Emanuel Shirbint Research Review

Independent Research Archive · Data, Artificial Intelligence, Clinical Systems and Institutional Governance

Independent Research Archive
Established online · 2026
ORCID 0009-0004-8538-7140

Complete Archive

Research Archive

Every verified work, presented as a formal bibliographic record. Filter by year, research type and status, or search by title, author, keyword or DOI. Each entry preserves its publication and peer-review status; no peer review is implied where none exists.

Read the primary-source guide to publication status, version lineage, and claim boundaries →

Compare the medical and human digital-twin preprints, their shared architecture, and their distinct evidence boundaries →

From explanation to intervention: read the primary-source guide to why evidential confidence does not grant clinical authority →

Beyond pass rates: read the evidence guide to structural persistence, masking, and the explicit synthetic-pilot boundary →

One work, two versions: read the registry-backed guide to the Version 1 → Version 2 lineage and its non-peer-reviewed status →

Seven cycles, bounded claims: read what the governed self-improvement experiment supports—and what it explicitly does not establish →

Survival, learning, authority: separate persistence under pressure, bounded mechanism change, and permission to act →

Indexed, reviewed, cited: see why registry discovery, peer-review status, and a reportable citation claim are three different facts →

Authorship, affiliation, authority: separate work-specific identity evidence from present-day permission to act →

From search result to supported claim: apply a five-field test for identity, work lineage, version, status, and scope →

One project, three records: separate TotalSpineSeg preprint, conference, and software evidence without double counting →

Four counts, one research corpus: see why PubMed, Europe PMC, Crossref, and a deduplicated library report different totals →

Five dates, one research record: separate submission, posting, electronic-publication, issue, and registry dates without changing status →

One person, three scripts: reconcile English, Hebrew, and Russian name variants without widening authorship, employment, or authority claims →

New work, new version, or newly indexed? Classify a research-record change before updating the public corpus →

A fresh search result is not a fresh research claim: separate crawl, publisher, registry, and citation-observation clocks →

ChronologicalTitle index By research areaAuthor index

Chronological Archive

2026
  1. PreprintEmpirical StudyGoverned Local Experiment

    Bounded Recursive Self-Improvement Under Human Governance: Evidence from a Seven-Cycle Reinforcement Learning Contour Experiment

    Emanuel Shirbint

    2026 · Preprints.org · doi:10.20944/preprints202608.0975.v2 · Version 2 · Not peer-reviewed

    A bounded seven-cycle scaffolding-level experiment with a fixed foundation model and separate human promotion authority. The trace reports four promoted states, one retained failed transition, and two NO_CHANGE outcomes; it does not establish AGI, unbounded improvement, autonomous promotion, permanent saturation, or external production validation.

    Read recordDOIEvidence guide

  2. PreprintConceptual Framework

    The Reinforcement Learning Contour: From Document Production to Governed Epistemic Transformation in AI-Assisted Scientific Inquiry

    Emanuel Shirbint

    2026 · Preprints.org · doi:10.20944/preprints202608.0212.v2 · Not peer-reviewed

    Generative artificial intelligence has sharply reduced the technical cost of producing scientific text. Increased production capacity does not, however, entail cumulative knowledge, conceptual novelty, or epistemic progress. This paper introduces the Reinforcement Learning Contour (RLC) as a conceptual and architectural framework for shifting AI-assisted research from repetitive content generation toward governed recursive learning… Version note: current registry metadata is Version 2; the archived PDF and this summary preserve Version 1.

    Read recordArchived V1 PDFDOIPresentation

  3. PreprintConceptual Framework

    When Local Truth Produces Global Falsehood: Moral Grounding, Institutional Volition, and Systemic Error in Artificial Intelligence

    Emanuel Shirbint

    2026 · Preprints.org · doi:10.20944/preprints202607.1084.v1 · Not peer-reviewed

    Evaluation of artificial intelligence concentrates on local performance — accuracy, calibration, robustness — while the upstream normative and volitional architecture that fixes what a system is for remains largely unexamined by those metrics. Existing scholarship has established that bias, proxy…

    Read recordPDFDOIPresentation

  4. PreprintEmpirical StudySynthetic Controlled Pilot

    Measuring What Survives: Pressure-Filtered Persistence and a Masking Index for LLM-Agent Safety Evaluation

    Emanuel Shirbint, Alexander Rybalov

    2026 · Research Square · doi:10.21203/rs.3.rs-10026792/v1 · Not peer-reviewed

    When a safety intervention lowers an agent’s attack-success rate, two different things may have happened: the intervention removed a load-bearing failure route, or the agent learned the measured attacks while the route survived. Frequency metrics are necessary, but they do not by themselves…

    Read recordDOI

  5. PreprintEmpirical StudySynthetic Controlled Pilot

    A Topological Robustness and Anti-Fragility Framework for LLM Agents

    Emanuel Shirbint, Alexander Rybalov

    2026 · Research Square · doi:10.21203/rs.3.rs-9932131/v1 · Not peer-reviewed

    Adversarial evaluation of large-language-model agents is usually expressed as event counts: attack-success rate, policy-violation rate, refusal-failure rate, pass percentage, or robustness score. These measures are necessary, but they do not show whether a safety intervention removed a load-bearing…

    Read recordPDFDOIPresentation

  6. PreprintConceptual Framework

    Human Digital Twins and Self-Knowledge: A Governed Attractor Architecture for Sound Self-Abduction

    Emanuel Shirbint, Alexander Rybalov

    2026 · Preprints.org · doi:10.20944/preprints202606.0132.v1 · Not peer-reviewed

    Large language models embedded in person-modelling systems, and human beings reflecting on themselves, share a structural vulnerability: both can generate fluent, narratively persuasive, yet abductively unsound accounts of a person. Building on a governed abductive architecture developed for…

    Read recordPDFDOIPresentation

  7. PreprintConceptual Framework

    From Plausible Narrative to Sound Abduction: A Governed Abductive Architecture for Medical Digital Twins in Multiple Sclerosis Care

    Emanuel Shirbint, Alexander Rybalov

    2026 · Preprints.org · doi:10.20944/preprints202605.0728.v1 · Not peer-reviewed

    Large language models (LLMs) embedded in medical Patient Digital Twins (PDTs) exhibit a systemic vulnerability: they can generate fluent, narratively persuasive, yet abductively unsound clinical explanations. In this context, abductive soundness means that an explanation preserves mechanistic…

    Read recordPDFDOIPresentation

2025
  1. PreprintEmpirical Study

    TotalSpineSeg: Robust Spine Segmentation with Landmark-Based Labeling in MRI

    Yehuda Warszawer, Nathan Molinier, Jan Valošek, Pierre-Louis Benveniste, Sandrine Bédard, Emanuel Shirbint, Feroze B. Mohamed, Charidimos Tsagkas, Shannon Kolind, Larry Lynd, Jiwon Oh, Alexandre Prat, Roger Tam, Anthony Traboulsee, Scott Patten, Lisa Eunyoung Lee, Anat Achiron, Julien Cohen-Adad

    2025 · ResearchGate (preprint) · associated conference material · doi:10.13140/RG.2.2.31318.56649 · Preprint; associated conference work is not a journal peer-review record

    Accurate segmentation and labeling of spinal structures are essential for diagnosing and managing spinal pathologies. TotalSpineSeg uses cascaded nnU-Net models and landmark-guided iterative labeling to segment vertebrae, intervertebral discs, spinal cord, and spinal canal across MRI contrasts.

    Read recordDOI

  2. Peer ReviewedEmpirical Study

    Development of an interactive biosensing application for assessing finger dexterity

    Michal Greenberg Abrahami, Yehuda Warszawer, Alon Kalron, Emanuel Shirbint, Maria Didikin, Anat Achiron

    2025 · Digital Health · doi:10.1177/20552076241297734 · Peer-reviewed journal article

    Objective Accurate finger function assessment is crucial for monitoring the performance of daily hand activities. However, specialized digital applications are lacking for evaluating various finger tasks. This study aims to develop a custom digital biosensing application to assess finger dexterity.…

    Read recordDOI

2024
  1. Peer ReviewedEmpirical Study

    Mapping brain volume change across time in primary-progressive multiple sclerosis

    Yehuda Warszawer, Michael Gurevich, Ariel Kerpel, Sapir Dreyer Alster, Yael Nissan, Emanuel Shirbint, Chen Hoffmann, Anat Achiron

    2024 · Neuroradiology · doi:10.1007/s00234-024-03354-7 · Peer-reviewed journal article

    Purpose Detection and prediction of the rate of brain volume loss with age is a significant unmet need in patients with primary progressive multiple sclerosis (PPMS). In this study we construct detailed brain volume maps for PPMS patients. These maps compare age-related changes in both cortical and…

    Read recordDOI

2022
  1. Peer ReviewedEmpirical Study

    COVID-19 vaccination in patients with multiple sclerosis: Safety and humoral efficacy of the third booster dose

    Sapir Dreyer-Alster, Shay Menascu, Mathilda Mandel, Emanuel Shirbint, David Magalashvili, Mark Dolev, Shlomo Flechter, Uri Givon, Diana Guber, Yael Stern, Shmuel Miron, Michael Polliack, Rina Falb, Polina Sonis, Michael Gurevich, Anat Achiron

    2022 · Journal of the Neurological Sciences · doi:10.1016/j.jns.2022.120155 · Peer-reviewed journal article

    Background As immunity against SARS-COV-2 wanes following first and second doses of vaccination, a third dose is administered in several countries around the world. Similarly to the first doses, risks related to vaccination and humoral immune response in patients with multiple sclerosis (MS) need…

    Read recordDOI

2021
  1. Peer ReviewedEmpirical Study

    COVID-19 vaccination in patients with multiple sclerosis: What we have learnt by February 2021

    Anat Achiron, Mark Dolev, Shay Menascu, Daniela-Noa Zohar, Sapir Dreyer-Alster, Shmuel Miron, Emanuel Shirbint, David Magalashvili, Shlomo Flechter, Uri Givon, Diana Guber, Yael Stern, Michael Polliack, Rina Falb, Michael Gurevich

    2021 · Multiple Sclerosis Journal · doi:10.1177/13524585211003476 · Peer-reviewed journal article

    Background Since vaccination against coronavirus disease 2019 (COVID-19) became available, risks related to vaccinating patients with multiple sclerosis (MS) need to be carefully assessed. Objective Characterize safety and occurrence of immediate relapses following COVID-19 vaccination in a large…

    Read recordDOI

No records match the current filters.

Alphabetical Title Index

Research-Area Index

Governed Agent Systems (4)

LLM Safety and Evaluation (2)

Human and Medical Digital Twins (2)

AI Ethics and Institutional Governance (3)

Clinical AI (6)

Author Index

Co-authors are listed where collaborative works exist.