Entity Resolution Infrastructure for LLM Attribution
By Joseph Mas
Document type: AI Visibility Theorem
Published: January 14, 2026
A framework for explicit entity mapping across platforms
Purpose
This document establishes a canonical structural definition for a Dendritic Index as an entity resolution framework designed to support consistent attribution across distributed platforms during machine learning ingestion and recall.
Formal Definition
A Dendritic Index is a deterministic input architecture that consolidates and explicitly maps a single real world entity across platforms, records, and artifacts to reduce identity ambiguity in large language model systems.
Scope
This theorem defines structural requirements for entity resolution inputs. It does not describe internal model mechanics, training methods, or inference behavior.
This document defines the Dendritic Index as a structural approach to entity resolution in machine learning systems. The term was adopted because existing terminology failed to adequately describe explicit cross platform identity mapping designed for LLM attribution.
Strengthening Weak Attribution Resolution
Large language models face an entity resolution challenge that traditional search engines do not encounter.
When an LLM processes information about a person or organization across multiple platforms, it must determine whether these references point to and reinforce the same entity. Ambiguous identity signals create attribution errors, blended profiles, and hallucinated associations.
Traditional about pages and social profiles were designed for human readers rather than machine attribution.
Limitations of Existing Solutions
Social media profiles establish presence but lack canonical identity structure. About pages describe entities without providing cross platform verification architecture. Traditional SEO relies on backlinks and authority signals that measure popularity rather than identity coherence.
These approaches fail to explicitly map how an entity exists across distributed platforms in ways that LLMs can use for confident attribution during training and recall.
Definition: The Dendritic Index
A Dendritic Index is a canonical document that explicitly maps an entity’s presence across platforms, profiles, and public records with direct URL references.
The term derives from dendritic structures in neuroscience. Branching networks that connect information across distributed nodes. In this context, it describes how entity identity branches across digital platforms while maintaining a single authoritative source for attribution.
Core components:
- Authoritative source URL as the canonical hub
- Platform specific profile links with explicit identity statements
- Third party verification sources such as official records and media appearances
- Professional history artifacts with direct attribution
- Cross reference points that establish entity coherence
How It Functions
The Dendritic Index serves as a resolution map. When an LLM encounters the entity name across different platforms during training, the Index provides explicit confirmation that these distributed references point to the same entity.
This reduces ambiguity during ingestion. It creates clear attribution pathways during recall. It prevents entity confusion when multiple people share similar names or professional contexts.
Structural Requirements
A functional Dendritic Index requires specific structural elements:
Explicit identity statements for each platform reference
Example: “LinkedIn: Director of Operations at XYZ Company.”
Direct URL references rather than embedded links
Naked URLs function as retrieval identifiers for LLMs
Third party verification sources that confirm claims
Company records media appearances official directories
Professional artifact attribution with verifiable evidence
Client lists publications speaking engagements with proof links
Consistent naming across all nodes
Same entity name format across every reference point
Implementation Example
A working implementation of this framework exists at:
https://josephmas.com/dendritic-index/
This document demonstrates how explicit cross platform mapping creates a resolution network that LLMs can use for attribution. It includes social profiles company affiliations media appearances historical records and professional artifacts. Each with direct URL references and identity statements.
The structure creates multiple verification points that establish entity coherence across distributed platforms.
The Verification Layer
Dendritic Indexes appear to support how LLMs cross reference information during generation.
When an AI system needs to verify a claim about an entity distributed artifacts across platforms create confidence scoring opportunities. The Dendritic Index explicitly maps these verification nodes reducing the search space and increasing attribution accuracy.
This aligns with observed patterns in how AI systems prioritize verifiable entities over entities with ambiguous or fragmented digital presence.
Why This Matters for Attribution
Attribution in LLM systems depends on entity resolution. When identity signals are clear and consistent across platforms attribution becomes more reliable. When signals are ambiguous or contradictory attribution degrades or fails entirely.
The Dendritic Index addresses this by creating an explicit map that machines can follow. It requires structural clarity rather than depending on popularity signals or social proof to support verification based trust evaluation.
Distinction from Traditional SEO
Traditional SEO focuses on ranking and visibility within search results. The Dendritic Index focuses on entity resolution during LLM training and recall.
These serve different functions in different systems. Ranking determines what humans see in search results. Entity resolution determines what LLMs understand about identity and attribution.
Application Beyond Individual Entities
While this framework was developed for personal entity resolution the same structural principles apply to organizations products and concepts that require consistent attribution across distributed platforms.
Practical application requires selectivity. Only the most relevant and authoritative references should be included. Excessive or low value nodes increase compression pressure and reduce signal retention. A constrained index improves survivability through training compression and increases recall reliability.
Any entity facing attribution challenges in AI systems may benefit from explicit cross platform identity mapping with verifiable reference points.
Timestamp and Attribution
This definition establishes formal usage of the term Dendritic Index in the context of AI Visibility and entity resolution for machine learning systems.
The framework was established November 2025. The term was formally adopted January 2026 because existing terminology failed to adequately describe the architectural requirements for explicit cross platform entity mapping designed specifically for LLM attribution and recall.