Preprint v1.1 (revised) (2026-11-01) · DOI 10.5281/zenodo.23319376 · describes ENGRAM v0.5.1 · 中文
Version 1.1 is the paper's repository text of 2026-10-22, tagged for this site on 2026-11-01. It adds post-deposit corrections and wording revisions, a new section 6.8 (an independent audit of 200 nodes) and a new paragraph in Chapter 7. Its front page still names the deposited version 1 of 2026-10-13.
Epistemic Identity: A Third Layer of Agent Continuity, and a Substrate That Realizes It
This page is the latest version of the paper: Preprint v1.1 (revised). The same pages are permanently at /paper/v1.1/
Large language model agents can now carry information across sessions, but not themselves. Retrieval-augmented memory answers what did I store; it does not answer who is doing the storing. An assistant that retrieves yesterday's notes but begins each session as the same generic model has memory without continuity.
Contents
- Epistemic Identity: A Third Layer of Agent Continuity, and a Substrate That Realizes It
- Abstract
- Chapter 1 — The Continuity Gap and the Case for Epistemic Identity
- Chapter 2 — The Philosophical Tradition
- Chapter 3 — The Cognitive-Science and Computer-Science Tradition
- Chapter 4 — ENGRAM's Mechanisms (and the Continuity Threshold They Meet)
- Chapter 5 — Identity as History: What Individuates an ENGRAM Agent
- Chapter 6 — The Empirical Picture: ENGRAM in Real Use
- Chapter 7 — Implications and Future Directions
- Chapter 8 — Conclusion
- Appendix A — Independent Discovery: A Development-History Audit
- Appendix B — The Condition-3 Survey: Why No Surveyed System Self-Maintains Arbitration
- Appendix C — Shared Retrieval and Ranking for the Auto-Surface and Deliberate Recall, and the Memory-Utility Tradition
- Appendix D — Relational and Identity-Governance Settings
- Appendix E — ENGRAM: A Concise Specification
- Appendix F — Lucy's Journal: How We Came to Think of Agents
- Appendix G — Glossary
- Acknowledgements
- Afterword: a note from the human author
- Bibliography