Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models
The paper introduces ODYSSEY, a categorical framework for building verifiable, local truth-preserving foundation models by composing 'foundries'—modular architectural components that specify local contexts, representation families, restriction maps, gluing rules, obstruction policies, update obligations, and human-facing views. Universal Foundry Learning formalizes construction via left and right Kan extensions, while Foundry SQL provides a query surface using TICKET certification. The system is fully implemented and tested across diverse foundries, and will be presented as a 2.5-hour tutorial at ICML 2026.
[2606.27593] Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models
[Submitted on 25 Jun 2026]
Title:Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models
View a PDF of the paper titled Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models, by Sridhar Mahadevan
View PDF HTML (experimental)
Abstract:We introduce a categorical framework called ODYSSEY for constructing verifiable, local truth-preserving foundation models as compositions of foundries: building-block architectural components that specify a cover of local contexts, local representation families, restriction maps, gluing rules, obstruction policies, update obligations, and human-facing views. A foundry is an organized sheaf of knowledge that carries within it an argumentation component. Concrete foundries are built from generic foundries such as evidence/argument, operational decision, institutional/financial, market meaning, scientific challenge, research-program, assistant-build, and evaluation-harness foundries. Universal Foundry Learning (UFL) formalizes foundry construction as a composition of left and right Kan extensions, with left Kan extension rolling local artifacts into candidate foundries and right Kan extension enforcing the restriction, gluing, obstruction, and argumentation conditions required for promotion. Foundry SQL (FSQL) is a small typed query surface for slicing maintained foundry artifacts that uses TICKET (Topos Integration using Causal Kan Extension Transformers) certification for admitting external or pre-built models into durable ODYSSEY state. ODYSSEY is fully implemented and tested across a wide spectrum of concrete foundries, showing that the same categorical machinery supports domain construction, artifact replay, sheaf diagnostics, grounded Toulmin/local-LLM scrutiny, residual-obstruction ledgers, and optimized TICKET-compatible causal-claim extraction across heterogeneous sources. This paper is to be presented as a 2.5 hour tutorial at ICML 2026. The tutorial home page is at this https URL.
Comments: 34 pages
Subjects:
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2606.27593 [cs.AI]
(or arXiv:2606.27593v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.27593
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Sridhar Mahadevan [view email] [v1] Thu, 25 Jun 2026 22:49:17 UTC (741 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models, by Sridhar Mahadevan
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)