terms go to PubMed with the year cut-off applied.
- Collect. Matches join the project's library; papers already collected are marked, not duplicated.
- Retrieve. Your question pulls passages out of that library only.
- Answer. Every claim carries the paper's title and year, and the passages sit under it as evidence.
Questions people ask
Can I ask without searching?
Yes. Leave the search terms empty and the run reads only the papers already collected under that project.
Where do answers come from?
Only from passages retrieved out of your project's library. If the library holds nothing relevant, the answer says so rather than guessing.
Do projects share papers?
No. Each project keeps its own papers, answers and search history, so two threads never contaminate each other.