Batch Enrich Paper IDs With Metadata From Semantic Scholar Into a Google Sheet

The Scenario

A colleague handed off a project two weeks ago and left you an Excel export with 400 paper IDs in column A. No titles, no abstracts, no citation counts — just the IDs. You need the full metadata filled in before you can start the analysis portion of the work, and there's no budget to delay the delivery date to rerun someone else's setup.

The bad version:

Open Semantic Scholar's paper detail page, paste the first ID into the URL, copy the title and abstract from the rendered page, switch back to the sheet, paste into columns B and C.
Repeat for paper 2. Realize the abstract on paper 7 contains a comma that breaks your CSV structure when you try to bulk-paste later.
By paper 30 you've been at this for 90 minutes and you still have 370 to go — and the abstract column keeps misaligning.

Four hundred individual lookups is not analysis work. It's data entry that exists only because the handoff was incomplete.

The Easy Way: One Prompt in SheetXAI

SheetXAI is an AI agent that lives inside your Google Sheet. It reads the paper IDs in column A, hits Semantic Scholar's batch endpoint in a single call, and writes every metadata field back into the adjacent columns without a single manual lookup.

Here is the prompt for this task:

Batch-fetch details from Semantic Scholar for all paper IDs in column A and write title, abstract, year, venue, and citation count into columns B through F

What You Get

Columns B through F filled for every row: Title, Abstract, Year, Venue, Citation Count.
Citation Count is a numeric value — ready for sorting and analysis.
Rows where Semantic Scholar returned no match are flagged with a clear note in column B rather than left blank.
The batch call handles the full 400-row list in one operation — no row-by-row polling.

What If the Data Is Not Quite Ready

Some rows in column A contain DOIs instead of Semantic Scholar paper IDs

For each identifier in column A — treating values that start with 10. as DOIs and others as Semantic Scholar paper IDs — batch-fetch metadata from Semantic Scholar and write title, year, venue, and citation count into columns B through E

You only want to enrich rows that are still missing titles

Check column B for blank cells, and for each row where the title is missing, fetch the paper details from Semantic Scholar using the ID in column A and fill in title, year, venue, and citation count

The paper ID column contains a mix of valid IDs and empty rows

Skip blank rows in column A, batch-fetch Semantic Scholar metadata for all valid paper IDs, and write title, abstract, year, and venue into columns B through E — leaving rows with no ID untouched

Clean the ID column, enrich, and flag low-citation papers in one prompt

Trim any whitespace from paper IDs in column A, batch-fetch title, abstract, year, venue, and citation count from Semantic Scholar for all of them, write results into columns B through F, and mark any paper with fewer than 10 citations as Low-Impact in column G

One prompt handles the data cleanup and the enrichment together.

Try It

Get the 7-day free trial of SheetXAI and open any sheet where column A holds a list of paper IDs or DOIs. Ask SheetXAI to batch-enrich the whole column at once — and skip the 400 individual tab-switches entirely.