Neutral Substrates

Defines neutral substrates that preserve shared reference without adopting contested interpretations.

Paper Overview

Neutral Substrates: A Design Constraint for Shared Records Under Persistent Interpretive Disagreement

• arXiv
• SciX

Main Contribution

This paper addresses a practical problem in shared records where parties persistently disagree about interpretation.

Simply omitting contested information can undermine accountability, because records should preserve what parties claim along with the provenance of those claims. But adopting one contested interpretation as the shared foundation can compromise neutrality.

The paper establishes a sufficient condition for semantic neutrality. If the shared referential commitments, taken as a whole, are compatible with every admissible framework, then limiting the foundation to those commitments and to attribution statements grounded in them is enough to preserve neutrality.

Contested causal and normative claims can still be represented as attributed assertions tied to an identified framework, source, agent, or record. The shared system records who asserted what, with provenance, without endorsing the asserted claim.

Guaranteeing neutrality by design requires additional justification. The paper establishes one sufficient approach to semantic neutrality, not the only possible way to build a neutral system.

Scope

The result does not apply when the shared referential information, or the basis for attributing claims to sources, conflicts with an admissible framework. Disagreement about interpretation alone does not trigger this.

Basis

• Lean basis summary
• Lean 4 formalization: se-theory-neutral-substrate

Building Locally

• On Windows, install Strawberry Perl and MiKTeX.

Requires a LaTeX distribution with latexmk (MiKTeX, TeX Live, or MacTeX):

latexmk -pdf se100-neutral-substrates.tex

texcount -inc -sum -total se100-neutral-substrates.tex

Windows:

# build
.\tools\build\build.ps1

# update ps1 as needed and calculate the basis (defs, etc.)
.\basis.ps1

Validate with:

uvx cffconvert --validate
uvx se-manifest-schema validate-manifest --strict

References

1. Carroll, J. J., Bizer, C., Hayes, P., and Stickler, P. (2005). "Named graphs, provenance and trust." In Proceedings of the 14th International Conference on World Wide Web (WWW 2005), pages 613–622. ACM. https://lists.w3.org/Archives/Public/www-archive/2004Apr/att-0081/PID-FAFPGYHS-1081860211.pdf

2. de Kleer, J. (1986). "An assumption-based TMS." Artificial Intelligence, 28(2):127–162. https://www.semanticscholar.org/paper/An-Assumption-Based-TMS-Kleer/ed3f9263e936a879092ad7a2bf27e0f94089ccd8

3. Dung, P. M. (1995). "On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games." Artificial Intelligence, 77(2):321–357. https://doi.org/10.1016/0004-3702(94)00041-X

4. Floridi, L. (2008). "The method of levels of abstraction." Minds and Machines, 18(3):303–329. https://doi.org/10.1007/s11023-008-9113-7

5. Gangemi, A., and Mika, P. (2003). "Understanding the Semantic Web through descriptions and situations." In R. Meersman, Z. Tari, and D. C. Schmidt (Eds.), On the Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE, Lecture Notes in Computer Science, vol. 2888. Springer. https://doi.org/10.1007/978-3-540-39964-3_44

6. Gómez Álvarez, L., and Rudolph, S. (2021). "Standpoint logic: Multi-perspective knowledge representation." In Formal Ontology in Information Systems (FOIS 2021), Frontiers in Artificial Intelligence and Applications, pages 3–17. IOS Press. https://doi.org/10.3233/FAIA210367

7. Guarino, N. (1998). "Formal ontology and information systems." In Formal Ontology in Information Systems (FOIS ’98), pages 3–15. IOS Press. https://www.loa-cnr.it/Papers/FOIS98.pdf

8. Hayes, P. (2004). RDF Semantics. W3C Recommendation, World Wide Web Consortium. https://www.w3.org/TR/2004/REC-rdf-mt-20040210/

9. Lebo, T., Sahoo, S., and McGuinness, D. L., editors (2013). PROV-O: The PROV Ontology. W3C Recommendation, World Wide Web Consortium. https://www.w3.org/TR/prov-o/

10. McCarthy, J. (1993). "Notes on formalizing context." In Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI-93), pages 555–560. https://www.ijcai.org/Proceedings/93-1/Papers/078.pdf

11. Searle, J. R. (1969). Speech Acts: An Essay in the Philosophy of Language. Cambridge University Press. https://doi.org/10.1017/CBO9781139173438

Related and Adjacent Work

Selected papers from the Harvard SciX similar-papers search for Neutral Substrates.

Identity and Equivalence

• Representing Identity and Equivalence for Scientific Data

Provenance

• Provenance-Enhanced Statements in Knowledge Graphs
• Responsible Agentic AI Requires Explicit Provenance
• From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents

Responsibility Attribution

• Mapping Responsibility Attribution in the Grenfell Tower Inquiry: A Network Analysis

Contradiction, Disagreement, and Ambiguity

• ECO/CPO-DAG: A Contradiction-Based Accountability Layer for Adversarial Supply Chains
• Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal
• Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks

Assertibility

• No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason

Operational Records and Auditable Agents

• The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems
• Auditable Agents

Annotations

Annotations

Changelog

CHANGELOG.md

Citation

CITATION.cff

License

CC BY 4.0

Repository Manifest

SE_MANIFEST.toml