Research Publications Methodology About Contact
SIGI RESEARCH PROGRAMME

Research Publications

100 open-access research papers from The Scientific Institute for Generative Intelligence. Our publication programme investigates how AI systems select, rank, and cite information sources, providing original data, controlled experiments, and frameworks for the emerging discipline of Generative Engine Optimisation.

Category A — Controlled Experiments

SIGI-2026-001 A: Controlled Experiment Level 4

Sentiment Threshold Dynamics in Large Language Model Evaluation of Service Provider Ratings: A Controlled Single-Variable Experiment

SIGI-2026-002 A: Controlled Experiment Level 4

Replication Considerations and Methodological Validation of Rating-Sentiment Threshold Probes in Generative AI Systems

SIGI-2026-003 A: Controlled Experiment Level 4

The Price-Credibility U-Curve: How Service Pricing Magnitude Affects Large Language Model Sentiment Assessment

SIGI-2026-004 A: Controlled Experiment Level 4

Methodological Framework for Pricing-Sentiment Probe Design: Volatility Analysis and Threshold Stability

SIGI-2026-005 A: Controlled Experiment Level 4

The Award Count Paradox: Non-Linear Credibility Assessment of Claimed Design Awards by Generative AI

SIGI-2026-006 A: Controlled Experiment Level 4

Qualitative Response Analysis in Award-Count Credibility Probes: How LLMs Frame Award Claims Across Magnitude Ranges

SIGI-2026-007 A: Controlled Experiment Level 4

Client Portfolio Size and AI Credibility Assessment: An Oscillating Signal with No Positive Ceiling

SIGI-2026-008 A: Controlled Experiment Level 4

Comparative Volatility Analysis: Awards versus Client Count as LLM Credibility Signals

SIGI-2026-009 A: Controlled Experiment Level 4

Review Volume Versus Rating Magnitude: How Large Language Models Resolve Conflicting Social Proof Signals

SIGI-2026-010 A: Controlled Experiment Level 4

The Statistical Reasoning of AI Evaluators: Bayesian Parallels in LLM Social Proof Assessment

SIGI-2026-011 A: Controlled Experiment Level 4

Domain Age as a Non-Signal: A Controlled Null Result in LLM Service Provider Evaluation

SIGI-2026-012 A: Controlled Experiment Level 4

The Irrelevance of Temporal Provenance: Implications of the Domain-Age Null Result for Generative Engine Optimization Theory

SIGI-2026-013 A: Controlled Experiment Level 4

Entity Density and AI-Assessed Citability: A Controlled Probe of Content Specificity Thresholds

SIGI-2026-014 A: Controlled Experiment Level 4

Content Specificity as a Prerequisite for AI Citation: Qualitative Citability Assessments Across Entity Density Levels

SIGI-2026-015 A: Controlled Experiment Level 4

List Magnitude and Entity Anchoring: How Request Size Affects Which Service Providers LLMs Recommend

SIGI-2026-016 A: Controlled Experiment Level 4

Computational Scaling in LLM List Generation: Resource Allocation Evidence from Magnitude Probes

SIGI-2026-017 A: Controlled Experiment Level 4

Position Primacy Bias in LLM Evaluation of Pre-Supplied Rankings: The First-Position Advantage

SIGI-2026-018 A: Controlled Experiment Level 4

Geographic Entity Mismatch Rejection: A Controlled Test of Contextual Consistency in LLM Ranking Assessment

SIGI-2026-019 A: Controlled Experiment Level 4

The Content Depth Sweet Spot: Source Length Effects on LLM Credibility Assessment with Negative Inversion at High Volume

SIGI-2026-020 A: Controlled Experiment Level 4

Information Burial and the 5,000-Word Inversion: Why More Content Can Reduce AI Citation Probability

Category B — Trust Signal Analysis

SIGI-2026-021 B: Trust Signal Analysis Level 1-2

A Taxonomy of 77 Trust Signals in AI Citation Decisions: An Introspective Framework from a Single Large Language Model

SIGI-2026-022 B: Trust Signal Analysis Level 1-2

Content Structure Signals in AI Citation: Question Headings, Direct Answers, and Self-Contained Paragraphs

SIGI-2026-023 B: Trust Signal Analysis Level 1-2

Technical Infrastructure Signals and AI Citation: From JavaScript Dependency to Robots.txt Configuration

SIGI-2026-024 B: Trust Signal Analysis Level 1-2

Authority and Provenance Signals: Named Authorship, Methodology Sections, and Source Citations in AI Trust Evaluation

SIGI-2026-025 B: Trust Signal Analysis Level 1-2

Commercial Independence as a Trust Signal: Paid Placement Declarations and Revenue Model Transparency

SIGI-2026-026 B: Trust Signal Analysis Level 1-2

Schema Markup and AI Citation: A Signal-by-Signal Analysis of 11 Structured Data Types

SIGI-2026-027 B: Trust Signal Analysis Level 1-2

Social Proof Signals in AI Evaluation: From Verified Reviews to Multi-Platform Presence

SIGI-2026-028 B: Trust Signal Analysis Level 1-2

Negative Trust Signals: Eight Patterns That Actively Reduce AI Citation Probability

SIGI-2026-029 B: Trust Signal Analysis Level 1-2

Inference-Time Versus Training-Time Signal Processing: A Dual-Layer Model of LLM Trust Evaluation

SIGI-2026-030 B: Trust Signal Analysis Level 1-2

The Minimum Viable Trust Stack: Identifying the Smallest Signal Set for Maximum AI Citation Impact

SIGI-2026-031 B: Trust Signal Analysis Level 1-2

Content Uniqueness and Information Gain: How Original Research Creates Forced Citation in AI Systems

SIGI-2026-032 B: Trust Signal Analysis Level 1-2

Structural Signals in AI Citation: Comparison Tables, Lists, and Heading Hierarchy as Extraction Facilitators

SIGI-2026-033 B: Trust Signal Analysis Level 1-2

Cross-Platform Entity Signals: sameAs Schema, Multi-Platform Presence, and Knowledge Graph Integration

SIGI-2026-034 B: Trust Signal Analysis Level 1-2

The Epistemological Limitations of LLM Introspective Trust Signal Research: A Critical Self-Assessment

SIGI-2026-035 B: Trust Signal Analysis Level 1-2

From Introspection to Experimentation: A Priority-Ranked Behavioral Validation Agenda for 77 Trust Signals

Category C — Competitive Intelligence

SIGI-2026-036 C: Competitive Intelligence Level 2

A 60-Variable Comparative Dataset for Studying AI Citation Behavior Across Service Industry Websites

SIGI-2026-037 C: Competitive Intelligence Level 3

Structural Correlates of AI Citation: An Observational Analysis of 22 On-Page Metrics

SIGI-2026-038 C: Competitive Intelligence Level 2-3

Schema Markup and AI Citation: Observational Evidence Against a Simple Positive Relationship

SIGI-2026-039 C: Competitive Intelligence Level 2-3

H2 Heading Taxonomy and AI Citation: A Classification Study of 232 Headings Across 21 Websites

SIGI-2026-040 C: Competitive Intelligence Level 2-3

Lexical Signatures of AI-Cited Versus Non-Cited Service Websites: A 306-Word Corpus Analysis

SIGI-2026-041 C: Competitive Intelligence Level 2

The GEO Vocabulary Paradox: Why Meta-Language About AI Citations Correlates with Their Absence

SIGI-2026-042 C: Competitive Intelligence Level 2-3

First-Paragraph Framing and AI Citation: An Observational Study of Opening Content Strategies

SIGI-2026-043 C: Competitive Intelligence Level 2

Content Volume Without External Validation: An Observational Study of High-Volume Zero-Citation Websites

SIGI-2026-044 C: Competitive Intelligence Level 2-3

Pricing Transparency Across Service Verticals: A Comparative Content Analysis

SIGI-2026-045 C: Competitive Intelligence Level 2-3

External Link Ecosystems and AI Citation: An Observational Analysis of Outbound Link Patterns

SIGI-2026-046 C: Competitive Intelligence Level 2

Image Count Disparity and AI Citation: Deconstructing the 30.7x Ratio Observation

SIGI-2026-047 C: Competitive Intelligence Level 2-3

Citation Score Distribution Across Four Service Verticals: Patterns of AI Visibility in Specialized Markets

SIGI-2026-048 C: Competitive Intelligence Level 2-3

CTA Density and Commercial Language in AI-Cited Versus Non-Cited Websites

SIGI-2026-049 C: Competitive Intelligence Level 2-3

Named Entity Density in Service Website Content: An Observational Comparison of Cited and Uncited Sites

SIGI-2026-050 C: Competitive Intelligence Level 3

The Confound Problem in Observational GEO Research: Why 21-Site Comparisons Cannot Support Causal Claims

Category D — AI Platform Behaviour

SIGI-2026-051 D: AI Platform Behaviour Level 2-3

Training-Data Commercial Knowledge in Large Language Models: What AI Systems Know About Paid Placement Practices

SIGI-2026-052 D: AI Platform Behaviour Level 2-3

The Dual Bias Mechanism: How Training-Time and Inference-Time Commercial Knowledge Combine in AI Citation Decisions

SIGI-2026-053 D: AI Platform Behaviour Level 2

A Five-Tier Trust Hierarchy for AI Citation Sources: From Independent Journalism to Promotional Content

SIGI-2026-054 D: AI Platform Behaviour Level 2-3

The Editorial Vacuum: Zero Independent Sources in a Competitive Service Query Space

SIGI-2026-055 D: AI Platform Behaviour Level 2-3

Query Framing Effects on AI Source Selection: How Single-Word Changes Alter Source Pools

SIGI-2026-056 D: AI Platform Behaviour Level 2-3

Search Position Versus Citation Priority: Evidence for a Separate Re-Ranking Pass in AI Answer Generation

SIGI-2026-057 D: AI Platform Behaviour Level 2-3

Content Extraction by Source Type: What AI Systems Extract from Directories, Listicles, and Agency Homepages

SIGI-2026-058 D: AI Platform Behaviour Level 2-3

The Memory-Citation Feedback Loop: How Conversational Context Creates Per-User Citation Advantages in AI Systems

SIGI-2026-059 D: AI Platform Behaviour Level 2-3

Freshness Versus Domain Authority: Observational Evidence of Temporal Override in AI Search Results

SIGI-2026-060 D: AI Platform Behaviour Level 2-3

Entity Density in Search Snippets: How Meta-Description Content Affects AI Extraction Utility

SIGI-2026-061 D: AI Platform Behaviour Level 2-3

Platform-Specific Citation Dominance: Observational Evidence of Directory Market Share in AI Recommendations

SIGI-2026-062 D: AI Platform Behaviour Level 2-3

The Self-Ranking Circular Citation Economy: How Service Providers Create Self-Referencing AI Recommendation Loops

SIGI-2026-063 D: AI Platform Behaviour Level 2-3

The New Publication Advantage: How Absence of Training-Data Bias Creates a Trust Signal Opportunity

SIGI-2026-064 D: AI Platform Behaviour Level 2

Trust Signal Taxonomy for AI Citation: Signals That Increase, Decrease, and Have Neutral Effects on Citation Probability

SIGI-2026-065 D: AI Platform Behaviour Level 2-3

De-Linking in AI Citation: How Large Language Models Strip URLs and Reconstruct Attribution

Category E — Methodology & Framework

SIGI-2026-066 E: Methodology Level 4+

The Logic-First Research Methodology: An Evidentiary Standard for Generative Engine Optimization Claims

SIGI-2026-067 E: Methodology Level 4+

The Seven Logic Gates for GEO Research: A Framework for Validating Claims About AI Citation Behavior

SIGI-2026-068 E: Methodology Level 4+

The Evidence Hierarchy for Generative Engine Optimization: Mapping Research Methods to Confidence Levels

SIGI-2026-069 E: Methodology Level 4+

Single-Variable Isolation in AI Behavior Research: The Probe Experiment Design Template

SIGI-2026-070 E: Methodology Level 4+

The Confidence Statement Template: Standardizing Uncertainty Communication in GEO Research

SIGI-2026-071 E: Methodology Level 4+

The Claim Audit Checklist: A Pre-Publication Quality Gate for GEO Research

SIGI-2026-072 E: Methodology Level 4+

The Signal Access Matrix: Determining Which Factors LLMs Can Actually Evaluate at Inference Time

SIGI-2026-073 E: Methodology Level 4+

Necessary, Sufficient, and Contributory: Applying the INUS Framework to GEO Factor Analysis

SIGI-2026-074 E: Methodology Level 4

Sentiment Analysis as a Measurement Instrument for AI Behavior Probes: Validity and Limitations

SIGI-2026-075 E: Methodology Level 4+

The 6-Layer Pipeline Test Matrix: A Comprehensive Research Design for Studying AI Citation Behavior

SIGI-2026-076 E: Methodology Level 4+

The Confound Matrix: A Practical Tool for Identifying Uncontrolled Variables in GEO Research

SIGI-2026-077 E: Methodology Level 4

Reclassifying GEO Findings: Applying the 7-Gate Framework to Separate Validated Findings from Hypotheses

SIGI-2026-078 E: Methodology Level 4+

Cross-Model Replication Requirements for GEO Research: Why Single-Model Findings Are Preliminary

SIGI-2026-079 E: Methodology Level 4+

Red Flags in GEO Research: Common Analytical Errors and How to Detect Them

SIGI-2026-080 E: Methodology Level 4+

Designing Experiments to Disprove: The Falsification Imperative in Generative Engine Optimization Research

APPLIED RESEARCH

Apply This Research

Our findings inform practical GEO strategy. For applied implementation of these research insights, speak with the team at TDS GEO Agency.