Home About Research People Papers Contact

Computational
Meaning
Dynamics

We study how meaning moves: measuring, modeling, and exploiting semantic instability in AI systems to advance both scientific understanding and practical AI alignment.

Scroll

Recent Activities

Aug 2026
Advancing AI Governance in Healthcare
TwinPath AI is an AI governance architecture that ties multi-axis semantic evaluation to longitudinal care pathways, so AI support can be measured against actual patient-care trajectories rather than judged in isolation. Built on Computational Meaning Dynamics methods, it exposes misalignments in both AI outputs and care behavior retrospectively and as it emerges, giving clinical and quality teams a data-grounded way to monitor, audit, and govern AI and care together. Learn more about TwinPath AI.
Jun 2026
Visualizing Meaning In AI
Meridian Observatory is a live-computing research instrument that measures the geometry of meaning as a conversation unfolds. Built on Semantic Substrate Dynamics Theory, it treats each interaction as a trajectory through embedding space and computes how meaning moves, turn by turn, in real time. Its rare capability is generating clean, labeled, per-turn-embedded interaction data under controlled conditions, then using it to track how meaning holds, drifts, or collapses across AI-to-AI and human-AI exchanges. This makes semantic dynamics and manifolds observable and measurable as they emerge rather than after the damage is done; read about Meridian Observatory.
May 2026
Semantic Sensemaking Surveillance
SemOSIris was created as a research workbench that measures and visualizes semantic frame shifts across live global event-streams. It ingests real-time open-source news and events as a layer on an interactive world map and watches how events are situated and get contextually reframed over time. For each shift it computes the geometry of meaning directly: how events’ details move through latent embedding space, how their semantic neighborhood reshapes, and how the distribution and entropy of meaning shift across temporal windows, turning reframing into a labeled, geo-spatial drift trajectory. Follow the work.
Dec 2025
Measuring Semantic Drift in AI Knowledge
DARMA (Drift-Aware Retrieval Metrics and Alignment) is a research platform for detecting when changes in authoritative knowledge are likely to alter the behavior of AI systems that depend on it. In retrieval-augmented systems, policies, guidelines, program specifications, solicitations, and technical documents are revised constantly. Seeing that text changed is easy; knowing whether the meaning changed enough to affect answers, recommendations, or decisions is much harder. DARMA measures how document meaning moves across versions in embedding space, distinguishing substantive semantic change from surface rewording and identifying where consequential drift occurs. The goal is not simply to compare old and new documents, but to support risk-directed validation: signaling which knowledge changes are likely to matter, where their effects may propagate, and which parts of an AI system should be revalidated before unintended behavior is discovered downstream. Learn how DARMA works.
Sep 2025
Personalized Meaning Matters
AiVisor is an agentic advising system that treats personalization as an experimental variable rather than assuming it helps, measuring what it actually does to answer quality. Built on Computational Meaning Dynamics methods, it runs personalized and non-personalized configurations across lexical, semantic, and reasoning metrics under deliberately conservative conditions. The AiVisor research isolates a trade-off standard evaluation hides: personalization improves reasoning and grounding while standard semantic metrics penalize it for correctly deviating from a standard reference, exposing how reference-based similarity metrics misjudge personalized answers. See an infographic about AiVisor.

Research Areas

Core

Semantic Drift Detection

Active
SSDTSemantic DriftRecursive LLM GenerationDynamical Systems

Semantic Substrate Dynamics Theory (SSDT) is the foundation the group is built on: the claim that meaning behaves as a dynamical system with measurable structure. Word senses, diagnostic codes, and learned representations do not hold still. They shift when models process their own outputs and when real-world usage moves underneath them. SSDT gives us the vocabulary and the geometry to measure that motion, track where it accumulates, and mark the point where it crosses from noise into failure. See DriftWell as an example

Methods

Geometric Methods in AI Analysis

Active
Ollivier-Ricci CurvatureEmbedding GeometryFrame-Shift Detection

Meaning has shape, and shape can be measured. This area applies Ollivier-Ricci curvature and related tools from differential geometry to the embedding spaces where language models hold meaning. Curvature marks where a semantic region is tightly bound and where it is about to fragment. Graph structure shows how concepts connect and where those connections reorganize. Followed over time, the same geometry reveals where meaning bends, where a frame shifts, and where a trajectory is about to break. It turns semantic movement into something with coordinates, direction, and rate. Read about Ollivier-Ricci Curvature in SSDT

Applied

AI Reliability

Active
RAGAgentic PipelinesEvaluationAdversarial Robustness

Agentic systems chain retrieval, reasoning, and generation, and meaning can move at every hop while the workflow looks stable. We study where that happens and what it costs. A pipeline can carry the right answer forward or quietly reframe it, and the difference rarely shows on the surface. The same instability that degrades reliability by accident can be induced on purpose, which is why adversarial semantic manipulation sits inside this work rather than beside it. The question throughout is whether an agentic pipeline still means what it started with by the time it answers. See how AiVisor exposed a structural flaw in how these systems get scored

Exemplar

Clinical AI and Healthcare Informatics

Active
Coding DriftRevenue CycleClinical SurveillanceAI Governance

Healthcare is where semantic drift stops being academic. Clinical ontologies shifting or a governance model that loses clinical specificity causes changes in meaning-in-use that carry direct costs and patient-care risk. Our work focuses on coding drift detection and shifts across large inpatient cohorts, denial and revenue cycle prediction, VTE and SSI surveillance, and governance frameworks that keep AI aligned to care trajectories. See AI governance in TwinPath AI|Why governance is needed

Frontier

Human-System Integration and Agent Orchestration

Active
Human-Agent TeamingOrchestrationSituation AwarenessGovernance

As agents take over ingestion, triage, coding, and other pipeline processes, humans are increasingly disconnected from direct evidence and start seeing workflow products that upstream AI has already shaped. An object can look stable while the meaning underneath it moves -- from accident to attack, or from outage to state-linked operation -- with nothing on screen to signal the shift. This area builds the supervisory layer that catches it: semantic-dynamics metrics that flag when a stable object no longer carries stable meaning, and orchestration that routes reframing and human-agent disagreement to a person while letting settled outputs pass. The goal is to keep the human in command of meaning, not just in the loop. See an example analyst tool with semantic frame-shift capabilities

People

Stephen Russell
Stephen Russell
Professor, Intelligent Systems and Robotics Department
Semantic Drift, Human-Machine Teaming, Healthcare AI, Decision Support Systems, Intelligent Agents
Graduate Researchers
Maria Ramirez
Maria Ramirez
PhD Student
Semantic Instability, Data Science
Satyajit Movidi
Satyajit Movidi
PhD Student
Semantic Equivalency, RAG Systems, Personalization
Heather Anderson
Heather Anderson
PhD Student
Healthcare AI, Machine Learning
Pratigya Paudel
Pratigya Paudel
Graduate Research Assistant
Uncertainty Quantification, Machine Learning

Select Papers

The Personalization Paradox: Semantic Loss vs. Reasoning Gains in Agentic AI Q&A

Cloud Computing and Data Science
Satyajit Movidi, Stephen Russell

Examines how personalization changes agentic AI performance, revealing a mismatch between semantic similarity metrics and reasoning quality. Personalized responses can appear less aligned to a reference while becoming more grounded, relevant, and useful.

When Workflows Stay Stable but Meaning Moves in Agentic Analyst Pipelines

18th International Conference on Applied Human Factors and Ergonomics (AHFE 2026)
Stephen Russell

Shows how meaning can shift across an agentic workflow even when the underlying object and process appear unchanged. Demonstrates ways to detect semantic movement that conventional workflow monitoring may miss.

Mutual Information and Multi-Agent Systems

Entropy
Ira S. Moskowitz, Pi Rogers, Stephen Russell

Uses information theory to examine communication and coordination among interacting agents. Provides a formal basis for understanding how information is transferred, constrained, and potentially degraded within multi-agent systems.

Providing Care: Intrinsic Human–Machine Teams and Data

Entropy
Stephen Russell, Ashwin Kumar

Explores how human expertise can be incorporated into the data used by AI systems in healthcare. Connects representation and human knowledge with explainability, trust, and decision-making in human-machine teams.

Re-orienting Toward the Science of the Artificial: Engineering AI Systems

Systems Engineering and Artificial Intelligence
Stephen Russell, Brian Jalaian, Ira S. Moskowitz

Frames AI as an engineered system whose behavior emerges from interactions among models, information, humans, and environments. Emphasizes uncertainty, interoperability, stability, and system-level reasoning beyond isolated model performance.

Context: Separating the Forest and the Trees—Wavelet Contextual Conditioning for AI

Human-Machine Shared Contexts
Stephen Russell, Ira S. Moskowitz, Brian Jalaian

Explores computational approaches for representing context in AI systems. Addresses how information can take on different significance across situations and how contextual structure can be preserved during automated reasoning.

Valuable Information and the Internet of Things

AAAI Spring Symposium Series
Ira S. Moskowitz, Stephen Russell

Distinguishes the quantity of information from its value to a particular user or decision. Examines how information becomes useful through context and interpretation rather than through transmission or availability alone.

Human Information Interaction, Artificial Intelligence, and Errors

Autonomy and Artificial Intelligence: A Threat or Savior?
Stephen Russell, Ira S. Moskowitz, Adrienne Raglin

Examines how AI increasingly mediates the information people encounter and the errors that can emerge from that relationship. Shifts attention from isolated algorithmic errors toward failures produced through human-information-AI interaction.

Communicating Uncertainty Information across Conceptual Boundaries

Proceedings of the 2011 Winter Simulation Conference (WSC)
Paul Hyden, Elias Ioup, Stephen Russell

Examines what happens when information and uncertainty move between people, systems, and conceptual frameworks. Focuses on how important context can be lost as information crosses boundaries and is reused downstream.

05

Contact

We welcome inquiries from prospective graduate students, collaborators, and organizations interested in supporting this research. If your interests involve meaning and reliability in AI, human-AI systems, or applied AI research, we would be glad to hear from you.

Dept. of Intelligent Systems and Robotics
University of West Florida
Pensacola, Florida