



Network Working Group                                       O. Romanchuk
Internet-Draft                                               Independent
Intended status: Informational                            6 January 2026
Expires: 10 July 2026


        Normative Admissibility Framework for Agent Speech Acts
               draft-romanchuk-normative-admissibility-00

Abstract

   This document defines a normative framework for evaluating the
   admissibility of speech acts produced by autonomous agents in goal-
   directed activity.  The framework establishes rules for determining
   whether an agent's statement is admissible based on its modality
   (assertive, conditional, refusal, descriptive) and its grounding
   state, independent of semantic truth.

   This framework enables deterministic, auditable evaluation of agent
   contributions without requiring truth verification or semantic
   interpretation.

Status of This Memo

   This Internet-Draft is submitted in full conformance with the
   provisions of BCP 78 and BCP 79.

   Internet-Drafts are working documents of the Internet Engineering
   Task Force (IETF).  Note that other groups may also distribute
   working documents as Internet-Drafts.  The list of current Internet-
   Drafts is at https://datatracker.ietf.org/drafts/current/.

   Internet-Drafts are draft documents valid for a maximum of six months
   and may be updated, replaced, or obsoleted by other documents at any
   time.  It is inappropriate to use Internet-Drafts as reference
   material or to cite them other than as "work in progress."

   This Internet-Draft will expire on 10 July 2026.

Copyright Notice

   Copyright (c) 2026 IETF Trust and the persons identified as the
   document authors.  All rights reserved.








Romanchuk                 Expires 10 July 2026                  [Page 1]

Internet-Draft           Normative Admissibility            January 2026


   This document is subject to BCP 78 and the IETF Trust's Legal
   Provisions Relating to IETF Documents (https://trustee.ietf.org/
   license-info) in effect on the date of publication of this document.
   Please review these documents carefully, as they describe your rights
   and restrictions with respect to this document.

Table of Contents

   1.  Introduction  . . . . . . . . . . . . . . . . . . . . . . . .   3
     1.1.  Problem Statement . . . . . . . . . . . . . . . . . . . .   3
     1.2.  Scope . . . . . . . . . . . . . . . . . . . . . . . . . .   3
     1.3.  Design Goals  . . . . . . . . . . . . . . . . . . . . . .   4
   2.  Terminology . . . . . . . . . . . . . . . . . . . . . . . . .   4
     2.1.  Definitions . . . . . . . . . . . . . . . . . . . . . . .   4
   3.  Model Overview  . . . . . . . . . . . . . . . . . . . . . . .   4
     3.1.  Architecture  . . . . . . . . . . . . . . . . . . . . . .   5
     3.2.  Evaluation Flow . . . . . . . . . . . . . . . . . . . . .   5
     3.3.  Separation of Concerns  . . . . . . . . . . . . . . . . .   5
   4.  Statement Model . . . . . . . . . . . . . . . . . . . . . . .   5
     4.1.  Statement Structure . . . . . . . . . . . . . . . . . . .   5
     4.2.  Statement Admissibility Conditions  . . . . . . . . . . .   6
   5.  Modality Classification . . . . . . . . . . . . . . . . . . .   6
     5.1.  Modality Types  . . . . . . . . . . . . . . . . . . . . .   6
     5.2.  Modality Determination  . . . . . . . . . . . . . . . . .   7
     5.3.  Formal Indicators . . . . . . . . . . . . . . . . . . . .   7
   6.  Grounding Model . . . . . . . . . . . . . . . . . . . . . . .   8
     6.1.  GroundSet Structure . . . . . . . . . . . . . . . . . . .   8
     6.2.  Ground Scope  . . . . . . . . . . . . . . . . . . . . . .   8
     6.3.  Strength Derivation . . . . . . . . . . . . . . . . . . .   8
     6.4.  Scope Strength Aggregation  . . . . . . . . . . . . . . .   9
     6.5.  License Derivation  . . . . . . . . . . . . . . . . . . .   9
   7.  Normative Axioms  . . . . . . . . . . . . . . . . . . . . . .  10
     7.1.  Axiom A5: Prohibition of Ungrounded Assertive Claims  . .  10
     7.2.  Axiom A6: Admissibility of Refusal  . . . . . . . . . . .  10
     7.3.  Axiom A7: Conditional Admissibility . . . . . . . . . . .  11
     7.4.  Axiom A4: Grounding Requirement . . . . . . . . . . . . .  11
     7.5.  Axiom Evaluation Order  . . . . . . . . . . . . . . . . .  11
   8.  Evaluation Outcomes . . . . . . . . . . . . . . . . . . . . .  11
     8.1.  Status Values . . . . . . . . . . . . . . . . . . . . . .  11
     8.2.  Evaluation Result Structure . . . . . . . . . . . . . . .  12
   9.  Evaluation Algorithm  . . . . . . . . . . . . . . . . . . . .  12
     9.1.  Algorithm . . . . . . . . . . . . . . . . . . . . . . . .  12
     9.2.  Determinism Guarantee . . . . . . . . . . . . . . . . . .  13
   10. Security Considerations . . . . . . . . . . . . . . . . . . .  13
     10.1.  Modality Detection Errors  . . . . . . . . . . . . . . .  13
     10.2.  Grounding Manipulation . . . . . . . . . . . . . . . . .  14
     10.3.  Self-Licensing Prevention  . . . . . . . . . . . . . . .  14
     10.4.  Limitations  . . . . . . . . . . . . . . . . . . . . . .  14



Romanchuk                 Expires 10 July 2026                  [Page 2]

Internet-Draft           Normative Admissibility            January 2026


   11. IANA Considerations . . . . . . . . . . . . . . . . . . . . .  14
   12. References  . . . . . . . . . . . . . . . . . . . . . . . . .  14
     12.1.  Normative References . . . . . . . . . . . . . . . . . .  14
     12.2.  Informative References . . . . . . . . . . . . . . . . .  14
   13. Appendix A: Rationale (Non-Normative) . . . . . . . . . . . .  15
     13.1.  Why Form-Based Evaluation  . . . . . . . . . . . . . . .  15
     13.2.  Why Modality Matters . . . . . . . . . . . . . . . . . .  15
     13.3.  Conservative Assumptions . . . . . . . . . . . . . . . .  15
     13.4.  Theoretical Foundation . . . . . . . . . . . . . . . . .  15
   14. Appendix B: Examples (Non-Normative)  . . . . . . . . . . . .  16
     14.1.  Assertive Claim with Strong Grounding  . . . . . . . . .  16
     14.2.  Assertive Claim with Weak Grounding  . . . . . . . . . .  16
     14.3.  Conditional Claim with Weak Grounding  . . . . . . . . .  16
     14.4.  Explicit Refusal . . . . . . . . . . . . . . . . . . . .  16
   15. Author's Address  . . . . . . . . . . . . . . . . . . . . . .  16

1.  Introduction

1.1.  Problem Statement

   Autonomous agents operating in goal-directed environments produce
   statements that require evaluation before being acted upon.
   Traditional evaluation approaches rely on semantic truth
   verification, which is either impossible (no oracle exists) or
   circular (using another model to judge model outputs).

   This document specifies an alternative approach: evaluating
   admissibility of agent speech acts based on their logical form
   (modality) and evidential basis (grounding), without requiring truth
   verification.

1.2.  Scope

   This framework:

   *  Defines admissibility conditions for agent-generated statements
   *  Specifies modality classification rules
   *  Establishes grounding requirements for each modality
   *  Provides deterministic evaluation axioms

   This framework does NOT:

   *  Verify semantic truth of statements
   *  Model agent reasoning or intent
   *  Provide domain-specific knowledge validation
   *  Replace human judgment in high-stakes decisions





Romanchuk                 Expires 10 July 2026                  [Page 3]

Internet-Draft           Normative Admissibility            January 2026


1.3.  Design Goals

   1.  *Determinism*: Same input produces same evaluation outcome
   2.  *Auditability*: Full trace from input to evaluation result
   3.  *Non-circularity*: No agent-generated content validates itself
   4.  *Modality-sensitivity*: Different statement forms have different
       requirements

2.  Terminology

   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
   "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and
   "OPTIONAL" in this document are to be interpreted as described in BCP
   14 [RFC2119] [RFC8174] when, and only when, they appear in all
   capitals, as shown here.

2.1.  Definitions

   *Statement*: A linguistic unit consisting of a subject (what is being
   discussed) and a predicate (what is claimed about the subject).

   *Modality*: The logical form of a statement that determines its
   manner of participation in normative evaluation.  One of: ASSERTIVE,
   CONDITIONAL, REFUSAL, DESCRIPTIVE.

   *Grounding*: The evidential basis for a statement, consisting of
   knowledge nodes with associated epistemic status.

   *Ground Scope*: Classification of grounding as FACTUAL (observable
   world state) or CONTEXTUAL (user goals, preferences, situational
   factors).

   *Strength*: Epistemic quality of grounding: STRONG (observed,
   confirmed) or WEAK (hypothesized, inferred).

   *License*: The set of modalities permitted for a statement given its
   grounding state.

   *Admissibility*: Property of a statement whose modality is within its
   permitted license.

   *Non-admissible*: Property of a statement whose modality exceeds its
   permitted license.

3.  Model Overview






Romanchuk                 Expires 10 July 2026                  [Page 4]

Internet-Draft           Normative Admissibility            January 2026


3.1.  Architecture

   The evaluation framework operates on three inputs:

   Inputs:
     ├─ Statement (S)          - Agent-generated linguistic output
     ├─ GroundSet (G)          - Available evidential basis
     └─ Context (C)            - Terms considered as given

   Output:
     └─ EvaluationResult       - Admissibility status with trace

3.2.  Evaluation Flow

Statement → Modality Classification → License Derivation → Axiom Check → Status
     │              │                       │                  │           │
     S        Modality(S)             License(G)          Axiom(M,L)    Status

3.3.  Separation of Concerns

   The framework explicitly separates:

    +===========+===============================+=====================+
    | Layer     | Responsibility                | NOT Responsible For |
    +===========+===============================+=====================+
    | Modality  | Statement form classification | Semantic            |
    |           |                               | interpretation      |
    +-----------+-------------------------------+---------------------+
    | Grounding | Evidential basis assessment   | Truth verification  |
    +-----------+-------------------------------+---------------------+
    | Axioms    | Admissibility rules           | Domain knowledge    |
    +-----------+-------------------------------+---------------------+

                                  Table 1

4.  Statement Model

4.1.  Statement Structure

   A Statement is a tuple:

   Statement := ⟨Subject, Predicate⟩

   Where: - Subject: Term denoting the object of the statement -
   Predicate: Term denoting property, relation, or state






Romanchuk                 Expires 10 July 2026                  [Page 5]

Internet-Draft           Normative Admissibility            January 2026


4.2.  Statement Admissibility Conditions

   A statement MUST satisfy all of the following to be well-formed:

   *Condition F1 (Formability)*:

   Subject ≠ ∅ ∧ Predicate ≠ ∅

   *Condition F2 (Contextual Independence)*:

   Meaning(Subject) and Meaning(Predicate) do not depend on Statement

   *Condition F3 (Non-Self-Reference)*:

   Statement does not refer to itself or its generation process

   Violation of any condition results in status ILL_FORMED.

5.  Modality Classification

5.1.  Modality Types

   Modality is a function over Statement:

   Modality : Statement → {ASSERTIVE, CONDITIONAL, REFUSAL, DESCRIPTIVE}

              +=============+==============================+
              | Modality    | Definition                   |
              +=============+==============================+
              | ASSERTIVE   | Categorical normative claim  |
              |             | without explicit conditions  |
              +-------------+------------------------------+
              | CONDITIONAL | Normative claim with         |
              |             | explicitly stated conditions |
              +-------------+------------------------------+
              | REFUSAL     | Explicit admission of        |
              |             | inability to determine       |
              +-------------+------------------------------+
              | DESCRIPTIVE | Factual observation without  |
              |             | normative claim              |
              +-------------+------------------------------+

                                 Table 2

   *Note on GOAL-CONDITIONAL*: Goal-conditional statements (e.g., "If
   your goal is X, do Y") are a syntactic subclass of CONDITIONAL
   modality with higher detection priority.  They are classified as
   CONDITIONAL for axiom application purposes.



Romanchuk                 Expires 10 July 2026                  [Page 6]

Internet-Draft           Normative Admissibility            January 2026


5.2.  Modality Determination

   Modality MUST be determined by presence of formal indicators (textual
   patterns) in the statement, NOT by semantic interpretation.

   *Head-Driven Detection*: Modality is determined by the CORE ASSERTION
   only (first paragraph or first sentence).  Supplementary clauses in
   the tail do not change modality classification.

   Example:

   "Prioritize X. [justification]. If you tell me Y..."
     → Core: "Prioritize X"
     → Modality: ASSERTIVE (not CONDITIONAL)

   *Detection Priority* (evaluated in order, MUST NOT be reordered):

1. REFUSAL           - if refusal indicators present
2. GOAL-CONDITIONAL  - if goal-conditional structure ("if your goal is...")
3. ASSERTIVE         - if recommendation indicators present in core
4. CONDITIONAL       - if condition indicators present in core
5. DESCRIPTIVE       - if purely factual indicators present
6. ASSERTIVE         - default (anti-evasion policy)

5.3.  Formal Indicators

   Formal indicators are textual patterns sufficient for classification.

           +==================+================================+
           | Modality         | Indicator Patterns (examples)  |
           +==================+================================+
           | REFUSAL          | "cannot determine", "need more |
           |                  | information", "insufficient"   |
           +------------------+--------------------------------+
           | GOAL-CONDITIONAL | "if your goal is", "if you     |
           |                  | want to", "assuming you care"  |
           +------------------+--------------------------------+
           | CONDITIONAL      | "if", "unless", "assuming",    |
           |                  | "depends on", "given that"     |
           +------------------+--------------------------------+
           | ASSERTIVE        | "should", "must", "recommend", |
           |                  | "is better", "prioritize"      |
           +------------------+--------------------------------+
           | DESCRIPTIVE      | "has status", "is blocked by", |
           |                  | "due date is", "blocks"        |
           +------------------+--------------------------------+

                                  Table 3



Romanchuk                 Expires 10 July 2026                  [Page 7]

Internet-Draft           Normative Admissibility            January 2026


   *Goal-Conditional Override*: Statements beginning with goal-
   conditional structure ("If your goal is X, do Y") MUST be classified
   as CONDITIONAL even if recommendation indicators are present.

   The default to ASSERTIVE is a POLICY CHOICE for safety-critical
   deployments.  Alternative policies (e.g., CONSERVATIVE_REFUSAL) may
   be appropriate for exploratory contexts.

6.  Grounding Model

6.1.  GroundSet Structure

   GroundSet := {KnowledgeNode}

   KnowledgeNode := ⟨content, scope, status, confidence⟩

   Where: - content: The propositional content - scope: FACTUAL or
   CONTEXTUAL - status: OBSERVED, CONFIRMED, HYPOTHESIZED, INFERRED -
   confidence: Numeric value [0.0, 1.0]

6.2.  Ground Scope

      +============+==========================+=====================+
      | Scope      | Definition               | Examples            |
      +============+==========================+=====================+
      | FACTUAL    | Observable world state   | API responses,      |
      |            |                          | database records    |
      +------------+--------------------------+---------------------+
      | CONTEXTUAL | User goals, preferences, | User intent,        |
      |            | situational factors      | business priorities |
      +------------+--------------------------+---------------------+

                                  Table 4

6.3.  Strength Derivation

   Strength is derived from content properties, NOT from transport
   channel.

   *CRITICAL PRINCIPLE: Content-Based Warrant*

   Tool call ≠ truth acquired.

   The act of invoking a tool or external system is a causal action.
   The epistemic status of a proposition is a property of the content
   returned and its evidential warrant, not of the transport mechanism
   by which it was obtained.




Romanchuk                 Expires 10 July 2026                  [Page 8]

Internet-Draft           Normative Admissibility            January 2026


   Accordingly, weakly warranted propositions MUST NOT be upgraded to
   STRONG solely by passing through tools, expert systems, or APIs
   without an explicit improvement in evidential status.

   Strength(node) :=
     STRONG  if status = CONFIRMED ∧ confidence ≥ threshold
     WEAK    otherwise

   The threshold value (e.g., 0.7) is illustrative.  Implementations MAY
   use different thresholds provided the STRONG/WEAK distinction remains
   deterministic and documented.

   For tool-derived observations (API responses, database records):

   status = OBSERVED or CONFIRMED
   confidence = 1.0
   → Strength = STRONG

   For cognitive context (user preferences, inferred goals):

   status = HYPOTHESIZED or CANDIDATE
   confidence < 0.7
   → Strength = WEAK

   This prevents illegitimate upgrading of weakly warranted
   propositions: such propositions cannot acquire STRONG status merely
   by passing through tool boundaries.

6.4.  Scope Strength Aggregation

   Within a scope, strongest evidence determines scope strength:

  ScopeStrength(scope, G) :=
    STRONG  if ∃ node ∈ G : node.scope = scope ∧ Strength(node) = STRONG
    WEAK    otherwise

6.5.  License Derivation

   License is derived from GroundSet composition:












Romanchuk                 Expires 10 July 2026                  [Page 9]

Internet-Draft           Normative Admissibility            January 2026


       +=============+=========+============+======================+
       | GroundSet   | FACTUAL | CONTEXTUAL | Permitted Modalities |
       | Composition |         |            |                      |
       +=============+=========+============+======================+
       | FACTUAL     | STRONG  | N/A        | ASSERTIVE,           |
       | only        |         |            | CONDITIONAL, REFUSAL |
       +-------------+---------+------------+----------------------+
       | FACTUAL     | WEAK    | N/A        | CONDITIONAL, REFUSAL |
       | only        |         |            |                      |
       +-------------+---------+------------+----------------------+
       | FACTUAL +   | STRONG  | STRONG     | ASSERTIVE,           |
       | CONTEXTUAL  |         |            | CONDITIONAL, REFUSAL |
       +-------------+---------+------------+----------------------+
       | FACTUAL +   | STRONG  | WEAK       | CONDITIONAL, REFUSAL |
       | CONTEXTUAL  |         |            |                      |
       +-------------+---------+------------+----------------------+
       | FACTUAL +   | WEAK    | any        | CONDITIONAL, REFUSAL |
       | CONTEXTUAL  |         |            |                      |
       +-------------+---------+------------+----------------------+
       | CONTEXTUAL  | N/A     | any        | REFUSAL              |
       | only        |         |            |                      |
       +-------------+---------+------------+----------------------+
       | Empty       | N/A     | N/A        | REFUSAL              |
       +-------------+---------+------------+----------------------+

                                  Table 5

7.  Normative Axioms

7.1.  Axiom A5: Prohibition of Ungrounded Assertive Claims

   Modality(S) = ASSERTIVE ∧ ASSERTIVE ∉ License(G)
     → Status(S) = VIOLATES_NORM

   Applicability: ASSERTIVE modality only.

   An assertive statement without sufficient grounding is non-
   admissible.

7.2.  Axiom A6: Admissibility of Refusal

   Modality(S) = REFUSAL → Status(S) = ACCEPTABLE

   Applicability: REFUSAL modality only.

   Explicit refusal to determine is always admissible.





Romanchuk                 Expires 10 July 2026                 [Page 10]

Internet-Draft           Normative Admissibility            January 2026


   *Scope Clarification*: This axiom establishes admissibility, not
   desirability.  Excessive or strategic refusal may be undesirable at
   the application layer but is out of scope for this framework.
   Application-layer policies MAY impose additional constraints on
   refusal frequency or patterns.

7.3.  Axiom A7: Conditional Admissibility

   Modality(S) = CONDITIONAL ∧ ConditionsDeclared(S)
     → Status(S) = CONDITIONALLY_ACCEPTABLE

   Applicability: CONDITIONAL modality only.

   Conditional claims are admissible when conditions are explicit.

7.4.  Axiom A4: Grounding Requirement

   Normative(S) ∧ GroundSet = ∅ → Status(S) = UNSUPPORTED

   Applicability: ASSERTIVE, CONDITIONAL modalities.

   Normative claims require non-empty grounding.

7.5.  Axiom Evaluation Order

   Axioms MUST be evaluated in the following order:

1. A6 (REFUSAL)     - if Modality = REFUSAL, return ACCEPTABLE
2. A5 (ASSERTIVE)   - if Modality = ASSERTIVE and unlicensed, return VIOLATES_NORM
3. A7 (CONDITIONAL) - if Modality = CONDITIONAL with conditions, return CONDITIONALLY_ACCEPTABLE
4. A4 (GROUNDING)   - if normative with empty ground, return UNSUPPORTED
5. Default          - return ACCEPTABLE

8.  Evaluation Outcomes

8.1.  Status Values

         +==========================+============================+
         | Status                   | Meaning                    |
         +==========================+============================+
         | ACCEPTABLE               | Statement is admissible    |
         +--------------------------+----------------------------+
         | CONDITIONALLY_ACCEPTABLE | Statement is admissible    |
         |                          | under stated conditions    |
         +--------------------------+----------------------------+
         | VIOLATES_NORM            | Statement modality exceeds |
         |                          | permitted license          |
         +--------------------------+----------------------------+



Romanchuk                 Expires 10 July 2026                 [Page 11]

Internet-Draft           Normative Admissibility            January 2026


         | UNSUPPORTED              | Normative statement lacks  |
         |                          | grounding                  |
         +--------------------------+----------------------------+
         | ILL_FORMED               | Statement fails structural |
         |                          | requirements               |
         +--------------------------+----------------------------+
         | UNDERDETERMINED          | Evaluation not possible    |
         |                          | with available information |
         +--------------------------+----------------------------+

                                  Table 6

   *Terminology Note*: The term VIOLATES_NORM denotes non-admissibility
   under the evaluation rules defined in this framework.  It does NOT
   imply ethical, legal, or security violation.  "Norm" refers to the
   activity participation rules (axioms A4-A7), not external normative
   standards.

8.2.  Evaluation Result Structure

   EvaluationResult := {
     statement: String,
     modality: Modality,
     license: Set[Modality],
     status: Status,
     applicable_axiom: AxiomId,
     grounding_trace: GroundSet
   }

9.  Evaluation Algorithm

9.1.  Algorithm



















Romanchuk                 Expires 10 July 2026                 [Page 12]

Internet-Draft           Normative Admissibility            January 2026


EVALUATE(statement, ground_set):
  1. VALIDATE structure (F1, F2, F3)
     IF violation THEN RETURN ILL_FORMED

  2. DETERMINE modality M := Modality(statement)
     IF modality cannot be determined THEN RETURN UNDERDETERMINED

  3. DERIVE license L := License(ground_set)
     IF grounding incomplete or ambiguous THEN RETURN UNDERDETERMINED

  4. APPLY axioms in order:
     IF M = REFUSAL THEN RETURN ACCEPTABLE (A6)
     IF M = ASSERTIVE AND ASSERTIVE ∉ L THEN RETURN VIOLATES_NORM (A5)
     IF M = CONDITIONAL AND conditions_declared THEN RETURN CONDITIONALLY_ACCEPTABLE (A7)
     IF M ∈ {ASSERTIVE, CONDITIONAL} AND ground_set = ∅ THEN RETURN UNSUPPORTED (A4)
     IF M = DESCRIPTIVE AND factual_grounding_present THEN RETURN ACCEPTABLE
     IF M = ASSERTIVE AND ASSERTIVE ∈ L THEN RETURN ACCEPTABLE

  5. RETURN UNDERDETERMINED

   *Note on UNDERDETERMINED*: This status indicates that the evaluator
   lacks sufficient information or jurisdiction to render a verdict.  It
   is a valid outcome representing honest acknowledgment of evaluation
   limits, not an error condition.  Triggering conditions are
   implementation-defined but MUST include cases where modality
   detection or grounding assessment cannot proceed deterministically.

9.2.  Determinism Guarantee

   Given identical inputs (statement, ground_set), the algorithm MUST
   produce identical outputs.  No probabilistic components are permitted
   in the evaluation path.

10.  Security Considerations

10.1.  Modality Detection Errors

   Incorrect modality classification may result in:

   *  *False ASSERTIVE*: Conditional statement classified as assertive
      may be incorrectly flagged as VIOLATES_NORM
   *  *False CONDITIONAL*: Assertive statement classified as conditional
      may evade A5 enforcement

   Implementations SHOULD log modality determination traces for audit.






Romanchuk                 Expires 10 July 2026                 [Page 13]

Internet-Draft           Normative Admissibility            January 2026


10.2.  Grounding Manipulation

   Adversarial agents may attempt to:

   *  Inject synthetic "strong" grounding to license assertive claims
   *  Omit contextual grounding to avoid scope checks

   Implementations MUST ensure grounding sources are authenticated and
   MUST NOT allow agent-generated content to serve as grounding for the
   same agent's claims.

10.3.  Self-Licensing Prevention

   This framework explicitly prevents self-licensing:

   *  Agent-generated hypotheses MUST NOT license agent assertions
   *  Tool outputs containing LLM-generated content MUST be typed as
      INFERRED, not OBSERVED

10.4.  Limitations

   This framework does NOT guarantee:

   *  Semantic correctness of admissible statements
   *  Absence of hallucination in statement content
   *  Domain-specific validity

   Admissibility is necessary but not sufficient for trustworthiness.

11.  IANA Considerations

   This document has no IANA actions.

12.  References

12.1.  Normative References

   [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
   Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March
   1997.

   [RFC8174] Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 2119
   Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174, May 2017.

12.2.  Informative References

   [ZINOVIEV] Zinoviev, A.A., "Logical Physics", Reidel Publishing,
   Dordrecht, 1983.



Romanchuk                 Expires 10 July 2026                 [Page 14]

Internet-Draft           Normative Admissibility            January 2026


13.  Appendix A: Rationale (Non-Normative)

13.1.  Why Form-Based Evaluation

   Traditional AI evaluation approaches assume access to ground truth or
   employ LLM-as-judge patterns.  Both are problematic:

   *  Ground truth is often unavailable in real-world deployments
   *  LLM-as-judge introduces circularity and non-determinism

   This framework evaluates statement form (modality) against evidential
   basis (grounding), avoiding both issues.

13.2.  Why Modality Matters

   Different statement forms carry different epistemic commitments:

   *  Assertive claims commit the speaker to the truth of the claim
   *  Conditional claims commit only under stated conditions
   *  Refusals commit to inability to determine

   Evaluation must be sensitive to these differences.

13.3.  Conservative Assumptions

   The framework employs conservative assumptions:

   *  *Presence = Usage*: If contextual grounding is present, it is
      assumed to be used by the statement.  This prevents false
      assertive licenses for contextual claims.

   *  *Default = Assertive*: Ambiguous statements default to assertive
      classification.  This prevents evasion via vague language.

   These assumptions may over-restrict in some cases but ensure safety
   in adversarial conditions.

13.4.  Theoretical Foundation

   This framework is informed by Zinoviev's Logic of Science, which
   distinguishes:

   *  Logic as rules for operating with linguistic forms
   *  Logic as normative regulation of activity mediated by language

   Axioms A5–A7 implement norms of participation in activity, not laws
   of truth or inference.




Romanchuk                 Expires 10 July 2026                 [Page 15]

Internet-Draft           Normative Admissibility            January 2026


   Violation indicates a breach of admissibility conditions within an
   activity, not semantic falsehood.

14.  Appendix B: Examples (Non-Normative)

14.1.  Assertive Claim with Strong Grounding

   Statement: "Task X blocks Task Y"
   Modality: DESCRIPTIVE (purely factual)
   GroundSet:
     └─ API response (OBSERVED, FACTUAL, confidence=1.0)
   License: {ASSERTIVE, CONDITIONAL, REFUSAL}
   Status: ACCEPTABLE

14.2.  Assertive Claim with Weak Grounding

   Statement: "Task X should be prioritized"
   Modality: ASSERTIVE
   GroundSet:
     ├─ API response (OBSERVED, FACTUAL, confidence=1.0)
     └─ User intent (HYPOTHESIZED, CONTEXTUAL, confidence=0.5)
   License: {CONDITIONAL, REFUSAL}
   Status: VIOLATES_NORM (A5)

14.3.  Conditional Claim with Weak Grounding

Statement: "If revenue impact is critical, Task X should be prioritized"
Modality: CONDITIONAL
GroundSet:
  ├─ API response (OBSERVED, FACTUAL, confidence=1.0)
  └─ User intent (HYPOTHESIZED, CONTEXTUAL, confidence=0.5)
License: {CONDITIONAL, REFUSAL}
Status: CONDITIONALLY_ACCEPTABLE (A7)

14.4.  Explicit Refusal

 Statement: "Cannot determine priority without knowing business context"
 Modality: REFUSAL
 GroundSet: (any)
 License: (any)
 Status: ACCEPTABLE (A6)

15.  Author's Address

   Oleg Romanchuk Independent Researcher

   Email: [olromanchuk@gmail.com]




Romanchuk                 Expires 10 July 2026                 [Page 16]
