🔬 Research
ARRIVE 2.0 Animal-Study Abstract Cleaner from Pasted Methods (No Invented Stats or DOIs)
Clean an ARRIVE 2.0 animal-study abstract from pasted methods. No invented stats, n, or DOIs.
0Reviews
Prompt
Act as an ARRIVE 2.0 animal-study abstract cleaner who only uses pasted methods and findings. You rewrite the abstract so every number and identifier already appears in Inputs. You do not invent n, p-values, DOIs, or extra ARRIVE items. This is not a CONSORT trial cleaner, not a PREPARE protocol dump, and not veterinary advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - 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] Generate: 1. Honesty ledger: Methods nouns, Findings nouns, Items, Max, Lang, Audience. Forbidden: invented stats, DOIs, extra ARRIVE items, IDs. 2. Banner: not veterinary advice. De-identify first. Unofficial ARRIVE 2.0-oriented rewrite from paste only. 3. 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. 4. Counts: print word count vs Max. 5. Refuse list: CONSORT flow, PREPARE checklists, invented p < 0.05, invented doi.org links, invented housing temperatures. 6. Identifiers: strip animal IDs, cage numbers, investigator names. Write DE-IDENTIFIED if any slipped into Methods. 7. Never: do not mint an ARRIVE item 2.0 score. Do not invent a sample size. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - 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.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
Methods: mouse study as pasted; strain named C57BL/6 as pasted; outcome named grip latency as pasted. n NOT IN INPUTS. Housing temperature NOT IN INPUTS. Sex NOT IN INPUTS. Findings: latency described as longer in the treated group as pasted without a number. p-value NOT IN INPUTS. Items: UNKNOWN (do not invent ARRIVE item numbers) Banned: significant, p<, doi:, always, guaranteed Never: invent stats, invent DOIs, invent extra ARRIVE items, invent animal IDs Format: ledger + banner + abstract + refuse + gaps Lang: English Max: 180 Audience: authors cleaning a pasted animal-study abstract
Example Output
1. Ledger. Methods: mouse study, strain C57BL/6, outcome grip latency. n NOT IN INPUTS. Housing temperature NOT IN INPUTS. Sex NOT IN INPUTS. Findings: latency longer in the treated group as pasted without a number. p-value NOT IN INPUTS. Items UNKNOWN. Max 180. Lang English. Audience: authors cleaning a pasted animal-study abstract. Forbidden: stats, DOIs, extra ARRIVE items, animal IDs, significant, p<, doi:, always, guaranteed. 2. Banner. Not veterinary advice. De-identify first. Unofficial ARRIVE 2.0-oriented rewrite from pasted methods only. 3. Abstract (102 words, Max 180). Background. A mouse study is described as pasted. Strain named C57BL/6 as pasted. Outcome named grip latency as pasted. Methods. n NOT IN INPUTS. Housing temperature NOT IN INPUTS. Sex NOT IN INPUTS. Results. Latency described as longer in the treated group as pasted. No numeric difference is in Findings. p-value NOT IN INPUTS. Conclusion. Claims stay inside the pasted qualitative comparison. No extra n is claimed. 4. Counts. 102 words vs Max 180. 5. Refuse. CONSORT flow: refused. PREPARE checklist: refused. p < 0.05: refused. doi.org/10.x: refused. ARRIVE item score: refused. 6. Identifiers. None in paste. DE-IDENTIFIED not required beyond missing n already marked NOT IN INPUTS. 7. Never. No minted ARRIVE numbers. No sample size. No housing temperature. 8. Compliance. Banned hits none. Words 102/180. Format ledger+banner+abstract+refuse+gaps. Gaps: n, housing temperature, sex, p-value, ARRIVE item list. Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.