How to Build an Evidence Table from Study Abstracts

Evidence tables invent n= and p-values. Extract only what the abstract says. Leave NOT IN ABSTRACT.

The matching generator is the Evidence Table from Pasted Study Abstracts (No Invented Stats) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).

Print the not-medical-advice banner

Build an evidence table from pasted study abstracts. Never invent sample sizes, effect sizes, or DOIs. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.

Paste these fields before you hit run:

Pasted abstracts (numbered): [Abstracts]
Columns I lock: [Columns or standard PICO+N+limits]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Banner I require: [Banner or Not medical advice]

That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.

One row per pasted abstract

Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.

Walk the Generate list in order:

1. Honesty ledger: abstract count, Columns, Banner, Lang.
2. Banner line.
3. Evidence table with one row per abstract. Missing cells: NOT IN ABSTRACT.
4. Never invent n=, p-values, DOIs, or years if absent.
5. Limitations column: only phrases from abstract or NOT IN ABSTRACT.
6. Refuse: pooled effect invent, risk-of-bias invent without tool, DOI invent.
7. Count row: abstracts in vs rows out (must match).
8. Compliance pass: Banned and Never. Format as Format.

If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.

Mark missing cells NOT IN ABSTRACT

Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.

Honor the constraints as hard stops, not vibes:

• Table from Abstracts only. Not a meta-analysis and not medical advice.
• Never invent stats or DOIs.
• Keep Banner visible.
• No emojis.

When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.

Refuse invented DOIs and pooled effects

Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.

Tags on the card (evidence table study abstracts, no invented stats abstracts, research evidence extraction table) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.

Fill the card, then run

Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.