How to Clean an ARRIVE 2.0 Animal-Study Abstract from Pasted Methods
Animal-study abstracts invent n=12 and a DOI. The paste named C57BL/6 mice and grip latency described as longer without a number. Sex NOT IN INPUTS.
The matching generator is the ARRIVE 2.0 Animal-Study Abstract Cleaner from Pasted Methods (No Invented Stats or DOIs) (Arrive 2 0 Animal Study Abstract Cleaner From Pasted Methods No Invented Stats Or Dois) 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-veterinary-advice banner first
Clean an ARRIVE 2.0 animal-study abstract from pasted methods. No invented stats, n, 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 methods I lock: [Methods]
Findings I may quote (or NONE): [Findings]
ARRIVE items I lock (or UNKNOWN): [Items]
Words I must not use: [Banned]
What I must never invent (stats, DOIs, extra ARRIVE items, animal IDs): [Never]
Output format: [Format]
Language: [Lang]
Word cap I lock: [Max]
Audience I may name: [Audience]
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.
Quote methods and findings only
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:
- Honesty ledger: Methods nouns, Findings nouns, Items, Max, Lang, Audience. Forbidden: invented stats, DOIs, extra ARRIVE items, IDs.
- Banner: not veterinary advice. De-identify first. Unofficial ARRIVE 2.0-oriented rewrite from paste only.
- Abstract: sections only from Items or a generic Background / Methods / Results / Conclusion if Items is UNKNOWN. Quote Methods and Findings. Missing n write NOT IN INPUTS.
- Counts: print word count vs Max.
- Refuse list: CONSORT flow, PREPARE checklists, invented p < 0.05, invented doi.org links, invented housing temperatures.
- Identifiers: strip animal IDs, cage numbers, investigator names. Write DE-IDENTIFIED if any slipped into Methods.
- Never: do not mint an ARRIVE item 2.0 score. Do not invent a sample size.
- Compliance pass: quote Banned and Never hits. Cut them. 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.
Refuse CONSORT PREPARE and invented DOIs
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:
- ARRIVE 2.0-oriented abstract from Methods and Findings only. Not CONSORT and not veterinary advice.
- Never invent stats, DOIs, or animal IDs.
- Stay at or under Max words.
- 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.
Count words against Max
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 (arrive 2.0 animal-study abstract, pasted methods only, no invented stats or dois) 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.