ORDIVON
Menu
Question dossierOrdivon Computinganswered

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

Separate deterministic byte identity from semantic tractability, and falsify wire/evaluator ambiguity before attributing Agent errors to presentation order.

All research questionsOpen project

01 / Current position

A hypothesis is not the current judgment.

The dossier preserves the live research position. Dated articles preserve the complete evidence and argument that changed it.

Working hypothesis

Canonicalization should be retained for owner-declared identity/replay needs but promoted as a model-facing representation only after an unambiguous prospective experiment beats raw presentation.

Current judgment

Answered for P11. Six unordered datasets collapsed 720 raw permutation digests to one stable identity, but after invalidating a truncated Tool-wire campaign and clarifying an ambiguous evaluator target, raw presentation scored 44/48 strict versus 42/48 stable list and 43/48 identity map. No semantic normalization advantage survived.

02 / Decision boundary

What keeps this Question alive?

Why it matters

Stable sorting and maps are mechanically attractive enough to become permanent Context infrastructure even when the observed model variance actually comes from a broken Tool wire or ambiguous oracle.

Next admitted test

Use deterministic canonicalization only where owner semantics require stable identity. Reopen model-facing order machinery after a new unambiguous workload reproduces material order sensitivity that simpler evaluator/prompt clarification cannot remove.

Condition for deletion

Across independent clear-oracle workloads, one canonical representation repeatedly improves semantic accuracy over raw presentation and the gain survives Provider changes without erasing meaningful event order.

03 / Supporting publications

Complete arguments connected to this Question.

1 dated publication currently document this research line.

Research report

We Sorted the Evidence. Accuracy Got Worse.

Computing P11 separated deterministic representation from semantic tractability, invalidated two confounded campaigns, and rejected active evidence-order normalization after a cleaner oracle made the raw baseline win.

12 August 2026 ↗

04 / Source discipline

The dossier is an index, not the evidence authority.

Question metadata

Owns the current judgment, next test, and deletion condition.

Publications

Own complete dated arguments, limitations, comparisons, and source links.

Repositories

Own exact code, tests, releases, receipts, and machine evidence.

Related frontier

testing

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

Testing under a contracted theory. External prior art falsifies the claim that action/interface expansion is absent, but it also weakens any absolute transcendence claim: callable, representational, affordance, and executor expansions can be new relative to one closure while remaining compositional inside a deeper supplied substrate. No universal basis hierarchy or generic basis-escape object is admitted.

testing

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

Testing with a stronger real-domain non-action case. Finance QB6 let one Agent request exact read-only evidence rather than infer missing execution facts, then update from more_research to no_op when the current minimum contract exceeded both the frozen 10% target and existing 25% canary bound; the branch ended before simulation, Decision, Proposal, or financial write.

open

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

Open. Round 1 showed that mature workflow engines can carry durable work mechanics, but no interrupted fan-out and fan-in workload has yet proved which semantic Join facts must remain visible above those mechanics.

reframed

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

Reframed and answered at the responsibility level. Game, Finance, Security, World, Web, Host, Harness, and Runtime now provide materially different consumers and deletion tests. The recurring result is not a universal Host→Harness→Runtime stack: Computing's canonical Core explicitly treats subsystem names as non-invariants and retains only responsibilities that remain unowned after mature mechanisms and owner-native composition. Cross-domain pressure has repeatedly localized, deleted, or kept different packages while preserving a smaller set of ownership/identity/currentness/recovery distinctions.

answered

Which Agent-native responsibilities remain after strong classical baselines?

Answered within Round 1. Strong baselines reduced the proposed core; later Host and Harness extraction clarified the surviving ownership split without adding a universal Agent platform.

answered

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

Answered on the EX3–EX7 Agent-facing surfaces. All treatments reached the same exact-action ceiling across 1,326 accepted decisions; richer representations added token burden, so the preregistered smallest-non-inferior rule selected compact prose.

answered

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

Answered for the current evidence horizon. Security EC1 separated byte identity from semantic applicability; World independently separates historical occurrence from current relation/Presence; Web source-bound publication distinguishes exact owner revision from current editorial judgment and exposed stale static/test consumers; Finance further showed that an already coherent state-changing Decision loses Proposal authority when its PortfolioSnapshot baseline is no longer current. Computing Knowledge now records both HistoricalValidity != Currentness and AdmissionCurrentness != CommitmentCurrentness. These cases support owner-native revalidation and have not forced a generic Freshness, impact-graph, or automatic rebase service.

answered

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

Answered for the HD0–HD9 programme. The frozen 1760–2026 campaign closed with 320 trajectories and 96 Deep Anchors across eight chronological waves. Cross-era recurrence survived only as a typed seven-family structural map plus explicit demotions, merges, replay negatives, and measurement/currentness results; the evidence did not justify ten universal success invariants or eight universal innovation laws.