Research and specification · Basis 22 August 2026

R / 10
Bounded research

Ordivon Computing

Keep only responsibilities that remain unowned after comparison with mature systems and materially different workloads.

The scientific synthesis and knowledge-transformation layer for Ordivon. Computing consumes owner-native and external evidence, tests cross-project claims, preserves reusable explanations, and keeps only compact shared responsibilities that survive deletion; it is not a global current-state authority.

Projected status
Mature cross-project synthesis, Knowledge, method, and conformance root; new research remains admission-gated
For
Researchers and system designers asking which distinctions survive independent domains and mature baselines, which owner should hold them, and which results should become reusable Knowledge rather than new infrastructure.
Evidence for status
The 1760–2026 historical dogfood closed without turning historical resemblance into proof of Ordivon theory, and the current Computer contraction reduced active shared machinery to a small responsibility map. On 2026-08-22 the canonical Research Method was strengthened to preserve imported mature knowledge through novelty subtraction, expose that method at first look, adjudicate closeout destinations, and materialize the Resource Ecology result as reusable Knowledge without creating a Resource owner or calculus.

Question this project must answer

Which facts and contracts must remain stable when models, Hosts, Harnesses, tools, and execution backends change?

Current operating model

QuestionStrong baselineExperimentDispositionProtocolConformance

Standing in this projection

Mature cross-project synthesis, Knowledge, method, and conformance root; new research remains admission-gated

Current Computing separates Research, reusable Knowledge, compact Core, owner-native Projects, and Git history. SCD and Computational Possibility remain independent semantic owners inside the repository. The contracted Computer has no obligation to keep an active research line by inertia: new shared structure must survive owner placement, mature-baseline, deletion, and materially different consumer tests.

Capability evidence

1760–2026closed historical dogfood horizon
10current contracted Computer responsibilities
import → Knowledgesource-neutral research closeout path

What this project owns

Facts, products, or methods maintained here.

  • Shared theory
  • Research portfolio
  • Promoted protocol
  • Conformance evidence

What it leaves elsewhere

Responsibilities and claims outside its boundary.

  • No production Tasks
  • No physical Jobs
  • No product maturity claims

Questions and current judgments

01

testing

When should a finite intelligence expand its interface to Reality instead of only reasoning harder?

02

testing

When should an Agent act, wait, observe, refuse, reconcile, or request a decision?

03

open

Which Task Runtime objects are required by asynchronous waiting and Join semantics?

04

reframed

Which responsibilities survive materially different workloads without becoming one mandatory stack?

05

answered

Which Agent-native responsibilities remain after strong classical baselines?

06

answered

What is the smallest explanation that preserves the causal boundaries an Agent needs?

07

answered

When does valid evidence stop being current enough to govern a decision?

08

answered

Does canonical evidence order make an Agent understand the evidence better?

09

answered

Which Agent-era world-model laws survive historical out-of-distribution pressure?