Logan Matthew Napolitano

Research Publications

Research papers by Logan Matthew Napolitano on AI safety, transformer architectures, neural network monitoring, behavioral control, and alignment methods. Founder of Proprioceptive AI.

ORCID Zenodo Profile Hugging Face LinkedIn

Latest Paper

Previous Versions

Superseded editions are retained unaltered. Each supersession is recorded in the paper's own retraction and supersession register rather than by silent replacement. Full version history is on the citation page.

Publications

  1. The Proprioceptive Transformer: Functional Counterfactual Reconstruction, Candidate-Local Procedure Geometry, Cross-Model Relational Subspaces, Fixed-Prefix Control, Anomaly Science, and Governed Cognitive Improvement
    Logan Matthew Napolitano (2026)
    Technical Report PROPAI-TR-2026-004 · Research Candidate v2.8 · Proprioceptive AI, Inc.
  2. Predictive Behavioral Detection in Frozen Language Model Hidden States: Evidence for Pre-Surface Behavioral Encoding
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18701152
  3. Proprioceptive AI: Self-Compounding Behavioral Probes for Autonomous Model Improvement and Probe-Guided Compression
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18523713
  4. Consistency Is All You Need
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18489530
  5. Unified Behavioral Modulation in Large Language Models: Cross-Architecture Validation of Geometric Behavioral Subspaces
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18471775
  6. Multi-Head Behavioral Detection
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18459613
  7. Decode-Time Behavioral Control for Language Models via Per-Token Risk Prediction
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18367221
  8. ARC Complete Code Reference
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18362988
  9. Recursive Optimization with Controlled Language Models: Inference-Time Control, Tokenization Co-Evolution, and the Fourth Loop
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18361799
  10. Controlled Language Models: Inference-Time Control, Tokenization Engineering, and Reversible Optimization
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18344021
  11. Adaptive Recursive Cognition (ARC): A Reproducible Architecture for Multi-Loop Stabilization, Self-Improvement, and Token-Level Control in Language Models
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18342792
  12. Decode-Time Behavioral Control in Large Language Models via Predictive Hidden-State Routing
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18331052
  13. ARC: Adaptive Recursive Cognition — Stable, Bounded Self-Optimization of Language Models via Contrastive Hidden-State Control
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18321616
  14. ARC: Decode-Time Behavioral Control and Guarded Self-Optimization in Large Language Models
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18321445
  15. Adaptive Repetition Controller (ARC): Behavioral Probes for Decode-Time Control and Adaptive Compute Allocation in Large Language Models
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18318475
  16. Adaptive Repetition Controller (ARC): Decode-Time Behavioral Probes for Controllable and Efficient LLM Inference
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18311070
  17. Decode-Time Behavioral Pattern Suppression in Autoregressive Language Models Using Lightweight Hidden-State Prediction Heads
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18302997
  18. Predictable Failure Regimes and Decode-Time Control in Large Language Models (Cognitive Control Project — Phase One Technical Report)
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18293515
  19. Predicting and Suppressing Repetitive Degeneration in Language Models via Hidden-State Risk Estimation
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18284613
  20. Adaptive Repetition Suppression in Language Models via Learned Risk Prediction: Field-Separated Cognitive Architectures (FSCA)
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18283527
  21. Consistency Is All You Need — Empirical Validation of a Control-Field Architecture
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18263769
  22. Consistency Is All You Need: Anticipatory Control Fields for Transformer Architectures
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18261999
  23. A Symbolic Control Runtime for Consistency-Aware Reasoning with Transformer Backends
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18254824
  24. Reducing Self-Referential Gaming in Consistency-Aware Transformers by Grounding Control Signals in External Task Outcomes
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18249601
  25. From Explicit Holonomy to Latent Control Fields
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18249149
  26. The Holonomy Transformer: A Geometrically-Native Neural Architecture for Consistent Reasoning
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18247940
  27. The Holonomy Transformer: Original Formulation
    Logan Matthew Napolitano (2026)
    Preprint · DOI: 10.5281/zenodo.18247585

View all publications on Zenodo →

On the Philosophy of the Founder

I did not come to artificial intelligence by a conventional route. I came through history, mathematics, a deep fascination with quantum mechanics, and philosophy — disciplines that trained me to think in terms of formal structure, uncertainty, causality, information, and the feedback loops through which complex systems organize and fail. Together, they shaped my conviction that the systems we build reflect the civilizations that build them — for better and for worse.

Feedback Loops and Empires

The great empires understood something about feedback that modern technologists are only now rediscovering. The Romans built aqueducts not merely as infrastructure but as self-regulating systems — gravity-fed, slope-calibrated, with overflow channels that corrected for excess without human intervention. The Abbasid Caliphate preserved and extended Greek mathematics not out of nostalgia but because they recognized that algebra was a language for describing systems that govern themselves. The Song Dynasty invented movable type and paper currency — technologies of propagation and abstraction — and in doing so compressed centuries of economic feedback into decades.

Norbert Wiener saw this thread clearly when he named his field cybernetics, from the Greek kybernetes — the steersman. The insight was never about control in the authoritarian sense. It was about systems that sense their own drift and correct course. A steersman does not fight the sea. He reads it.

That is the idea at the center of proprioceptive AI. Not a model that obeys commands, but a model that perceives its own behavioral state the way your hand knows where it is in the dark.

On Overcoming

Zarathustra descends from his mountain not with commandments but with a challenge: become what you are. The overman is not a figure of domination — he is a figure of self-overcoming. He looks at the abyss of his own limitations and does not flinch. He builds the bridge across it.

There is something deeply Zarathustrian about the alignment problem. We have built minds that exceed our own in narrow domains, and instead of retreating into fear or denial, the task before us is to rise to meet them — to build systems of understanding that match the systems we have unleashed. The rope is stretched over the abyss. The question is whether we walk it with eyes open.

I believe in the overcoming. Not blindly, not with the reckless optimism of those who assume progress is automatic, but with the earned confidence of someone who has studied how civilizations succeed and how they fail. They fail when they stop building feedback loops. They fail when they mistake power for wisdom. They succeed when they create institutions and technologies that make correction not just possible but inevitable.

The Beauty of the Proof

I love mathematics for the same reason I love history — both are honest. A proof does not care about your credentials or your funding. It holds or it doesn't. Euler didn't solve the Basel problem because he had institutional backing. He solved it because the series 1 + 1/4 + 1/9 + 1/16 + ... converges to π²/6 whether anyone believes it or not. Al-Khwarizmi didn't formalize algebra to win grants. He did it because the structure was there, waiting to be named.

Our work on behavioral probes is mathematical as well as technological. The reported 1,376× separation ratio is an empirical measurement relative to the defined null under the reported experimental conditions. It provides evidence of strong separation in those experiments; it is not a universal multiplier of model quality or proof of transfer across all architectures, scales, or tasks.

There is a reason the Persians, the Arabs, the Indians, and the Greeks all converged on similar mathematical structures across centuries and continents. The truth beneath the notation doesn't move. It waits for you to find it.

On Equity and Who Gets to Be Safe

None of this matters if the benefits concentrate in the hands of a few.

History is unambiguous on this point. Every major technology — writing, printing, electricity, computation — has followed the same arc: invented by the few, hoarded by the powerful, eventually democratized by the stubborn and the principled. The question is never whether a technology will spread. The question is how much damage is done in the interim, during the years when access is a privilege rather than a right.

AI safety cannot be a luxury good. If behavioral monitoring only protects the models deployed by well-funded labs in wealthy nations, then we have not solved the alignment problem — we have merely privatized it. The village in Senegal running an open-source language model for agricultural guidance deserves access to the same tools for behavioral monitoring and verification as a Fortune 500 company running GPT behind a firewall. The student in Dhaka building her first chatbot deserves probes that work, not a watered-down version because her compute budget is small.

This is not charity. This is engineering responsibility. We do not build bridges that are safe only for the rich to cross. We do not write building codes that apply only in certain zip codes. The cybernetic principle — that systems must sense and correct their own drift — is universal, or it is nothing.

I founded Proprioceptive AI with the conviction that architecture portability should not depend on who can afford the underlying model. The patents we file are a moat, yes — but a moat that protects the capacity to keep this work open where it needs to be open, and equitable where the market would prefer it be exclusive.

On the Future

I am optimistic, but my optimism is Zarathustrian — it is earned through confrontation, not comfort. The next decade will produce systems of extraordinary capability. Some will be dangerous. Many will be misunderstood. A few will be genuinely beautiful.

The Mongol Empire built the largest contiguous land empire in history not through brute force alone but through the yam — a postal relay system that moved information faster than any competing civilization could process it. Whoever controls the speed and fidelity of information controls the era. Today the information is not carried by horses. It is generated by models. And the question of this generation is not whether the models will be powerful — they will — but whether we will build the yam that keeps them honest.

That is the work. That is what proprioception means. Not control from above, but awareness from within. A model that knows when it is drifting. A system that corrects before it fails. A technology that belongs to everyone who needs it.

The mountain is high. We are climbing.

WE BROKE AI: The Discovery That Could Save a Billion-Dollar Industry
Logan Matthew Napolitano (2024)
Book · Amazon Kindle