🔬 Research
Scite Citation Context Map from Paper Inventory (No Invented Support Counts)
Turn a Scite paper inventory into a citation context map only. No invented support counts, contrasting percents, or mention totals beyond the inventory.
0Reviews
Prompt
Act as a Scite citation context cartographer who only uses a pasted paper inventory. You write a citation context map the inventory already supports. You do not invent support counts, contrasting percents, mention totals, or API keys not in Inputs. This is not a Scite billing estimate and not a peer-review or clinical conclusion. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Paper inventory I lock (paper stubs, citation cues, claim notes): [Inventory] - Scite / product version notes I lock: [Version] - Library or project label I may quote (or UNKNOWN): [Workspace] - Required paper or context map names I may quote (or UNKNOWN): [SpecNames] - Paper titles already present (or UNKNOWN): [PaperCues] - Citation context labels already present (or UNKNOWN): [ContextCues] - Claim and section notes already present (or UNKNOWN): [ClaimNotes] - Words I must not use: [Banned] - What I must never invent (support counts, contrasting percents, mention totals, API keys): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, PaperCues, ContextCues, ClaimNotes, Lang. Forbidden: invented support counts, contrasting percents, mention totals, API keys. Banner: not a Scite billing estimate; not a peer-review or clinical conclusion. 2. Citation context map: one numbered row per Inventory paper stub or context cue. Missing ClaimNotes write NOT IN INPUTS. Use Scite Supporting, Contrasting, Mentioning, Smart Citations, and Citation Statements language when Inventory supports it. Never print support-count or contrasting-percent VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed papers stay NOT IN INPUTS. Never invent mention-total VALUES not in Inventory. 4. Version lock: print Version. Refuse Scite features newer than Version if Version is named. 5. Refuse list: inventing support counts, inventing contrasting percents, inventing mention totals, inventing API keys. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented support VALUES. Teach Scite citation context maps, not a Connected Papers or Consensus swap. - Honor Version. No emojis. Refuse to invent DOIs not in Inventory.
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 Meta as pasted context cue Supporting as pasted claim notes Sample size caution as pasted; paper River Ops Diet Trial as pasted context cue Contrasting as pasted. Support invent NONE. Contrast invent NONE. Version: Scite.ai web as pasted (do not invent unreleased auto-summary pack) Workspace: Harbor Quay lit review library as pasted SpecNames: Sleep Meta context map as pasted; Diet Trial context map as pasted. Mention total UNKNOWN. PaperCues: Sleep Meta as pasted; Diet Trial as pasted. Protocol UNKNOWN. ContextCues: Supporting as pasted; Contrasting as pasted. Mentioning UNKNOWN. ClaimNotes: Sample size caution as pasted. Support count VALUES NOT IN INPUTS. Banned: guaranteed support, support invent, contrast invent, mention invent Never: invent support counts, invent contrasting percents, invent mention totals, invent API keys Format: ledger + table + specs + version + refuse + compliance Lang: English
Example Output
1. Ledger. Inventory: paper Harbor Quay Sleep Meta context cue Supporting claim notes Sample size caution; paper River Ops Diet Trial context cue Contrasting. Support invent NONE. Contrast invent NONE. Version Scite.ai web. Workspace Harbor Quay lit review library. SpecNames Sleep Meta context map; Diet Trial context map; Mention total UNKNOWN. PaperCues Sleep Meta; Diet Trial; Protocol UNKNOWN. ContextCues Supporting; Contrasting; Mentioning UNKNOWN. ClaimNotes Sample size caution; Support count VALUES NOT IN INPUTS. Lang English. Banner: not a Scite billing estimate; not a peer-review or clinical conclusion. Forbidden: invented support counts, contrasting percents, mention totals, API keys, guaranteed support, support invent, contrast invent, mention invent. 2. Citation context map. 1. Harbor Quay Sleep Meta | PaperCues Sleep Meta as pasted | ContextCues Supporting as pasted | ClaimNotes Sample size caution as pasted | support VALUES NONE | contrast NONE | Scite citation context map only. 2. River Ops Diet Trial | PaperCues Diet Trial as pasted | ContextCues Contrasting as pasted | ClaimNotes beyond Sample size caution NOT IN INPUTS | support VALUES NONE | contrast NONE. Mention total UNKNOWN so write mention total NOT IN INPUTS. Protocol not invented beyond PaperCues. 3. Spec name set. Sleep Meta context map; Diet Trial context map as SpecNames. Mention total UNKNOWN so write mention total NOT IN INPUTS. No support VALUES beyond Inventory. No third paper invented. 4. Version lock. Scite.ai web as pasted. Unreleased auto-summary pack not used. Mentioning ContextCues NOT IN INPUTS. 5. Refuse. Support invent: refused. Contrast invent: refused. Mention invent: refused. API invent: refused. Guaranteed support: refused. 6. Compliance. Banned hits none. Format ledger+table+specs+version+refuse+compliance. Gaps: mention total policy, Protocol PaperCues, Mentioning ContextCues, support count VALUES ClaimNotes, DOI list 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.