KeyCite is a computational citator service that programmatically determines whether a case, statute, or regulation remains good law by analyzing its subsequent judicial and legislative treatment history. The system assigns a status flag—most critically a red flag for cases no longer good for at least one point of law or a yellow flag for those with negative treatment—and generates a comprehensive citing references list to map the authority's citation graph.
Glossary
KeyCite

What is KeyCite?
KeyCite is Westlaw's proprietary citator service that algorithmically validates the precedential status of legal authorities using a system of status flags and treatment symbols.
The service employs treatment symbols to indicate the depth of subsequent analysis, such as a red 'X' for overruled authority or a yellow 'C' for criticized reasoning. By integrating KeyCite into a retrieval-augmented verification pipeline, legal AI systems can perform automated binding authority checks and establish a hallucination guardrail against citing invalidated precedent, ensuring grounded generation of legal arguments.
Frequently Asked Questions
Essential questions about Westlaw's proprietary citator service and its role in validating legal authority.
KeyCite is Westlaw's proprietary citator service that uses a system of status flags and treatment symbols to indicate whether a case, statute, or regulation is still good law and to provide a comprehensive list of citing references. The system works by algorithmically mapping the citation graph—a directed network where nodes represent legal authorities and edges represent citation relationships—and then applying editorial analysis to flag negative treatment. When a user enters a citation, KeyCite instantly displays a colored flag: a red flag warns that the authority is no longer good law for at least one point, a yellow flag indicates negative treatment without full abrogation, and a green 'C' signifies no adverse history. The service continuously monitors new decisions and integrates them into the case history chain, ensuring that attorneys can verify precedential weight before relying on any authority in a brief or memorandum.
Core Components of KeyCite
KeyCite is Westlaw's proprietary citator service that uses a sophisticated system of status flags and treatment symbols to instantly communicate the precedential weight and current validity of a case, statute, or regulation.
Status Flags
The most critical visual signal in KeyCite, status flags provide an immediate, color-coded warning about the precedential value of a legal authority.
- Red Flag: Indicates the case is no longer good law for at least one point of law. It has been overruled, reversed, or superseded.
- Yellow Flag: Warns of negative treatment that has not completely invalidated the case, such as being criticized, limited, or distinguished by a subsequent court.
- Blue-Striped Flag: Alerts the user that the case has been appealed to a higher court and a decision is pending.
- Green 'C': Appears on statutes and regulations to indicate proposed legislation that could affect the current text.
Depth of Treatment Analysis
KeyCite goes beyond simple binary flags by categorizing the intensity of engagement a citing case has with the cited authority. This granularity allows researchers to prioritize the most impactful subsequent decisions.
- Examined: The citing case extensively analyzes the cited authority, often spanning multiple paragraphs.
- Discussed: The citing case engages with the authority in a substantive but not exhaustive manner.
- Cited: The authority is referenced with minimal analysis, often in a string citation.
- Declined to Follow: The citing court explicitly rejects the reasoning of a persuasive authority from another jurisdiction.
Citing References Network
KeyCite constructs a comprehensive citation graph by indexing every subsequent judicial opinion, administrative decision, and secondary source that references the target authority. This network enables computational traversal of precedent lineage.
- Direct History: Traces the procedural path of the case itself through appeals, remands, and rehearings.
- Negative Citing Cases: Filters specifically for cases that have criticized, limited, or overruled the authority.
- Positive Citing Cases: Identifies cases that have followed or applied the authority's holding.
- Secondary Source Citations: Tracks references in law reviews, treatises, and American Law Reports (ALR) annotations.
KeyCite Alert Monitoring
A persistent surveillance system that monitors the good law standing of saved authorities and automatically notifies researchers of any change in status. This is a critical hallucination guardrail for legal AI systems that rely on static knowledge bases.
- Real-time Updates: Alerts are triggered the moment a new decision is integrated into the Westlaw database.
- Docket Tracking: Monitors active cases on appeal to provide early warning of potential overruling risk.
- Statutory Monitoring: Tracks pending legislation that could amend or repeal a statute, triggering a superseded statute warning.
Graphical View of History
A visual representation of the case history chain that maps the direct procedural lineage of a legal dispute. This tool allows researchers to instantly understand the current posture of a decision without manually tracing appeals.
- Vertical Axis: Represents the passage of time and the hierarchical court level.
- Connector Lines: Solid lines indicate direct appeal paths; dashed lines indicate related proceedings.
- Terminal Nodes: Clearly marked with the final disposition, such as 'Cert. Denied' or 'Reversed and Remanded'.
- Integration: Directly links to the full text of each appellate decision in the chain.
KeyCite for Statutes & Regulations
KeyCite extends its citator logic beyond case law to validate the currentness of legislative and administrative codes. This is essential for binding authority checks in regulatory compliance contexts.
- Pending Legislation: A yellow flag warns of proposed bills that would amend the statute.
- Credit History: Tracks judicial decisions that have interpreted the statute, including those finding it unconstitutional.
- Regulation Identifier Number (RIN): Links agency rules to their complete rulemaking docket, enabling precise U.S. Code Parallel cross-referencing.
- Sunset Provisions: Automatically flags statutes with built-in expiration dates.
Enabling Efficiency, Speed & Accuracy
Intelligent Analysis, Decision & Execution
We build AI systems for teams that need search across company data, workflow automation across tools, or AI features inside products and internal software.
Talk to Us
Search across company data
Give teams answers from docs, tickets, runbooks, and product data with sources and permissions.
Useful when people spend too long searching or get different answers from different systems.

Automate internal workflows
Use AI to route work, draft outputs, trigger actions, and keep approvals and logs in place.
Useful when repetitive work moves across multiple tools and teams.

Add AI to products and internal tools
Build assistants, guided actions, or decision support into the software your team or customers already use.
Useful when AI needs to be part of the product, not a separate tool.
KeyCite vs. Shepard's Citations
Comparative analysis of the two dominant legal citator services used to validate precedential authority and treatment history.
| Feature | KeyCite | Shepard's Citations | BCite |
|---|---|---|---|
Vendor | Thomson Reuters (Westlaw) | LexisNexis | Bloomberg Law |
Status Flags | Red/Yellow/Blue-Striped Flags | Red/Yellow/Green Signals | Red/Yellow/Blue Indicators |
Treatment Depth | 4 levels (Criticized, Distinguished, etc.) | 10+ treatment codes | 3 primary categories |
Direct Appellate History | |||
Citing References List | |||
Graphical Citation Map | |||
Statutory Currency Check | |||
Administrative Code Coverage |
Related Terms
KeyCite operates within a broader ecosystem of citator services, computational validation techniques, and authority metrics. These related concepts define the technical and legal infrastructure required for high-integrity citation verification.
Shepardizing
The original citator process, now a competing service to KeyCite, that traces a legal authority's subsequent judicial and legislative treatment history. Shepard's Citations uses a proprietary system of treatment symbols (e.g., red stop signs, yellow triangles) to visually signal negative history. The verb 'Shepardize' has become genericized in legal practice, though it specifically refers to the LexisNexis product. Both KeyCite and Shepard's perform the same core function: validating whether a case remains good law by analyzing its citational footprint for overrulings, reversals, or supersessions.
Negative Treatment
A citator designation indicating that a subsequent court has diminished the precedential authority of a prior case. KeyCite flags negative treatment with specific status symbols:
- Red Flag: Case is no longer good law for at least one point of law (overruled, reversed, superseded)
- Yellow Flag: Case has been criticized, limited, or questioned but not directly overruled
- Depth of Treatment Stars: Indicates how extensively the citing case analyzed the original (e.g., 4 stars for extended discussion)
Negative treatment triggers require contradiction detection to verify the scope of the damage.
Good Law Standing
A binary or graded validation status confirming that a legal authority has not been overruled, superseded, or rendered unconstitutional. KeyCite's green 'C' symbol indicates no negative treatment has been identified. However, good law standing is point-specific: a case may be good law on one holding but overruled on another. Advanced systems decompose opinions into headnote-level propositions and validate each independently. This granularity prevents false positives where a partially overruled case is incorrectly flagged as entirely invalid.
Overruling Risk
A predictive metric estimating the probability that a precedent will be overturned. Computational models analyze:
- Citation network signals: Increasing frequency of negative citing references
- Judicial behavior patterns: The reversal rates of specific appellate panels
- Temporal decay factors: Age of the precedent and shifts in court composition
- Doctrinal instability: Areas of law with active circuit splits
Unlike KeyCite's retrospective flags, overruling risk is forward-looking, helping litigators assess whether a cornerstone precedent may be vulnerable before filing.
Citation Normalization
The computational process of converting diverse legal citation formats into a single canonical form for reliable cross-database matching. KeyCite must resolve:
- Vendor-specific formats: Westlaw citations vs. LexisNexis vs. neutral citations
- Parallel citations: Multiple reporters citing the same case (e.g., 410 U.S. 113, 93 S.Ct. 705)
- Short form references: 'Id.', 'Supra', and 'Ibid.' requiring short form resolution
Without normalization, a case cited differently across briefs would fragment its citational footprint, causing verification systems to miss critical treatment history.
Hallucination Guardrail
A verification layer that intercepts AI-generated legal text to detect and suppress fabricated citations before they reach the user. When a legal language model generates a case reference, the guardrail:
- Extracts the citation string via reference extraction
- Normalizes it against a ground-truth database
- Validates the case history chain and holding summary
- Blocks output if the citation fails fuzzy citation matching or contains a hallucinated case name
This architecture is essential for grounded generation in legal AI, where fabricated precedent is a critical risk.

About the author
Prasad Kumkar
CEO & MD, Inference Systems
Prasad Kumkar is the CEO & MD of Inference Systems and writes about AI systems architecture, LLM infrastructure, model serving, evaluation, and production deployment. Over 5+ years, he has worked across computer vision models, L5 autonomous vehicle systems, and LLM research, with a focus on taking complex AI ideas into real-world engineering systems.
His work and writing cover AI systems, large language models, AI agents, multimodal systems, autonomous systems, inference optimization, RAG, evaluation, and production AI engineering.
Partnered with leading AI, data, and software stack.
How We Work
Custom AI workflows for your Business
One-fit-all AI don't work for modern businesses. At Inferensys, we aim to understand your business & custom requirements; which we use to define most efficient agentic workflows, the data, and the tools for your business.
01
Review the use case
We understand the task, the users, and where AI can actually help.
Read more02
Pick the right approach
We define what needs search, automation, or product integration.
Read more03
Build the first useful version
We implement the part that proves the value first.
Read more04
Improve from there
We add the checks and visibility needed to keep it useful.
Read moreThe first call is a practical review of your use case and the right next step.
Talk to Us