Engineering a reliable
interface to reality.

• 01 / ResearchBeyond OntologyFrom semantic understanding to fact acceptance: the boundary between Knowledge, Claim and Operational State.3 publications
• 02 / ResearchVerifiable RealityEvidence, provenance, authorization, validity, conflicts, revocation and cross-party verification.2 publications
• 03 / ResearchReality RuntimeSemantic runtime, agent execution, permission boundaries and open agent networks.2 publications
• 04 / ResearchEngineering & BenchmarksProtocol implementation, engineering trade-offs, reproducible experiments, correctness and cross-domain cost.1 publication

1. 01
   Reality Runtime · Perspective · October 2026Why Agents Need Verifiable StateFrom procurement questionnaires to external AI inquiries: why agents need attributable, current, permission-aware state — and what cryptography alone cannot prove.
   →
2. 02
   Beyond Ontology · Perspective · October 2026Agent Memory Is Not Operational StateWhy durable agent memory, RAG corpora, and knowledge graphs are not the same as formally accepted operational state with sources, authority, and disclosure boundaries.
   →
3. 03
   Verifiable Reality · Engineering Note · October 2026Managing Revocation and Conflicting ClaimsHow late evidence, revocations, and conflicting claims change current state — with an illustrative walkthrough and explicit limits on what Tinor claims today.
   →

• Series 1From Knowledge to StateWhat has to happen before an interpretation of reality becomes something others can rely on.3 available
• Series 2Engineering Reality StateTypes, time and disagreement: the engineering of state that changes and is contested.1 available
• Series 4Measuring Reliable RealityHow to measure whether a stateful system admits the right things, and at what cost.1 available

1. Beyond Ontology · PerspectiveAgent Memory Is Not Operational StateWhy durable agent memory, RAG corpora, and knowledge graphs are not the same as formally accepted operational state with sources, authority, and disclosure boundaries.October 2026
2. Verifiable Reality · Engineering NoteManaging Revocation and Conflicting ClaimsHow late evidence, revocations, and conflicting claims change current state — with an illustrative walkthrough and explicit limits on what Tinor claims today.October 2026
3. Reality Runtime · PerspectiveWhy Agents Need Verifiable StateFrom procurement questionnaires to external AI inquiries: why agents need attributable, current, permission-aware state — and what cryptography alone cannot prove.October 2026
4. Beyond Ontology · PerspectiveBeyond Ontology: From Understanding Reality to Relying on ItOperational ontologies made business reality computable and actionable. Cross-party reliance asks a further question: is this specific claim admissible, by whose authority, and as of when?October 2026
5. Verifiable Reality · PerspectiveProof Is Not TruthWhen a record, credential or signature verifies, what exactly has been verified? Integrity, signer identity, authority, status, scope and applicability are different checks — and none of them is truth.October 2026
6. Beyond Ontology · PerspectiveAn AI Answer Is Not a FactWhat has to happen before a probabilistic interpretation becomes accepted, reusable state: the Fact Admission Boundary, step by step, with a certification claim extracted from a website and a PDF.October 2026
7. Reality Runtime · Engineering NoteReality Needs a Type SystemCan real-world claims be compiled into representations with machine-checkable constraints before anyone accepts or acts on them? An engineering note on subjects, scope, time, authority and evidence as types.October 2026
8. Engineering & Benchmarks · Research NoteToward Zero Invalid State Admissions: A Benchmark ProposalA proposed benchmark for stateful AI systems: measure invalid admissions and useful task completion together, so that neither reckless acceptance nor blanket refusal looks like reliability.October 2026

1. Jun 2026Protocol coreObject timelines, Profiles, six core event types with semantic boundaries, and a proof / evidence / signature model that keeps integrity separate from truth.
2. Jul 2026Identity, resolution and disclosurePrincipal identity, a read-side fact resolution engine, typed references with invalidation, and unified authorization and disclosure governance.
3. Aug 2026Resolved trust read planeA read plane for resolved trust, and rights authorization modelled as a first-class object.
4. Sep 2026From candidate to admitted factAgreement as derived shared state, the Semantic Runtime boundary from typed candidate to deterministic action, domain semantic assets, and fact identity and admission.
5. Oct 2026Conflict, standing and reality compilationMulti-assertion conflict and standing-resolution contracts, reality compilation with layered assessment, and the first public Journal essays.

Follow new publications: RSS · English