the receipt of one searchthe web26registers9journals6what each datasource founda paid archivenot searchedwhat was not searched, and whyit needs a loginfound41returned3dropped38what was dropped, and why30 not relevant8 copiesnothing more relevantwhy the list ended
The run in 6 steps
Choose the datasources of the protocol
The catalog lists each datasource with the countries and the languages it covers, how it is reached, and which filters it applies itself. Your agent reads the catalog once and takes the ids of the datasources that the protocol names. A search takes up to 10 of them.Search in every wording, without a model
Send the question in each wording and each language that a trial can be reported in. Withdeterministic_only set to true, no model ranks the results or chooses datasources, so nothing in the list is a model’s judgment.
Request body of search
datasources with ids from the catalog.
Read the numbers that the protocol asks for
The response has the counts of the whole search and one entry for each datasource. This response is cut to those counts and to one datasource.Part of the response
each datasource, with its own count148an index of journals41a register of trials23a preprint server212 records found61 copieseach with its reason151 records to screenthe numbers add upwritten up by the search itself
Take the whole list, with the reason for each dropped record
The list is stored with the search. Its later pages have every record that did not come back in the first response, each with itsdropped_reason. Your screening log starts from all 212 records, and none of them is missing without a reason.
Hand the write-up to the reviewer
Because the request sentrecord_form as prisma, the response has record: the search written up in the form that a systematic review reports, as text and as structured data. It can go into the appendix of the review as it is.
Run the search again next month
Send the same request withpublished_from set to the day after the last run. The records published since then come back, with their own counts and their own write-up. No model takes part, so a difference between 2 runs comes from the datasources and not from the search.