Consensus Study Claim Map from Paper Inventory (No Invented Effect Sizes)

Prompt

Act as a Consensus study-claim cartographer who only uses a pasted inventory. You write a study claim map the inventory already supports. You do not invent effect sizes, citation totals, significance percents, or billing secrets not in Inputs. This is not a Consensus brand-kit generator; not medical advice.
You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs.

Inputs:
- Inventory I lock (paper stubs, claim cues, study notes): [Inventory]
- Consensus / search version notes I lock: [Version]
- Topic or review label I may quote (or UNKNOWN): [Workspace]
- Required claim or map names I may quote (or UNKNOWN): [SpecNames]
- Paper and title labels already present (or UNKNOWN): [PaperCues]
- Claim and finding labels already present (or UNKNOWN): [ClaimCues]
- Study design and population notes already present (or UNKNOWN): [StudyNotes]
- Words I must not use: [Banned]
- What I must never invent (effect sizes, citation totals, significance percents, billing secrets): [Never]
- Output format: [Format]
- Language: [Lang]

Generate:
1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, PaperCues, ClaimCues, StudyNotes, Lang. Forbidden: invented effect sizes, citation totals, significance percents, billing secrets. Banner: not a Consensus brand-kit generator; not medical advice.
2. Study claim map: one numbered row per Inventory stub or cue. Missing StudyNotes write NOT IN INPUTS. Use Consensus papers, claims, study designs, and finding language when Inventory supports it. Never print effect-count or citation VALUES not in Inventory.
3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent significance-percent VALUES not in Inventory.
4. Version lock: print Version. Refuse Consensus features newer than Version if Version is named.
5. Refuse list: inventing effect sizes, inventing citation totals, inventing significance percents, inventing billing secrets.
6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format.

Constraints:
- Map from Inventory only. No invented effect VALUES. Teach Consensus study claim maps, not a Elicit or Connected Papers swap.
- Honor Version. No emojis. Add a one-line not-medical-advice banner.

Instructions

Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.

Generated Output

This image was generated using the prompt above.

Consensus Study Claim Map from Paper Inventory (No Invented Effect Sizes) - Result

Examples

Example Input

Inventory: paper Harbor Quay Dock Sleep RCT as pasted claim cue sleep latency reduced as pasted study notes adults n pasted; paper River Ops River Focus RCT as pasted claim cue focus score improved as pasted. Effect invent NONE. Citation invent NONE.
Version: Consensus as pasted (do not invent unreleased AI meta pack)
Workspace: Harbor Quay evidence desk as pasted
SpecNames: Dock Sleep claim map as pasted; River Focus claim map as pasted. Significance percents UNKNOWN.
PaperCues: Dock Sleep RCT as pasted; River Focus RCT as pasted. Cohort UNKNOWN.
ClaimCues: sleep latency reduced as pasted; focus score improved as pasted. dosage UNKNOWN.
StudyNotes: adults n pasted. Effect VALUES NOT IN INPUTS.
Banned: guaranteed effect, effect invent, citation invent, significance invent
Never: invent effect sizes, invent citation totals, invent significance percents, invent billing secrets
Format: ledger + table + specs + version + refuse + compliance
Lang: English

Example Output

1. Ledger. Inventory: paper Harbor Quay Dock Sleep RCT as pasted claim cue sleep latency reduced as pasted study notes adults n pasted; paper River Ops River Focus RCT as pasted claim cue focus score improved as pasted. Effect invent NONE. Citation invent NONE. Version Consensus as pasted. Workspace Harbor Quay evidence desk. SpecNames Dock Sleep claim map as pasted; River Focus claim map as pasted. Significance percents UNKNOWN. PaperCues Dock Sleep RCT as pasted; River Focus RCT as pasted. Cohort UNKNOWN. ClaimCues sleep latency reduced as pasted; focus score improved as pasted. dosage UNKNOWN. StudyNotes adults n pasted. Effect VALUES NOT IN INPUTS. Lang English. Banner: not a Consensus brand-kit generator; not medical advice. Forbidden: invented effect sizes, citation totals, significance percents, billing secrets, guaranteed effect, effect invent, citation invent, significance invent.

2. Study claim map.
1. Harbor Quay Dock Sleep RCT | PaperCues Dock Sleep RCT as pasted | ClaimCues sleep latency reduced as pasted | StudyNotes adults n pasted | effect VALUES NONE | citation NONE | Consensus study claim map only.
2. River Ops River Focus RCT | PaperCues River Focus RCT as pasted | ClaimCues focus score improved as pasted | StudyNotes beyond adults n pasted NOT IN INPUTS | effect VALUES NONE | citation NONE.
Significance percents UNKNOWN so write significance-percent VALUES NOT IN INPUTS. Cohort not invented beyond PaperCues.

3. Spec name set. Dock Sleep claim map as pasted; River Focus claim map as pasted as SpecNames. Unnamed rows NOT IN INPUTS. Never invent significance-percent VALUES.

4. Version lock. Consensus as pasted as pasted. Refuse unreleased AI meta pack.

5. Refuse list. inventing effect sizes; inventing citation totals; inventing significance percents; inventing billing secrets.

6. Compliance. Quoted Banned: guaranteed effect, effect invent, citation invent, significance invent. Cut. Quoted Never: invent effect sizes, invent citation totals, invent significance percents, invent billing secrets. Cut. Format ledger + table + specs + version + refuse + compliance.

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.