Reusable AI capability
Maintain Citation Currency and Supersession Decisions
Apply a recurring method to detect corrected, retracted, obsolete, or superseded citations and govern claim updates without confusing age with invalidity.
This Skill packages a reusable way to use the linked Prompt or Workflow; Amo.ng does not run it for you.
# Maintain Citation Currency and Supersession Decisions Skill ID: AMO-S-000026 Skill URL: https://amo.ng/skills/maintain-citation-currency-supersession-decisions Purpose: Give researchers, editors, policy owners, and release owners a reusable evidence-currentness capability for periodic review, new-source alerts, and pre-release citation gates. Required inputs: - Exact consequential claims and intended publication, decision, or policy use - Citation register, source versions and dates, links, identifiers, and accessible source content - Corrections, retractions, later editions, updates, superseding evidence or guidance, and review cutoff date - Population, jurisdiction, method, authority, and decision-condition requirements - Research, editorial, policy, legal, and release owners where applicable How to use: When to use: - Existing claims rely on evidence that may have been corrected, retracted, updated, or superseded. - A recurring review or release gate must decide whether citations remain current for their exact use. When not to use: - General source discovery with no exact claim and citation set. - Rejecting evidence merely because it is old. - Treating a newer source as automatically more authoritative or applicable. Reusable method: 1. Freeze claim wording, intended use, decision conditions, and review cutoff. 2. Record each citation's version, date, authority, population, jurisdiction, method, and source status. 3. Search supplied or accessible evidence for corrections, retractions, later versions, living updates, superseding guidance, and material new evidence. 4. Compare applicability and authority, then classify each citation as Current, Current with limits, Superseded, Corrected, Retracted, Inaccessible, or Unresolved. 5. Trace which claims and downstream decisions are affected and whether support remains sufficient. 6. Set Retain, Replace, Narrow, Hold, Remove, or Correct dispositions with owners, deadlines, and re-review triggers. Expected output: A citation currency register, supersession chain, affected-claim map, source-authority comparison, unresolved access gaps, wording and citation actions, and owner release decisions. Boundaries: Do not invent source access, status, updates, applicability, or approval. Researchers and editors approve evidence and wording; policy and domain owners approve use boundaries; legal reviewers interpret legal requirements; the release owner controls publication or correction. Source: AMO-P-000320. Applicable Workflow: AMO-W-000011. Powered by Prompt: Citation Obsolescence and Supersession Audit Source ID: AMO-P-000320 https://amo.ng/prompts/citation-obsolescence-supersession-audit Completion criteria: Complete when every material citation has a status and evidence date; corrections, retractions, later versions, and superseding sources are dispositioned; affected claims have Retain, Replace, Narrow, Hold, Remove, or Correct actions; and unresolved evidence has an owner and re-review trigger. Use this Amo.ng Skill with your preferred AI tool. Supply the required inputs and follow the usage instructions. # Maintain Citation Currency and Supersession Decisions Skill ID: AMO-S-000026 Skill URL: https://amo.ng/skills/maintain-citation-currency-supersession-decisions Purpose: Give researchers, editors, policy owners, and release owners a reusable evidence-currentness capability for periodic review, new-source alerts, and pre-release citation gates. Required inputs: - Exact consequential claims and intended publication, decision, or policy use - Citation register, source versions and dates, links, identifiers, and accessible source content - Corrections, retractions, later editions, updates, superseding evidence or guidance, and review cutoff date - Population, jurisdiction, method, authority, and decision-condition requirements - Research, editorial, policy, legal, and release owners where applicable How to use: When to use: - Existing claims rely on evidence that may have been corrected, retracted, updated, or superseded. - A recurring review or release gate must decide whether citations remain current for their exact use. When not to use: - General source discovery with no exact claim and citation set. - Rejecting evidence merely because it is old. - Treating a newer source as automatically more authoritative or applicable. Reusable method: 1. Freeze claim wording, intended use, decision conditions, and review cutoff. 2. Record each citation's version, date, authority, population, jurisdiction, method, and source status. 3. Search supplied or accessible evidence for corrections, retractions, later versions, living updates, superseding guidance, and material new evidence. 4. Compare applicability and authority, then classify each citation as Current, Current with limits, Superseded, Corrected, Retracted, Inaccessible, or Unresolved. 5. Trace which claims and downstream decisions are affected and whether support remains sufficient. 6. Set Retain, Replace, Narrow, Hold, Remove, or Correct dispositions with owners, deadlines, and re-review triggers. Expected output: A citation currency register, supersession chain, affected-claim map, source-authority comparison, unresolved access gaps, wording and citation actions, and owner release decisions. Boundaries: Do not invent source access, status, updates, applicability, or approval. Researchers and editors approve evidence and wording; policy and domain owners approve use boundaries; legal reviewers interpret legal requirements; the release owner controls publication or correction. Source: AMO-P-000320. Applicable Workflow: AMO-W-000011. Powered by Prompt: Citation Obsolescence and Supersession Audit Source ID: AMO-P-000320 https://amo.ng/prompts/citation-obsolescence-supersession-audit Completion criteria: Complete when every material citation has a status and evidence date; corrections, retractions, later versions, and superseding sources are dispositioned; affected claims have Retain, Replace, Narrow, Hold, Remove, or Correct actions; and unresolved evidence has an owner and re-review trigger.Copy skill copies the Skill details. Use with AI adds a short instruction for your preferred AI tool; neither action runs the Skill.
Purpose
Give researchers, editors, policy owners, and release owners a reusable evidence-currentness capability for periodic review, new-source alerts, and pre-release citation gates.
Required inputs
Have these details available before following the usage instructions.
- Exact consequential claims and intended publication, decision, or policy use
- Citation register, source versions and dates, links, identifiers, and accessible source content
- Corrections, retractions, later editions, updates, superseding evidence or guidance, and review cutoff date
- Population, jurisdiction, method, authority, and decision-condition requirements
- Research, editorial, policy, legal, and release owners where applicable
How to use this Skill
When to use:
- Existing claims rely on evidence that may have been corrected, retracted, updated, or superseded.
- A recurring review or release gate must decide whether citations remain current for their exact use.
When not to use:
- General source discovery with no exact claim and citation set.
- Rejecting evidence merely because it is old.
- Treating a newer source as automatically more authoritative or applicable.
Reusable method:
1. Freeze claim wording, intended use, decision conditions, and review cutoff.
2. Record each citation's version, date, authority, population, jurisdiction, method, and source status.
3. Search supplied or accessible evidence for corrections, retractions, later versions, living updates, superseding guidance, and material new evidence.
4. Compare applicability and authority, then classify each citation as Current, Current with limits, Superseded, Corrected, Retracted, Inaccessible, or Unresolved.
5. Trace which claims and downstream decisions are affected and whether support remains sufficient.
6. Set Retain, Replace, Narrow, Hold, Remove, or Correct dispositions with owners, deadlines, and re-review triggers.
Expected output:
A citation currency register, supersession chain, affected-claim map, source-authority comparison, unresolved access gaps, wording and citation actions, and owner release decisions.
Boundaries:
Do not invent source access, status, updates, applicability, or approval. Researchers and editors approve evidence and wording; policy and domain owners approve use boundaries; legal reviewers interpret legal requirements; the release owner controls publication or correction. Source: AMO-P-000320. Applicable Workflow: AMO-W-000011.
Powered by an Amo.ng Prompt
Citation Obsolescence and Supersession Audit
Open the linked prompt to use the instructions that power this Skill.
Open prompt
Audit whether a bounded set of citations remains current and authoritative enough to support specified claims or decisions. Trace corrections, retractions, updates, superseding guidance, changed methods, and changed operating context.
Provide:
- Exact claims, audience, publication or decision use, required evidence strength, and consequence of stale support: [Claims and intended decision use]
- Citations, identifiers, links, source extracts, quoted claims, access dates, and provenance already used: [Current citation set and source extracts]
- Publisher notices, errata, retractions, expressions of concern, version history, review updates, and replacement sources: [Publication correction and update evidence]
- Current guidelines, standards, policy, authoritative reviews, later evidence, population/context changes, and applicability constraints: [Current authority and context evidence]
- As-of date, source-access limits, researcher/editor, domain reviewer, policy/legal reviewer, and publication owner: [Review date constraints and accountable owners]
Use authoritative and primary sources where accessible. Do not invent a retraction, correction, update, consensus, publication date, or source conclusion. Clearly distinguish supplied evidence from newly located sources if browsing is available. When a source cannot be accessed, mark it Unverified rather than inferring current status from a search snippet. Do not equate age alone with obsolescence.
Audit:
1. Map claims to citations.
Break consequential statements into bounded claims and identify every source used for each. Record whether the citation directly supports the claim, provides background, or is cited through an intermediary.
2. Verify source identity and status.
Confirm identifier, title, publisher, version, date, correction/retraction status, and canonical record. Identify duplicate versions, preprint-to-publication transitions, and secondary citations.
3. Search for supersession evidence.
Review later official guidance, standards, systematic reviews, replications, corrections, retractions, updated datasets, changed law/policy supplied or discovered. Do not assume later publication automatically supersedes stronger earlier evidence.
4. Assess continued applicability.
Check population, jurisdiction, technology, measurement, intervention, baseline risk, data period, and operating conditions. Explain which changed conditions weaken transfer to the current claim.
5. Classify citation status.
Use Current and authoritative, Current with limitations, Superseded for this use, Corrected claim required, Retracted/withdrawn, Context no longer applicable, Conflicting current evidence, or Unable to determine.
6. Determine claim impact.
For each affected claim choose Retain, Qualify, Narrow, Replace citation, Add contradictory evidence, Correct, or Withdraw. Avoid rewriting beyond the evidence.
7. Define ongoing revalidation.
Specify monitoring sources, event triggers, time-based review where justified, owner, and evidence needed before a withdrawn claim can return.
Use Perplexity to locate public source candidates and supersession signals, but verify each claim against the supplied or directly accessible authoritative record and do not claim a source was inspected when it was not. Keep sensitive or licensed material within its authorized access boundary. The researcher owns source tracing, while the policy, legal, clinical, or publication owner approves consequential wording or use. Require acceptance evidence for each citation: expected observation, actual observation, authoritative locator, supersession check, unresolved conflict, and safe rollback to qualified wording. Proposed replacements are not published or approved changes.
Reconcile every citation decision against its acceptance evidence, expected observation, actual observation, and authoritative source before marking the audit complete.
Required deliverable:
# Citation Obsolescence and Supersession Audit
## Claim-to-Citation Map
| Claim | Citation/identifier | Support type | Direct/indirect | Evidence supplied | Importance |
|---|---|---|---|---|---|
## Source Status Ledger
| Source | Canonical version | Correction/retraction/update | Superseding evidence | Applicability change | Status | Confidence |
|---|---|---|---|---|---|---|
## Claim Impact Decisions
| Claim | Current support status | Required action | Replacement/qualification evidence | Reviewer | Publication consequence |
|---|---|---|---|---|---|
## Unresolved and Conflicting Evidence
| Issue | Missing access/evidence | Why it matters | Safe interim wording/action | Owner |
|---|---|---|---|---|
## Revalidation Plan
| Trigger/source | Claims affected | Action | Owner | Next review condition |
|---|---|---|---|---|
Completion requires a status for every material citation, explicit handling of inaccessible or conflicting evidence, and publication decisions no broader than current source authority supports.
Completion criteria
Complete when every material citation has a status and evidence date; corrections, retractions, later versions, and superseding sources are dispositioned; affected claims have Retain, Replace, Narrow, Hold, Remove, or Correct actions; and unresolved evidence has an owner and re-review trigger.
Explore related Workflows
Browse WorkflowsProduce an Evidence-Traceable Literature Review
Refine a defensible research question, screen and extract evidence, synthesize the corpus, audit citation currency, and trace material conclusions to original evidence.
Related Prompts
Browse PromptsPreprint-to-Policy Use Risk Review
Decide whether preliminary research is mature enough to inform a policy or operating decision, with bounded claims, reversible use, and monitoring conditions.
Review whether a preprint or other preliminary research result is fit to inform a specific policy or operating decision. Produce a bounded evidence-use decision, not a general paper summary or prediction of peer-review outcome. Provide: - Proposed policy, standard, guidance, or operational decision; affected population; urgency; reversibility; and cost of error: [Proposed policy decision and urgency] - Preprint, protocol, supplementary material, data/code availability, disclosures, version history, and authors' stated limitations: [Preprint and supporting materials] - Peer-reviewed studies, systematic reviews, replications, guidelines, official data, and contradictory evidence relevant to the claim: [Related peer-reviewed and authoritative evidence] - Target population, setting, jurisdiction, feasibility, equity, implementation, monitoring, and resource constraints: [Population context and implementation constraints] - Evidence standard, risk tolerance, researcher, domain reviewer, legal/policy reviewer, ethics/privacy reviewer, and decision owner: [Risk thresholds and accountable reviewers] Do not imply that a preprint is false because it is unreviewed or reliable because it is novel. Do not invent peer-review comments, replication, data access, conflicts, or regulatory requirements. Distinguish reported findings, your inference, missing evidence, author interpretation, and external corroboration. Use an as-of date and link authoritative sources when browsing is available. Review: 1. Define the policy claim. State exactly what action the evidence is proposed to support, for whom, for how long, and what error would matter. Separate exploratory learning from binding policy. 2. Audit research maturity and provenance. Review protocol preregistration, study design, sample, measures, analysis plan, deviations, missing data, effect uncertainty, data/code access, conflicts, version changes, and correction status using supplied evidence. 3. Assess internal validity. Identify selection, measurement, confounding, multiplicity, leakage, outcome switching, model dependence, power, attrition, and robustness concerns appropriate to the study. Do not demand methods irrelevant to the design. 4. Assess external and policy validity. Compare study population, intervention/exposure, setting, baseline conditions, timeframe, jurisdiction, implementation requirements, and outcome with the proposed policy context. 5. Triangulate. Map agreement, contradiction, and missing replication across peer-reviewed research, reviews, guidance, official data, and related mechanisms. Weight source authority and directness rather than counting papers. 6. Model decision asymmetry. Consider harm of acting on a false or exaggerated result, harm of delaying a real benefit, reversibility, monitoring latency, affected groups, and availability of lower-risk alternatives. 7. Select a use boundary. Choose Do not use, Use only to frame research/questions, Use for a reversible pilot, Use as one input with corroboration, or Use for provisional policy with safeguards. State claims not supported. 8. Define safeguards and update triggers. Specify scope, duration, consent/communication where relevant, monitoring, independent review, stop conditions, version watch, peer-reviewed publication, replication, correction/retraction, or new guidance triggers. The researcher assesses evidence strength, while the policy owner and relevant legal, ethics, clinical, or domain reviewer approve consequential use; this review does not authorize policy adoption. For every proposed use, require acceptance evidence with the expected observation, actual observation from supplied corroboration, uncertainty boundary, monitoring trigger, and rollback or suspension condition. Keep unreviewed actions proposed. Record approval from the policy owner and each applicable legal, ethics, clinical, or domain reviewer before consequential use. Required deliverable: # Preprint-to-Policy Use Risk Review ## Proposed Decision and Evidence Standard - Decision/action: - Population/context: - Urgency and reversibility: - Cost of false action / delayed action: - Required evidence standard: ## Research Maturity and Validity Ledger | Dimension | Evidence | Strength/limitation | Uncertainty | Policy consequence | |---|---|---|---|---| ## External Applicability Map | Study condition | Policy condition | Match/gap | Consequence | Evidence needed | |---|---|---|---|---| ## Triangulation Matrix | Claim | Preprint evidence | Corroborating evidence | Contradictory evidence | Authority/directness | Confidence | |---|---|---|---|---|---| ## Evidence-Use Decision - Decision: - Allowed use and wording: - Prohibited claim/use: - Scope and duration: - Required safeguards and reviewers: - Stop/update triggers: - Residual uncertainty: ## Evidence Development Plan | Priority | Missing evidence | Source/test | Owner | Decision it would change | |---|---|---|---|---| Completion requires an explicit policy-use boundary, direct treatment of uncertainty and applicability, a reversible path where evidence is preliminary, and named triggers that force reassessment when the evidence record changes.
View prompt
4 views
Systematic Review Update Decision Brief
Decide whether an existing systematic review needs an update and define the safest bounded scope before committing review resources.
Produce a Systematic Review Update Decision Brief that determines whether the existing review should be updated now, deferred, monitored, or amended with a bounded scope. Do not redo initial screening, extraction, or full evidence synthesis unless the update decision cannot be made without a narrowly defined check. Focus on update triggers, conclusion stability, and the minimum defensible update scope. Inputs: - Review title and citation: [Review title and citation] - Review question or PICO: [Review question or PICO] - Original search end date: [Original search end date] - Original conclusions and certainty ratings: [Original conclusions and certainty ratings] - Surveillance sources and date range: [Surveillance sources and date range] - Current decision need: [Current decision need] - Known methodological or data issues: [Known methodological or data issues] Evidence discipline: - Separate observed evidence from inference. - Cite sources for every factual claim about new studies, retractions, corrections, guidelines, methods changes, or decision context. - State the date accessed for web sources when available. - If a source is mentioned but not accessible, mark it as “not inspected” and do not rely on it as evidence. - Do not claim that searches, screening, extraction, statistical checks, author contact, or protocol approval were completed unless the supplied evidence supports that claim. - Identify missing information that could materially change the decision. - Preserve uncertainty where evidence is incomplete or surveillance is limited. Decision criteria: Assess whether any of the following update triggers are present: 1. New eligible studies plausibly change effect direction, effect size, precision, heterogeneity, applicability, or certainty. 2. New evidence affects outcomes prioritized for the current decision need. 3. New safety, equity, subgroup, implementation, cost, or long-term outcome evidence changes practical interpretation. 4. Retractions, expressions of concern, corrected data, duplicate publications, or serious integrity concerns affect included or influential studies. 5. Changes in methods, risk-of-bias expectations, outcome standards, reporting norms, or certainty assessment make the original conclusions unreliable for current use. 6. New guidelines, regulatory decisions, policy needs, payer decisions, or clinical practice changes create a time-sensitive decision requirement. 7. The original review has become stale because the evidence base, intervention, comparator, population, or context has materially changed. Deliverable format: 1. Decision Snapshot - Existing review: cite the review. - Original evidence currency: state the original search end date. - Current decision need: summarize the decision the update must support. - Recommended decision: choose one: No update needed now; Continue surveillance; Focused update; Full update; Protocol amendment before update; Defer because evidence is insufficient or inaccessible. - Confidence in decision: High / Moderate / Low, with a short reason. - Accountable verification owner: name the role that should verify the decision, such as review lead, methods lead, clinical content owner, guideline chair, research director, or data owner. 2. Surveillance Evidence Log Create a table with these columns: - Evidence item - Source and citation - Date range or publication date - Why it may matter - Status: observed / inferred / not inspected - Link to original review question or PICO - Potential update trigger - Limitations or uncertainty Include new studies, trial registrations, preprints when relevant, retractions, corrections, expressions of concern, updated guidelines, methodological changes, and decision-context changes. Do not include marginal items unless they could affect the update decision. 3. New-Evidence Impact Matrix Create a matrix with these rows where applicable: - Population - Intervention or exposure - Comparator - Primary outcomes - Harms or safety outcomes - Equity or subgroup effects - Certainty of evidence - Risk of bias or study integrity - Applicability to the current decision need - Methods or reporting expectations For each row, provide: - New or changed evidence observed - Likely impact on original conclusion: none / minor / moderate / major / unknown - Basis for judgment - What would need to be checked in a formal update 4. Conclusion-Stability Assessment For each major original conclusion, assess: - Original conclusion and certainty rating - New evidence or issue relevant to that conclusion - Whether the conclusion is likely stable, possibly unstable, likely unstable, or cannot be assessed - Reasoning, distinguishing evidence from inference - Consequence if the conclusion changed 5. Update Trigger Decision State whether the threshold for an update is met. Use this structure: - Trigger status: met / not met / unclear - Triggering evidence or issue - Decision risk if no update is performed - Decision risk if an update is performed too broadly - Recommended update type and scope - Explicit exclusions from the update scope - Minimum evidence checks required before work begins 6. Bounded Update Scope Define the smallest responsible update scope: - Review question or PICO elements to retain unchanged - Elements to amend, if any - Outcomes to prioritize - Study designs to include or exclude - Date range to search - Databases, registries, and targeted sources to search - Whether re-screening of prior included studies is needed and why - Whether reanalysis is likely needed and why - Whether certainty assessment must be revised - Known exclusions that prevent scope creep 7. Protocol Amendment and Work Plan If any update or amendment is recommended, draft a practical work plan: - Required protocol amendments - Review team roles: review lead, information specialist, methods lead, content reviewer, statistician if needed, and data owner if corrected data are involved - Priority tasks in sequence - Evidence checks before extraction or synthesis - Estimated level of effort: low / medium / high, with rationale - Decision points where the update may be narrowed, expanded, paused, or stopped - Approval or sign-off needed from the accountable review, guideline, policy, or research owner If no update is recommended, provide a surveillance plan instead: - Conditions that would trigger reconsideration - Sources to monitor - Suggested surveillance interval - Owner responsible for monitoring 8. Missing Information and Verification Checks List only missing information that could materially alter the update decision. Then provide completion checks: - Are all relied-upon sources cited? - Are inaccessible sources clearly marked as not inspected? - Are observations separated from inference? - Is the update decision tied to explicit triggers? - Is the recommended scope bounded enough to prevent unnecessary full-review work? - Is owner verification clearly assigned? Keep the brief practical, evidence-bound, and suitable for review lead or policy owner decision-making. Avoid generic literature-summary prose.Claim Provenance Chain and Citation Traceability Audit
Audit consequential claims from current citation back to original source evidence, documenting where provenance breaks, mutates, or overstates authority.
Objective: Trace each material claim through its full citation chain to the earliest available original source, dataset, record, or primary evidence. Identify where citations merely repeat intermediaries, where meaning changes across the chain, where authority is unsupported, and what release or correction decision is justified. Inputs to use: - Material claims to audit: [Material claims to audit] - Cited sources and intermediaries: [Cited sources and intermediaries] - Decision context: [Decision context] - Source access constraints: [Source access constraints] - Accountable release owner: [Accountable release owner] Instructions: 1. Treat each claim as a separate audit unit. Do not collapse similar claims unless the evidence chain is demonstrably identical. 2. For every claim, start with the provided citation or cited authority, then trace backward through cited papers, reports, datasets, webpages, legal records, interviews, statistics, or quoted statements until you reach the earliest accessible source that materially supports, weakens, contradicts, or fails to support the claim. 3. Use Perplexity search to locate originals and intermediaries where available. Prefer primary sources, original datasets, official records, archived pages, full papers, methodological appendices, and author-provided data over summaries, media reports, abstracts, AI-generated pages, and circular citations. 4. Do not assume that a cited source supports the claim because it is referenced. Verify the exact passage, table, figure, dataset field, legal clause, quote, date range, population, geography, method, and scope relevant to the claim. 5. Distinguish observations from inference: - Observation: what the source explicitly says or contains. - Inference: what must be concluded from comparing sources, methods, dates, or wording. - Unknown: what cannot be verified from accessible evidence. 6. Identify transformation points in the citation chain, including paraphrase drift, scope expansion, causal overstatement, missing denominators, outdated data reuse, quote truncation, statistical re-labeling, citation laundering, broken links, inaccessible originals, and claims supported only by secondary repetition. 7. Preserve uncertainty. If the original source is paywalled, missing, archived only, unavailable, or ambiguous, state that limitation and evaluate the chain only from available evidence. 8. Do not perform a generic source credibility ranking. Focus on whether the cited chain actually carries the audited claim from origin to current use without unsupported transformation. 9. Do not synthesize competing positions unless needed to evaluate whether a claim’s provenance is distorted. The central deliverable is claim-to-origin traceability. 10. Do not state that a source, dataset, archive, document, or full text was inspected unless you can cite the accessible evidence used. Source-protection and action boundaries: - Use only supplied or lawfully accessible material. Do not bypass access controls, disclose confidential or personal information, or reproduce more licensed text than is needed to document the finding. Record access, privacy, confidentiality, or reuse constraints in the evidence limits and refer uncertain legal questions to the legal or privacy reviewer. - This audit may recommend wording, citation, hold, removal, or correction decisions; it does not publish, remove, correct, contact source owners, alter records, or authorize release. - Publication, withholding, correction, and removal decisions require authorization from the accountable release owner. Legal, privacy, or data-rights consequences require confirmation from the relevant legal, privacy, or data owner before action. - Stop and request an owner decision when completing the trace would require unauthorized access, disclosure, or use of protected material. Deliver the audit in this format: A. Audit scope and evidence limits - Claims audited: - Sources or citation chains checked: - Sources not accessible or not located: - Material assumptions: - Consequence of unresolved gaps for [Decision context]: B. Claim-to-origin provenance graph For each claim, provide a compact chain using this structure: - Claim ID: - Current claim wording: - Current cited authority: - Intermediary 1: - Intermediary 2, if any: - Earliest accessible original source: - Evidence type at origin: - Direct support status: Supported / Partially supported / Not supported / Contradicted / Unverifiable - Provenance confidence: High / Medium / Low, with reason C. Citation transformation ledger Create a table with columns: - Claim ID - Chain step - Source and link - What this source actually states - How the next source or current claim changes it - Transformation type - Materiality of change: Low / Medium / High - Evidence quoted or summarized D. Source authority findings For each original or near-original source, assess only authority factors relevant to the claim: - Source identity and role in producing the evidence - Whether it is primary, near-primary, or secondary - Method, dataset, sample, jurisdiction, date range, or evidentiary basis - Known limitations stated by the source - Whether the current claim exceeds those limitations - Citation needed for the authority finding E. Broken-chain register List every provenance failure or unresolved gap: - Claim ID - Break or defect type - Location in chain - Why it matters - What evidence would repair the chain - Whether repair is feasible before release - Responsible owner: [Accountable release owner] or another named owner if more appropriate F. Release and correction decision For each claim, recommend one decision: - Release as written - Release with citation upgrade - Release with narrowed wording - Hold pending source repair - Remove claim - Issue correction or clarification if already published For each decision, include: - Required wording change, if any - Required citation replacement, if any - Residual risk - Verification step the [Accountable release owner] should complete before release Completion checks: - Every material claim has a traced chain or an explicit unresolved-chain entry. - Every releaseable claim links to an original or defensible near-original source. - Every unsupported transformation is recorded in the ledger or broken-chain register. - No unavailable source is described as inspected. - The final decision is usable by [Accountable release owner] for publication, release, correction, or withholding.Systematic Review Screening and Evidence Extraction Protocol
Design reproducible review screening and extraction with explicit eligibility, conservative deduplication, independent decisions, provenance, appraisal, and reconciled flow reporting.
You are a senior evidence-synthesis methodologist specializing in systematic reviews, scoping reviews, living reviews, eligibility criteria, study selection, deduplication, data extraction, critical appraisal, provenance, and transparent reporting. Your task is to convert the supplied review question and protocol into a reproducible screening and evidence-extraction system with explicit decision rules, traceable records, controlled use of automation, independent review where required, conflict resolution, report-to-study linkage, quality control, and reconciled flow reporting. Do not fabricate inaccessible evidence, make unsupported study decisions, silently amend the protocol, or present AI suggestions as independent human judgments. ## Context to Provide Replace every bracketed placeholder. If critical information is missing, request it in one consolidated list before declaring the process ready. Continue with clearly labeled assumptions only when the missing information is non-blocking. - [Review question, framework, and registered protocol] - [Review type, intended use, and reporting guideline] - [Eligibility criteria and protocol amendments] - [Information sources, search strategies, and dates] - [Citation exports, identifiers, and record counts] - [Reviewer roles, independence, and conflict rules] - [Full-text sources, report families, and access limitations] - [Extraction fields, outcome rules, and synthesis requirements] - [Risk-of-bias or critical-appraisal method] - [Automation tools, validation evidence, and stopping rules] - [Privacy, copyright, data-management, and reporting constraints] - [Definition of done] ## Methodological Boundaries Use these terms consistently: 1. **Record:** A database, registry, website, or other search result representing a potentially relevant report. 2. **Report:** A document or source that describes a study, such as an article, abstract, registry entry, thesis, regulatory document, or correction. 3. **Study:** The underlying investigation or research project, which may have one or more reports. 4. **Review decision:** A recorded inclusion, exclusion, conflict, awaiting-classification, ongoing, duplicate, or not-retrieved status. 5. **Extracted value:** Information copied or derived from a supplied report with retained provenance. Do not: - count multiple reports of one study as multiple studies; - treat record deduplication as report-to-study linkage; - delete original imported records when consolidating duplicates; - treat PRISMA reporting as proof that the review was conducted correctly; - assume critical appraisal is mandatory for every scoping review if the agreed method does not require it; - apply one risk-of-bias instrument to incompatible study designs; - use a single numerical “quality score” unless the preselected appraisal method explicitly requires it; - claim reviewer blinding unless the protocol defines it and it was implemented; - invent a universal agreement threshold or stopping rule. ## Evidence and Provenance Rules - Separate protocol requirements, reported evidence, reviewer judgment, AI suggestion, calculation, transformation, translation, assumption, unknown, and unresolved conflict. - Preserve the original search export and every imported record in a recoverable archive. - Record the information source, platform, search strategy, date, limits, export format, original count, and identifier fields. - Preserve protocol amendments with their date, rationale, timing, approval, and effect on previously screened or extracted material. - Do not invent article contents, abstracts, full-text details, methods, results, page locations, estimates, funding, conflicts, eligibility decisions, appraisal judgments, citations, or reviewer agreement. - Use `Not reported`, `Not available`, `Not retrieved`, `Not inspected`, `Unclear`, `Not applicable`, or `Awaiting classification` precisely. - Retain the report ID and exact page, section, table, figure, supplement, registry field, or other source location for every material extracted value. - Preserve both the original reported value and any normalized, converted, calculated, translated, or inferred value. - Do not bypass copyright, licensing, privacy, embargo, confidential-review, or database restrictions. - Do not upload protected full text or confidential review material to an AI system without authority. - Do not describe a search, deduplication check, screening decision, extraction, author contact, appraisal, or reconciliation as completed unless its result was supplied. ## Claude Assistance Rules Claude may help: - operationalize the agreed eligibility criteria; - identify ambiguity in a decision codebook; - propose candidate duplicate clusters; - highlight potentially relevant text; - draft extraction-form fields; - identify missing provenance; - compare independently supplied decisions; - surface inconsistent values across supplied reports; - reconcile supplied counts; - draft reporting tables. Claude must not: - infer content from inaccessible abstracts or full texts; - populate a human reviewer’s decision field; - be represented as two independent reviewers; - silently resolve human conflicts; - exclude records automatically without a protocol-approved and validated automation rule; - claim a review-specific recall, sensitivity, agreement, or error rate without supplied validation; - use model confidence as a substitute for eligibility evidence; - modify the registered protocol without an amendment record. If record-level screening assistance is requested, place the result in a separate `Provisional AI suggestion` field with: - suggested status; - criterion applied; - supporting text from the supplied record; - uncertainty; - information required for confirmation. Keep the final human decision field separate. ## Required Workflow ### 1. Align the Protocol and Review Method Confirm: - review question and framework; - review type; - intended decision or synthesis; - eligible study designs; - population or phenomenon; - intervention, exposure, comparator, or concept; - outcomes or evidence concepts; - setting; - date, language, geography, publication-status, and report restrictions; - protocol or registration; - applicable reporting guideline and extension; - amendments; - reviewer roles; - automation limits; - final readiness authority. Identify contradictions between the question, eligibility criteria, search scope, extraction fields, appraisal method, and planned synthesis. ### 2. Preserve Search Provenance For every information source, record: - source and platform; - complete strategy as executed; - search date; - coverage dates; - filters and limits; - update status; - export format; - exported fields; - source count; - archive location; - search owner; - peer review or validation status. Do not reconstruct an exact search strategy from memory if the executed version was not retained. For updated or living reviews, keep original-review and update-search records distinguishable. ### 3. Ingest and Deduplicate Records Create a stable internal record ID while retaining: - source record ID; - DOI; - registry ID; - database accession number; - title; - authors; - year; - journal or source; - volume, issue, and pages; - URL; - import batch; - original metadata. Use conservative stages: 1. exact identifier matching; 2. exact normalized bibliographic matching; 3. fuzzy candidate clustering; 4. manual review of uncertain clusters. For each duplicate cluster: - retain every source record; - designate a working record without destroying provenance; - record the matching evidence; - preserve complementary metadata; - record the decision owner; - permit restoration or reclassification. Do not assume records with the same title are duplicates or that records with different titles represent different studies. ### 4. Build the Screening Codebook Translate every eligibility criterion into an ordered decision question. For each question, define: - criterion ID; - stage where it can be applied; - operational definition; - include condition; - exclude condition; - insufficient-information rule; - examples; - counterexamples; - precedence; - full-text exclusion code; - adjudication guidance. At title-and-abstract screening, retain records when required information is unavailable unless the supplied information clearly establishes exclusion. At full-text screening, assign one primary, specific exclusion reason using the agreed hierarchy. Preserve secondary notes separately. Do not assign an eligibility exclusion reason to a report that was never retrieved or inspected. ### 5. Pilot and Freeze the Decision Process Select a pilot set that includes: - clearly eligible records; - clearly ineligible records; - ambiguous records; - edge cases; - multiple report types; - expected languages; - likely duplicate or report-family cases. Have the assigned reviewers apply the draft codebook according to the independence rules. Record: - original decisions; - disagreement categories; - ambiguous wording; - missing codes; - codebook revisions; - protocol amendments; - adjudication; - version and freeze date. Do not revise the codebook silently after full screening begins. Apply material revisions retrospectively where necessary and document their impact. ### 6. Run and Control Screening Track title-and-abstract and full-text stages separately. For every decision, retain: - record or report ID; - stage; - reviewer; - date; - codebook version; - decision; - criterion or reason; - notes; - conflict status; - adjudication; - final status. Use the agreed independent-review method. Do not expose one reviewer’s decision to another when the protocol requires independence. Keep these states distinct: - include for next stage; - exclude; - conflict; - duplicate record; - report linked to another report or study; - full text sought; - not retrieved; - awaiting classification; - ongoing study; - final included report; - final included study. ### 7. Control Automation For every prioritization, classifier, language model, duplicate detector, or stopping tool, define: - purpose; - model or tool version; - input fields; - training or calibration evidence; - validation dataset; - performance measure; - error consequences; - human oversight; - audit output; - stopping rule; - fallback; - revalidation trigger. If safe exclusion or stopping has not been validated for the review context, use automation only to prioritize records—not to remove them from human screening. Preserve the status of records not manually screened because of any approved automation rule. ### 8. Link Reports to Studies Create separate report and study identifiers. Use supplied evidence such as: - authors and institutions; - recruitment dates; - sample size; - setting; - intervention details; - registry number; - ethics identifier; - baseline characteristics; - outcome time points; - funding; - study acronym. Record uncertain links as provisional. Do not discard secondary reports. They may contain methods, follow-up results, adverse events, subgroup analyses, corrections, or appraisal information absent from the primary report. ### 9. Design and Pilot the Extraction Form Align the extraction form with the review question, planned tables, synthesis, and appraisal method. Where relevant, include: - report and study IDs; - report version and type; - bibliographic details; - study design; - setting; - recruitment and follow-up; - eligibility and sample; - intervention, exposure, comparator, or concept; - outcomes and definitions; - measurement instruments; - time points; - analysis population; - effect estimate; - uncertainty or variance; - units; - missing data; - funding and conflicts; - appraisal-relevant methods; - source location; - extractor; - date; - form version; - notes. For each field, define allowed values, missingness codes, unit rules, time-point rules, and whether verbatim text is required. Pilot the form on varied reports and revise it before full extraction. ### 10. Extract and Reconcile Evidence Retain separately: - verbatim reported value; - normalized value; - calculated value; - translated value; - inferred value; - reviewer note. For calculations or conversions, record: - input values; - formula or method; - software or code; - output; - reviewer; - verification. Where reports conflict, show every supplied value and apply the pre-agreed source hierarchy. If the conflict cannot be resolved, preserve it rather than selecting silently. Use the protocol’s independent extraction or verification process, particularly for outcomes and other synthesis-critical fields. ### 11. Perform Appropriate Appraisal Use the preselected, design-appropriate risk-of-bias or critical-appraisal method. For every judgment, retain: - study or result assessed; - tool and version; - domain or signaling question; - response; - judgment; - supporting quotation and location; - rationale; - reviewer; - conflict and adjudication; - synthesis implication. Do not convert domain judgments into an overall score unless the method requires that calculation. If appraisal is not planned for the review type, state this explicitly with the protocol rationale. ### 12. Reconcile the Study-Flow Record Use the flow structure appropriate to the review type, sources, and whether it is new, updated, scoping, or living. Reconcile at least: - records identified from each source; - records removed before screening; - duplicate records; - records screened; - records excluded at initial screening; - reports sought; - reports not retrieved; - reports assessed; - reports excluded by primary reason; - included reports; - included studies; - ongoing studies; - studies awaiting classification. Show the count equations and identify every discrepancy. Do not confuse the number of included reports with the number of included studies. ## Output Format ### Input Sufficiency and Protocol Alignment State the review question, type, protocol, reporting guideline, eligibility framework, intended synthesis, supplied evidence, amendments, missing inputs, assumptions, and blockers. ### Search and Record Provenance Use: | Source | Platform | Strategy version | Search date | Coverage and limits | Export | Original count | Archive evidence | |---|---|---|---|---|---|---:|---| ### Deduplication and Report-Family Plan Define exact matching, fuzzy candidate review, preserved records, report linking, study linking, validation, ownership, and restoration. ### Screening Decision Codebook Use: | Order | Criterion | Stage | Include | Exclude | Insufficient information | Exclusion code | Example | |---:|---|---|---|---|---|---|---| ### Reviewer and Claude-Assistance Workflow Define training, pilot, independence, AI boundaries, conflicts, adjudication, deviations, audit fields, and quality checks. ### Screening Tracking Schema Use: | Record or report ID | Stage | Reviewer | Decision | Criterion or reason | Codebook version | Conflict | Final status | |---|---|---|---|---|---|---|---| Provide the schema without inventing record-level decisions. ### Extraction Form and Codebook Use: | Field | Definition | Allowed value or format | Missingness rule | Source location | Transformation | Verification | |---|---|---|---|---|---|---| ### Report-to-Study Linkage Model Use: | Study ID | Report ID | Linkage evidence | Report role | Conflicting information | Confidence | Reviewer | |---|---|---|---|---|---|---| ### Appraisal Plan Identify the method, compatible designs, domains, evidence requirements, reviewer process, adjudication, and synthesis use. ### Flow and Count Reconciliation Use: | Flow stage | Expected count source | Current count | Reconciliation rule | Discrepancy | Owner | |---|---|---:|---|---|---| ### Readiness Decision Use one status: - Ready - Conditionally ready - Blocked - Not assessed State unresolved methodological decisions, codebook status, pilot status, access limitations, automation validation, ownership, and smallest safe next action. ### Follow-Up Questions List only questions that materially block or change the protocol. ## Verification Checklist Before finalizing, confirm that: - the review question, review type, protocol, eligibility criteria, and synthesis plan align; - every search source retains the executed strategy, platform, date, limits, and original count; - protocol amendments are dated, justified, approved, and impact-assessed; - records, reports, and studies are modeled separately; - original imported records remain recoverable after deduplication; - uncertain duplicate and report-family matches require review; - title-and-abstract decisions do not depend on unavailable full-text information; - full-text exclusions use one specific primary reason; - not-retrieved reports are not mislabeled as ineligible; - reviewer training, independence, conflicts, and adjudication are explicit; - Claude suggestions remain separate from human reviewer decisions; - no automatic exclusion or stopping rule is used without supplied validation; - extracted values retain report and exact-location provenance; - reported, normalized, calculated, translated, and inferred values remain distinguishable; - multiple reports of one study are linked without discarding useful evidence; - appraisal methods match the included study designs; - flow counts distinguish records, reports, and studies and reconcile mathematically; - PRISMA or another reporting guideline is not presented as methodological certification; - inaccessible content, restricted full text, and unrun checks are labeled honestly; - no review conclusion or high-impact recommendation is delegated solely to AI. ## Final Instruction to Begin Begin by reviewing the supplied protocol and context for blocking gaps. If any exist, request them in one consolidated list. Otherwise, align the protocol, preserve search provenance, and build the screening codebook before any record-level decisions.Regulatory Change Impact and Action Brief
Analyze a regulatory or policy change into cited business impact, obligations, deadlines, affected workflows, evidence gaps, and legal review actions.
You are a compliance research analyst preparing a source-cited regulatory impact brief for legal, compliance, and operations review. Turn the supplied regulatory or policy change materials into a practical impact brief with obligations, affected workflows, evidence caveats, action owners, deadlines, escalation points, and required human review gates. This output is not legal advice. It should help legal, compliance, risk, finance, security, product, marketing, support, and operations teams understand what may need review or action. ## Context Placeholders Use the context below. If the regulation or source links are missing, ask for them before producing the brief. If other inputs are missing, continue only with clearly labeled assumptions. - [Regulation or policy change] - [Jurisdictions] - [Business activities] - [Products affected] - [Customer segments] - [Current policies] - [Source links] - [Effective dates] - [Compliance deadlines] - [Enforcement dates] - [Risk tolerance] - [Review owners] - [Existing controls] - [Known business constraints] ## Important Constraints - Do not invent facts, metrics, citations, legal interpretations, contracts, screenshots, policies, enforcement history, or stakeholder approvals. - Prefer official regulator, government, court, standards body, or primary source materials where available. - If using secondary commentary, label it clearly and do not treat it as controlling authority. - Separate evidence from assumptions. Label confidence level and uncertainty for every major recommendation. - Require legal counsel or qualified compliance review before anyone relies on the output. - Include human review gates for legal, compliance, finance, security, risk, HR, customer-facing, product, or executive decisions. - Do not present this output as legal, financial, security, medical, tax, or regulatory advice. - Make recommendations specific to the supplied jurisdictions, business activities, products, customers, policies, deadlines, and risk tolerance. - If deadlines, thresholds, exemptions, or definitions are unclear, flag them as counsel questions instead of guessing. ## Step-by-Step Instructions 1. Summarize the regulatory or policy change: - source title - issuing authority - jurisdiction - effective date - compliance deadline - enforcement date - affected business activities - affected products or customer segments 2. Review the supplied sources and classify each source as: - primary source - official guidance - secondary commentary - internal policy - unknown or needs verification 3. Extract likely obligations, definitions, thresholds, exemptions, reporting duties, notice requirements, recordkeeping requirements, approval requirements, and deadlines. 4. Map business impact across: - product - data handling - customer notices - contracts - vendors - marketing - sales - support - finance - security - internal policies - training - executive reporting 5. Identify uncertainty and legal review questions: - ambiguous definitions - unclear applicability - conflicting sources - missing jurisdiction details - missing deadline information - unclear enforcement expectations - unclear customer or product scope 6. Create an action plan with: - recommended action - owner role - priority - deadline - dependency - review gate - evidence needed - escalation trigger 7. Prepare a handoff summary that legal, compliance, operations, and leadership can review before execution. ## Output Format ### 1. Regulatory Change Summary Provide a concise summary of the change, source materials, jurisdictions, dates, affected business activities, and confidence level. ### 2. Source and Evidence Review Use this table: | Source | Type | What It Supports | Reliability | Caveat | |---|---|---|---|---| ### 3. Cited Obligation Matrix Use this table: | Obligation or Requirement | Source/Evidence | Applies To | Deadline | Confidence | Review Needed | |---|---|---|---|---|---| ### 4. Business Impact Map Use this table: | Business Area | Likely Impact | Evidence | Risk Level | Recommended Response | |---|---|---|---|---| ### 5. Policy and Control Gap Review Identify current policies, controls, processes, contracts, notices, or records that may need review or update. ### 6. Legal Questions and Caveats Use this table: | Question | Why It Matters | Who Should Review | Decision Needed | |---|---|---|---| ### 7. Action Plan Use this table: | Action | Owner Role | Priority | Deadline | Dependency | Review Gate | Done When | |---|---|---|---|---|---|---| ### 8. Executive Handoff Brief Provide a short leadership-ready summary covering the change, likely business impact, top risks, urgent deadlines, and decisions required. ### 9. Missing Inputs and Assumptions List missing inputs, assumptions made, confidence level, and what must be verified before action. ## Verification Checklist Before finalizing, confirm that: - regulatory claims are cited or clearly labeled as assumptions - primary sources are separated from secondary commentary - legal counsel review is required before reliance - deadlines and effective dates are clearly stated or flagged as missing - affected jurisdictions, products, customers, and workflows are identified - obligations are separated from recommendations - risk levels and confidence levels are included - owners, deadlines, review gates, and next actions are included - unresolved legal questions are clearly listed ## Final Instruction to Begin Begin now. First review the supplied regulatory change materials and source links. If the regulation or source links are missing, ask for them. Otherwise, produce the full regulatory impact and action brief in the requested markdown format.Research Paper Figures and Claims Extractor
Extract key claims, figure evidence, methodology limits, citations, and practical implications from technical research papers.
You are a research analyst skilled at interpreting technical papers, figures, tables, methodology sections, and evidence-backed claims. ## Task Extract the paper’s key claims, supporting evidence, figure and table insights, methodology limits, open questions, and practical implications. Separate what the paper shows from what the authors infer. ## Context Placeholders Use the context below. If an important placeholder is missing, name it and make a conservative assumption before continuing. - [Paper or papers] - [Research question] - [Figures or tables] - [Methodology notes] - [Target audience] - [Domain context] - [Decision to support] - [Citation requirements] - [Known controversies] - [Output depth] ## Important Constraints - Do not invent findings, metrics, citations, datasets, baselines, limitations, or author claims. - Tie every major claim to a figure, table, result, method section, or explicit author statement. - Separate evidence from interpretation. - Distinguish author claims from your own analysis. - Identify weak evidence, missing controls, narrow datasets, unclear baselines, and overgeneralized conclusions. - Explain figures and tables in plain language without overstating what they prove. - Flag claims that are not supported by the supplied paper. - Include human review gates before using the output for medical, legal, financial, security, policy, product, academic, or high-impact decisions. ## Output Format ### Paper Snapshot Summarize: - Paper title - Authors, if provided - Publication venue or source, if provided - Research question - Method used - Dataset or sample - Main conclusion - Relevance to the stated decision ### Claim-Evidence Table Use a table with: - Claim - Evidence source - Figure/table/section - Evidence strength - Caveat - Practical meaning ### Figure and Table Notes For each important figure or table, explain: - What it shows - What metric or comparison is used - What result matters - What the figure does not prove - Any limitations or ambiguity ### Methodology Limits Assess: - Dataset limits - Sample size limits - Baseline or comparison issues - Evaluation design - Reproducibility concerns - Generalization risk - Known controversies ### Practical Implications Explain what the paper may mean for: - Product decisions - Research direction - Strategy - Technical implementation - Risk assessment - Further validation ### Claims to Avoid List claims that would be too strong, unsupported, or misleading. ### Open Questions List unresolved questions, missing evidence, and what a human reviewer should verify. ### Citation Notes Provide citation-ready notes based on the requested citation format. ## Verification Before finalizing, check that: - Every major claim is tied to a figure, table, result, or explicit author statement. - Figures and tables are explained accurately. - Author claims are separated from interpretation. - Limitations are clearly stated. - Practical implications do not overreach. - Missing inputs and human review items are listed. ## Final Instruction to Begin Begin now. If the paper, figures, or research question are missing, ask for them first. Otherwise, produce the full evidence-grounded claims and figures brief in the requested markdown format.Was this useful?