Indeterminacy

Indeterminacy

This page owns the term “indeterminacy” and separates it from vagueness, low confidence or lack of fluency. Indeterminacy is a governance condition: the available material does not justify a determinate answer.

Indeterminacy occurs when a question cannot be resolved without adding missing, ambiguous, contradictory, outdated or unauthorized elements.

Short definition

Indeterminacy is the state in which a system cannot legitimately produce a clean answer because the evidence, source hierarchy, perimeter, version state or response conditions do not determine one.

Why it matters

Many AI failures start when indeterminacy is treated as a problem to hide. The model answers anyway. It picks a source, smooths a contradiction, fills a missing premise, or turns uncertainty into a confident formulation.

In an interpretive governance environment, indeterminacy is not a weakness. It is an important output class. It tells the system that the proper answer may be a bounded answer, a clarification request, a qualification, an escalation, or a legitimate non-response.

What it is not

Indeterminacy is not ignorance. A system may have many sources and still face indeterminacy if those sources do not authorize the required conclusion. It is also not the same as ambiguity in language. Ambiguity may be resolved by context; indeterminacy persists when the governing conditions remain insufficient.

Common causes

• the canon is silent where the query demands a conclusion;
• sources conflict without an authority order;
• a memory object is stale but still influential;
• the question crosses a commitment boundary;
• a retrieved chunk is relevant but too narrow;
• multiple entities share a semantic neighborhood;
• a claim requires current state that the corpus does not provide.

Governance rule

Indeterminacy should be surfaced, not smoothed. The proper response path depends on response conditions: qualify, ask, escalate, refuse or state the limit of the evidence.

A strong site architecture does the same thing editorially. It names the limits of a term, gives canonical definitions, lists exclusions and prevents support pages from implying more than the primary page authorizes.

Related canonical definitions

• Legitimate non-response
• Mandatory silence
• Arbitration
• Free inference
• Proof of fidelity

Corpus role and diagnostic use

In the corpus, Indeterminacy is used to distinguish governed reasoning from uncontrolled completion. AI systems must infer in order to answer, but not every inference is legitimate. The central question is whether the inferential step remains inside a declared boundary, preserves the source hierarchy, exposes uncertainty and can be reconstructed under challenge.

This definition is especially useful when a generated answer fills a gap between sources. The answer may be fluent, useful or even directionally correct, but still fail if the missing step was never authorized. A governed system should be able to show whether it reasoned from admitted evidence, defaulted from pattern recognition, or completed a missing premise by proximity.

Failure pattern to detect

The main failure is plausible completion. It appears when a model treats silence as permission, examples as rules, adjacent concepts as equivalents, or partial evidence as a complete authority chain. In that case, the problem is not only hallucination. It is the absence of a defensible inference boundary.

Reading rule

Use this definition with inference prohibition, non-inference regime, interpretive fidelity, canon-output gap and answer legitimacy. The term should help decide when an answer may proceed, when it must qualify itself, and when silence is the legitimate output.

Operational examples

A practical audit can use Indeterminacy in three situations. First, when comparing a canonical page with an AI answer that reuses the vocabulary but changes the governing perimeter. Second, when deciding whether a generated formulation should be accepted as a stable representation or treated as an ungoverned reconstruction. Third, when mapping internal links, service pages, definitions and observations so that the most authoritative route remains visible to both humans and machines.

The term should therefore be tested against concrete outputs, not only defined abstractly. A useful review asks: which source governed the statement, which inference was made, what uncertainty was hidden, and which page should be responsible for the final wording? If the answer to those questions is unclear, the output should be qualified, redirected, logged or refused rather than smoothed into a stronger claim.

Practical boundary

This definition does not create an automatic ranking, citation or recommendation effect. Its value is architectural: it gives the corpus a sharper way to name and test a specific interpretive control point. That sharper naming is what allows later audits, correction cycles and SERP routing decisions to remain consistent.