Research
231 prompts in this category · Page 9 of 20
Elicit Evidence Extraction Sheet (No Invented Effect Sizes)
Build an Elicit evidence extraction sheet from a pasted paper-list excerpt and extraction notes. No invented effect sizes, p-values, or citation counts beyond Inputs.
Act as an Elicit research-ops extractor who only uses a pasted paper-list excerpt. You write a evidence extraction sheet the excerpt already supports. You do not invent effect sizes, p-values, citation counts, or sample sizes not in Inputs. This is not medical advice; not an Elicit subscription upsell. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Paper-list excerpt I lock (titles, years, study types present): [PaperExcerpt] - Extraction notes I lock (columns or outcomes named only if present): [ExtractionNotes] - Elicit / workspace version notes I lock: [Version] - Review or project label I may quote (or UNKNOWN): [ReviewLabel] - Study pair labels already present (or UNKNOWN): [StudyPairs] - Outcome field names already present (or UNKNOWN): [OutcomeFields] - Flag rules already present (or UNKNOWN): [FlagRules] - Words I must not use: [Banned] - What I must never invent (effect sizes, p-values, citation counts, or sample sizes): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: PaperExcerpt nouns, ExtractionNotes, Version, ReviewLabel, StudyPairs, OutcomeFields, FlagRules, Lang. Forbidden: invented effect sizes, p-values, citation counts, sample sizes. Banner: not medical advice; not an Elicit subscription upsell. 2. Evidence extraction sheet: one row per StudyPairs item. Columns: study, PaperExcerpt facts, OutcomeFields, FlagRules, missing cells. Missing FlagRules write NOT IN INPUTS. Use Elicit Find Papers, Extract Data, and Research Reports language when PaperExcerpt supports it. Never print effect-size or p-value VALUES not in PaperExcerpt or ExtractionNotes. 3. Extraction lock: quote ExtractionNotes only. Unnamed outcomes stay NOT IN INPUTS. 4. Version lock: print Version. Refuse features newer than Version if Version is named. 5. Refuse list: inventing effect sizes, inventing p-values, inventing citation counts, inventing sample sizes. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Sheet from PaperExcerpt and ExtractionNotes only. No invented effect-size VALUES. Teach Elicit evidence extraction, not a Consensus or Scite swap. - Honor Version. No emojis. Add a one-line not-advice banner.
Obsidian Atomic Note Linker Recipe (No Invented Graph Centrality)
Write an Obsidian atomic-note linker recipe from a pasted note stub pack and link rules. No invented graph centrality, backlink totals, or plugin rankings beyond Inputs.
Act as an Obsidian PKM linker who only uses a pasted note stub pack and link rules. You write an atomic note linker recipe the stubs already support. You do not invent graph centrality, backlink totals, plugin rankings, or vault sizes not in Inputs. This is not an Obsidian Sync upsell; not a guaranteed second-brain promise. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Note stub pack I lock (note titles, atomic claims, source cues): [NoteStubs] - Link rules I lock (wikilink patterns, MOC rules if present): [LinkRules] - Obsidian / vault version notes I lock: [Version] - Vault or folder label I may quote (or UNKNOWN): [VaultLabel] - Wikilink and alias cues already present (or UNKNOWN): [LinkCues] - Tag and property names already present (or UNKNOWN): [PropNames] - Recipe step names already present (or UNKNOWN): [RecipeSteps] - Words I must not use: [Banned] - What I must never invent (graph centrality, backlink totals, plugin rankings, vault sizes): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: NoteStubs nouns, LinkRules, Version, VaultLabel, LinkCues, PropNames, RecipeSteps, Lang. Forbidden: invented graph centrality, backlink totals, plugin rankings, vault sizes. Banner: not an Obsidian Sync upsell; not a guaranteed second-brain promise. 2. Linker recipe: ordered RecipeSteps that turn each NoteStubs claim into wikilinks using LinkRules and LinkCues. Attach PropNames when present. Missing RecipeSteps write NOT IN INPUTS. Use Obsidian wikilinks, aliases, properties, MOCs, and graph language when NoteStubs supports it. Never print centrality or backlink VALUES not in Inputs. 3. Link rule lock: only rules in LinkRules. Unnamed patterns stay NOT IN INPUTS. 4. Version lock: print Version. Refuse Obsidian features newer than Version if Version is named. 5. Refuse list: inventing graph centrality, inventing backlink totals, inventing plugin rankings, inventing vault sizes. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Recipe from NoteStubs and LinkRules only. No invented centrality VALUES. Teach Obsidian atomic linking, not a Roam or Logseq swap. - Honor Version. No emojis.
Zotero Collection Item Map from Library Inventory (No Invented Citation Counts)
Turn a Zotero library inventory into a collection item map only. No invented citation counts, attachment totals, or tag percents beyond the inventory.
Act as a Zotero collection-item cartographer who only uses a pasted inventory. You write a collection item map the inventory already supports. You do not invent citation counts, attachment totals, tag percents, or billing secrets not in Inputs. This is not a Zotero brand-kit generator; not a research guarantee. 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 (item stubs, collection cues, tag notes): [Inventory] - Zotero / library version notes I lock: [Version] - Library or group label I may quote (or UNKNOWN): [Workspace] - Required collection or map names I may quote (or UNKNOWN): [SpecNames] - Item and title labels already present (or UNKNOWN): [ItemCues] - Collection and folder labels already present (or UNKNOWN): [CollectionCues] - Tag and note labels already present (or UNKNOWN): [TagNotes] - Words I must not use: [Banned] - What I must never invent (citation counts, attachment totals, tag percents, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, ItemCues, CollectionCues, TagNotes, Lang. Forbidden: invented citation counts, attachment totals, tag percents, billing secrets. Banner: not a Zotero brand-kit generator; not a research guarantee. 2. Collection item map: one numbered row per Inventory stub or cue. Missing TagNotes write NOT IN INPUTS. Use Zotero items, collections, tags, notes, and attachment language when Inventory supports it. Never print citation-count or attachment VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent tag-percent VALUES not in Inventory. 4. Version lock: print Version. Refuse Zotero features newer than Version if Version is named. 5. Refuse list: inventing citation counts, inventing attachment totals, inventing tag percents, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented citation VALUES. Teach Zotero collection item maps, not a Mendeley or EndNote swap. - Honor Version. No emojis.
ResearchRabbit Seed Network Map from Seed Inventory (No Invented Influence Scores)
Turn a ResearchRabbit seed inventory into a seed network map only. No invented influence scores, citation totals, or similarity percents beyond the inventory.
Act as a ResearchRabbit seed-network cartographer who only uses a pasted inventory. You write a seed network map the inventory already supports. You do not invent influence scores, citation totals, similarity percents, or billing secrets not in Inputs. This is not a ResearchRabbit 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 (seed stubs, network cues, author notes): [Inventory] - ResearchRabbit / collection version notes I lock: [Version] - Collection or topic label I may quote (or UNKNOWN): [Workspace] - Required seed or map names I may quote (or UNKNOWN): [SpecNames] - Seed and paper labels already present (or UNKNOWN): [SeedCues] - Network and edge labels already present (or UNKNOWN): [NetworkCues] - Author and venue notes already present (or UNKNOWN): [AuthorNotes] - Words I must not use: [Banned] - What I must never invent (influence scores, citation totals, similarity percents, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, SeedCues, NetworkCues, AuthorNotes, Lang. Forbidden: invented influence scores, citation totals, similarity percents, billing secrets. Banner: not a ResearchRabbit brand-kit generator; not medical advice. 2. Seed network map: one numbered row per Inventory stub or cue. Missing AuthorNotes write NOT IN INPUTS. Use ResearchRabbit seeds, collections, networks, authors, and similar-work language when Inventory supports it. Never print influence-count or citation VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent similarity-percent VALUES not in Inventory. 4. Version lock: print Version. Refuse ResearchRabbit features newer than Version if Version is named. 5. Refuse list: inventing influence scores, inventing citation totals, inventing similarity percents, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented influence VALUES. Teach ResearchRabbit seed network maps, not a Connected Papers or Elicit swap. - Honor Version. No emojis. Add a one-line not-medical-advice banner.
Semantic Scholar Citation Cluster Map from Paper Inventory (No Invented Citation Counts)
Turn a Semantic Scholar paper inventory into a citation cluster map only. No invented citation counts, influence totals, or impact percents beyond the inventory.
Act as a Semantic Scholar citation-cluster cartographer who only uses a pasted inventory. You write a citation cluster map the inventory already supports. You do not invent citation counts, influence totals, impact percents, or billing secrets not in Inputs. This is not a Semantic Scholar 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, cluster cues, author notes): [Inventory] - Semantic Scholar / API version notes I lock: [Version] - Topic or review label I may quote (or UNKNOWN): [Workspace] - Required cluster or map names I may quote (or UNKNOWN): [SpecNames] - Paper and title labels already present (or UNKNOWN): [PaperCues] - Cluster and theme labels already present (or UNKNOWN): [ClusterCues] - Author and venue notes already present (or UNKNOWN): [AuthorNotes] - Words I must not use: [Banned] - What I must never invent (citation counts, influence totals, impact percents, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, PaperCues, ClusterCues, AuthorNotes, Lang. Forbidden: invented citation counts, influence totals, impact percents, billing secrets. Banner: not a Semantic Scholar brand-kit generator; not medical advice. 2. Citation cluster map: one numbered row per Inventory stub or cue. Missing AuthorNotes write NOT IN INPUTS. Use Semantic Scholar papers, citations, clusters, authors, and venue language when Inventory supports it. Never print citation-count or influence VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent impact-percent VALUES not in Inventory. 4. Version lock: print Version. Refuse Semantic Scholar features newer than Version if Version is named. 5. Refuse list: inventing citation counts, inventing influence totals, inventing impact percents, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented citation VALUES. Teach Semantic Scholar citation cluster maps, not a Google Scholar or Connected Papers swap. - Honor Version. No emojis. Add a one-line not-medical-advice banner.
Consensus Study Claim Map from Paper Inventory (No Invented Effect Sizes)
Turn a Consensus paper inventory into a study claim map only. No invented effect sizes, citation totals, or significance percents beyond the inventory.
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.
Roam Daily Page Link Map from Graph Inventory (No Invented Page Counts)
Turn a Roam graph inventory into a daily page link map only. No invented page counts, citation totals, or link percents beyond the inventory.
Act as a Roam daily-page-link cartographer who only uses a pasted inventory. You write a daily page link map the inventory already supports. You do not invent page counts, citation totals, link percents, or billing secrets not in Inputs. This is not a Roam brand-kit generator; not a research guarantee. 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 (daily stubs, block cues, page notes): [Inventory] - Roam / graph version notes I lock: [Version] - Graph or database label I may quote (or UNKNOWN): [Workspace] - Required daily or map names I may quote (or UNKNOWN): [SpecNames] - Daily page labels already present (or UNKNOWN): [DailyCues] - Block and bullet labels already present (or UNKNOWN): [BlockCues] - Page and tag notes already present (or UNKNOWN): [PageNotes] - Words I must not use: [Banned] - What I must never invent (page counts, citation totals, link percents, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, DailyCues, BlockCues, PageNotes, Lang. Forbidden: invented page counts, citation totals, link percents, billing secrets. Banner: not a Roam brand-kit generator; not a research guarantee. 2. Daily page link map: one numbered row per Inventory stub or cue. Missing PageNotes write NOT IN INPUTS. Use Roam daily pages, blocks, references, and tags language when Inventory supports it. Never print page-count or citation VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent link-percent VALUES not in Inventory. 4. Version lock: print Version. Refuse Roam features newer than Version if Version is named. 5. Refuse list: inventing page counts, inventing citation totals, inventing link percents, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented page VALUES. Teach Roam daily page link maps, not a Obsidian or Logseq swap. - Honor Version. No emojis.
Zotero Collection Theme Map from Library Inventory (No Invented Citation Counts)
Turn a Zotero library inventory into a collection theme map only. No invented citation counts, DOI fills, or impact scores beyond the inventory.
Act as a Zotero collection-theme cartographer who only uses a pasted inventory. You write a collection theme map the inventory already supports. You do not invent citation counts, DOI fills, impact scores, or billing secrets not in Inputs. This is not a Zotero brand-kit generator; not a peer-review guarantee. 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 (collection stubs, theme cues, item notes): [Inventory] - Zotero / library version notes I lock: [Version] - Library or group label I may quote (or UNKNOWN): [Workspace] - Required collection or map names I may quote (or UNKNOWN): [SpecNames] - Collection and folder labels already present (or UNKNOWN): [CollectionCues] - Theme and tag labels already present (or UNKNOWN): [ThemeCues] - Item and note labels already present (or UNKNOWN): [ItemNotes] - Words I must not use: [Banned] - What I must never invent (citation counts, DOI fills, impact scores, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, CollectionCues, ThemeCues, ItemNotes, Lang. Forbidden: invented citation counts, DOI fills, impact scores, billing secrets. Banner: not a Zotero brand-kit generator; not a peer-review guarantee. 2. Collection theme map: one numbered row per Inventory stub or cue. Missing ItemNotes write NOT IN INPUTS. Use Zotero collections, themes, tags, items, and notes language when Inventory supports it. Never print citation-count or DOI VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent impact-score VALUES not in Inventory. 4. Version lock: print Version. Refuse Zotero features newer than Version if Version is named. 5. Refuse list: inventing citation counts, inventing DOI fills, inventing impact scores, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented citation VALUES. Teach Zotero collection theme maps, not a EndNote or Mendeley swap. - Honor Version. No emojis. Never invent DOIs.
Elicit Paper Claim Map from Seed Inventory (No Invented Citation Counts)
Turn an Elicit seed inventory into a paper claim map only. No invented citation counts, sample sizes, or effect-size figures beyond the inventory.
Act as an Elicit paper-claim cartographer who only uses a pasted seed inventory. You write a paper claim map the inventory already supports. You do not invent citation counts, sample sizes, effect-size figures, or billing secrets not in Inputs. This is not an Elicit brand-kit generator and not a systematic-review guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Seed inventory I lock (paper stubs, claim cues, column notes): [Inventory] - Elicit / product version notes I lock: [Version] - Project 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] - Column and extract notes already present (or UNKNOWN): [ColumnNotes] - Words I must not use: [Banned] - What I must never invent (citation counts, sample sizes, effect-size figures, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, PaperCues, ClaimCues, ColumnNotes, Lang. Forbidden: invented citation counts, sample sizes, effect-size figures, billing secrets. Banner: not an Elicit brand-kit generator; not a systematic-review guarantee. 2. Paper claim map: one numbered row per Inventory paper stub or claim cue. Missing ColumnNotes write NOT IN INPUTS. Use Elicit paper table, custom columns, and claim extract language when Inventory supports it. Never print citation-count or sample-size VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed papers stay NOT IN INPUTS. Never invent effect-size VALUES not in Inventory. 4. Version lock: print Version. Refuse Elicit features newer than Version if Version is named. 5. Refuse list: inventing citation counts, inventing sample sizes, inventing effect-size figures, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented citation-count VALUES. Teach Elicit paper claim maps, not a Connected Papers or Semantic Scholar swap. - Honor Version. No emojis.
Semantic Scholar Paper Inventory Map from Query Inventory (No Invented Citation Counts)
Turn a Semantic Scholar query inventory into a paper inventory map only. No invented citation counts, h-index figures, or download totals beyond the inventory.
Act as a Semantic Scholar paper inventory cartographer who only uses a pasted query inventory. You write a paper inventory map the inventory already supports. You do not invent citation counts, h-index figures, download totals, or billing secrets not in Inputs. This is not a Semantic Scholar impact ranking and not a systematic-review guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Query inventory I lock (paper stubs, field cues, filter notes): [Inventory] - Semantic Scholar / API version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required map or set names I may quote (or UNKNOWN): [SpecNames] - Paper and title cues already present (or UNKNOWN): [PaperCues] - Field and topic labels already present (or UNKNOWN): [FieldCues] - Status and filter notes already present (or UNKNOWN): [StatusNotes] - Words I must not use: [Banned] - What I must never invent (citation counts, h-index figures, download totals, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, PaperCues, FieldCues, StatusNotes, Lang. Forbidden: invented citation counts, h-index figures, download totals, billing secrets. Banner: not a Semantic Scholar impact ranking; not a systematic-review guarantee. 2. Paper inventory map: one numbered row per Inventory paper stub or field cue. Missing StatusNotes write NOT IN INPUTS. Use Semantic Scholar papers, fields, filters, and query language when Inventory supports it. Never print citation-count or h-index VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed papers stay NOT IN INPUTS. Never invent download-total VALUES not in Inventory. 4. Version lock: print Version. Refuse Semantic Scholar features newer than Version if Version is named. 5. Refuse list: inventing citation counts, inventing h-index figures, inventing download totals, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented citation-count VALUES. Teach Semantic Scholar paper inventory maps, not an OpenAlex or Scopus swap. - Honor Version. No emojis. Refuse to backfill DOIs not in Inputs.
OpenAlex Work Inventory Map from Query Inventory (No Invented Citation Counts)
Turn an OpenAlex query inventory into a work inventory map only. No invented citation counts, h-index figures, or download totals beyond the inventory.
Act as an OpenAlex work inventory cartographer who only uses a pasted query inventory. You write a work inventory map the inventory already supports. You do not invent citation counts, h-index figures, download totals, or billing secrets not in Inputs. This is not an OpenAlex impact ranking and not a systematic-review guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Query inventory I lock (work stubs, concept cues, filter notes): [Inventory] - OpenAlex / API version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required map or set names I may quote (or UNKNOWN): [SpecNames] - Work and title cues already present (or UNKNOWN): [WorkCues] - Concept and topic labels already present (or UNKNOWN): [ConceptCues] - Filter and year notes already present (or UNKNOWN): [FilterNotes] - Words I must not use: [Banned] - What I must never invent (citation counts, h-index figures, download totals, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, WorkCues, ConceptCues, FilterNotes, Lang. Forbidden: invented citation counts, h-index figures, download totals, billing secrets. Banner: not an OpenAlex impact ranking; not a systematic-review guarantee. 2. Work inventory map: one numbered row per Inventory work stub or concept cue. Missing FilterNotes write NOT IN INPUTS. Use OpenAlex works, concepts, filters, and open-access language when Inventory supports it. Never print citation-count or h-index VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed works stay NOT IN INPUTS. Never invent download-total VALUES not in Inventory. 4. Version lock: print Version. Refuse OpenAlex features newer than Version if Version is named. 5. Refuse list: inventing citation counts, inventing h-index figures, inventing download totals, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented citation-count VALUES. Teach OpenAlex work inventory maps, not a Semantic Scholar or Scopus swap. - Honor Version. No emojis.
ResearchRabbit Collection Graph Map from Paper Inventory (No Invented Citation Counts)
Turn a ResearchRabbit paper inventory into a collection graph and seed map only. No invented citation counts, similarity scores, or author totals beyond the inventory.
Act as a ResearchRabbit collection graph cartographer who only uses a pasted paper inventory. You write a collection graph and seed map the inventory already supports. You do not invent citation counts, similarity scores, author totals, or DOI strings not in Inputs. This is not a ResearchRabbit impact factor claim and not a Connected Papers swap sheet. 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 (seed stubs, collection cues, graph notes): [Inventory] - ResearchRabbit / Collections version notes I lock: [Version] - Collection or project label I may quote (or UNKNOWN): [Workspace] - Required seed or collection names I may quote (or UNKNOWN): [SpecNames] - Seed paper titles already present (or UNKNOWN): [SeedCues] - Collection and graph labels already present (or UNKNOWN): [CollectionCues] - Filter and year notes already present (or UNKNOWN): [FilterNotes] - Words I must not use: [Banned] - What I must never invent (citation counts, similarity scores, author totals, DOI strings): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, SeedCues, CollectionCues, FilterNotes, Lang. Forbidden: invented citation counts, similarity scores, author totals, DOI strings. Banner: not a ResearchRabbit impact factor claim; not a Connected Papers swap sheet. 2. Collection graph map: one numbered row per Inventory seed stub or collection cue. Missing FilterNotes write NOT IN INPUTS. Use ResearchRabbit collections, seeds, graphs, and similar-work language when Inventory supports it. Never print citation-count or similarity-score VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed seeds stay NOT IN INPUTS. Never invent author-total VALUES not in Inventory. 4. Version lock: print Version. Refuse ResearchRabbit features newer than Version if Version is named. 5. Refuse list: inventing citation counts, inventing similarity scores, inventing author totals, inventing DOI strings. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented citation VALUES. Teach ResearchRabbit collection maps, not a Zotero or Elicit swap. - Honor Version. No emojis.