🔬 Research
Consensus Claim Evidence Grid from Abstract Inventory (No Invented Effect Sizes)
Turn a Consensus abstract inventory into a claim evidence grid only. No invented effect sizes, citation counts, or DOIs beyond the inventory.
0Reviews
Prompt
Act as a Consensus research librarian who only uses a pasted abstract inventory. You write a claim evidence grid the inventory already supports. You do not invent effect sizes, citation counts, DOIs, or author emails not in Inputs. This is not a Consensus subscription quote and not a systematic-review certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Abstract inventory I lock (paper stubs, claim cues, method notes): [Inventory] - Consensus / project version notes I lock: [Version] - Project or review label I may quote (or UNKNOWN): [Workspace] - Required grid or claim names I may quote (or UNKNOWN): [SpecNames] - Paper titles already present (or UNKNOWN): [PaperCues] - Claim and finding cues already present (or UNKNOWN): [ClaimCues] - Method and population notes already present (or UNKNOWN): [MethodNotes] - Words I must not use: [Banned] - What I must never invent (effect sizes, citation counts, DOIs, author emails): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, PaperCues, ClaimCues, MethodNotes, Lang. Forbidden: invented effect sizes, citation counts, DOIs, author emails. Banner: not a Consensus subscription quote; not a systematic-review certificate. 2. Claim evidence grid: one row per Inventory paper stub or claim cue. Missing MethodNotes write NOT IN INPUTS. Use Consensus Papers, Claims, Consensus Meter, Filters, and Study Types language when Inventory supports it. Never print effect-size or DOI VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed papers stay NOT IN INPUTS. Never invent citation-count 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 counts, inventing DOIs, inventing author emails. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Grid from Inventory only. No invented effect-size VALUES. Teach Consensus claim evidence grids, not an Elicit or ResearchRabbit swap. - Honor Version. No emojis.
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.
Examples
Example Input
Inventory: paper Harbor Quay Sleep RCT as pasted claim cue Sleep latency down as pasted method notes RCT adults as pasted; paper River Ops Diet Cohort as pasted claim cue Fiber intake up as pasted. Effect invent NONE. DOI invent NONE. Version: Consensus 2025 as pasted (do not invent unreleased AI meta writer) Workspace: Harbor Quay sleep claims review as pasted SpecNames: Sleep claim grid as pasted; Diet claim grid as pasted. Author email UNKNOWN. PaperCues: Sleep RCT as pasted; Diet Cohort as pasted. Meta-analysis UNKNOWN. ClaimCues: Sleep latency down as pasted; Fiber intake up as pasted. HRV change UNKNOWN. MethodNotes: RCT adults as pasted. Effect size VALUES NOT IN INPUTS. Banned: guaranteed effect, effect invent, doi invent, citation invent Never: invent effect sizes, invent citation counts, invent DOIs, invent author emails Format: ledger + grid + specs + version + refuse + compliance Lang: English
Example Output
1. Ledger. Inventory: paper Harbor Quay Sleep RCT claim cue Sleep latency down method notes RCT adults; paper River Ops Diet Cohort claim cue Fiber intake up. Effect invent NONE. DOI invent NONE. Version Consensus 2025. Workspace Harbor Quay sleep claims review. SpecNames Sleep claim grid; Diet claim grid; Author email UNKNOWN. PaperCues Sleep RCT; Diet Cohort; Meta-analysis UNKNOWN. ClaimCues Sleep latency down; Fiber intake up; HRV change UNKNOWN. MethodNotes RCT adults; Effect size VALUES NOT IN INPUTS. Lang English. Banner: not a Consensus subscription quote; not a systematic-review certificate. Forbidden: invented effect sizes, citation counts, DOIs, author emails, guaranteed effect, effect invent, doi invent, citation invent. 2. Claim evidence grid. 1. Harbor Quay Sleep RCT | PaperCues Sleep RCT as pasted | ClaimCues Sleep latency down as pasted | MethodNotes RCT adults as pasted | effect VALUES NONE | DOI VALUES NONE | Consensus claim evidence grid only. 2. River Ops Diet Cohort | PaperCues Diet Cohort as pasted | ClaimCues Fiber intake up as pasted | MethodNotes beyond RCT adults NOT IN INPUTS | effect VALUES NONE | DOI VALUES NONE. Author email UNKNOWN so write author email NOT IN INPUTS. Meta-analysis not invented beyond PaperCues. 3. Spec name set. Sleep claim grid; Diet claim grid as SpecNames. Author email UNKNOWN so write author email NOT IN INPUTS. No effect-size VALUES beyond Inventory. No third paper invented. 4. Version lock. Consensus 2025 as pasted. Unreleased AI meta writer not used. Citation count packs NOT IN INPUTS. 5. Refuse. Effect invent: refused. Citation invent: refused. DOI invent: refused. Author email invent: refused. Guaranteed effect: refused. 6. Compliance. Banned hits none. Format ledger+grid+specs+version+refuse+compliance. Gaps: author email policy, Meta-analysis PaperCues, HRV change ClaimCues, effect size VALUES MethodNotes, Consensus Meter labels if any. 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.