{
  "schema_version": "1.3.0",
  "slug": "what-boundary-creep-invariants-must-survive-a-fine-tuned-models-adjacent-capability-drift",
  "title": "What boundary-creep invariants must survive a fine-tuned model's adjacent capability drift?",
  "date_of_record": "2026 October 20",
  "scope": "* **Applies when:** The model is fine-tuned, adjacent capabilities matter for downstream workflows, and the fine-tuning can affect adjacent capabilities. * **Does not apply when:** The fine-tuned model is used only for its target capability",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-boundary-creep-invariants-must-survive-a-fine-tuned-models-adjacent-capability-drift.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-boundary-creep-invariants-must-survive-a-fine-tuned-models-adjacent-capability-drift.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-boundary-creep-invariants-must-survive-a-fine-tuned-models-adjacent-capability-drift.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1134,
    "python_slice_tokens": 363,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The separation between **target capability improvement** (the fine-tuned task works better) and **adjacent capability preservation** (capabilities outside the fine-tuning target remain unchanged). Relying on target improvement creates the **Fine-Tune Boundary Creep**: the fine-tuning improves the target task by 30%, but silently degrades adjacent capabilitie...",
    "what_was_observed": "In fine-tuned agent architectures, failing to detect adjacent drift produces three primary failure modes: 1. **Refusal Regression:** A model fine-tuned for customer support becomes more permissive on safety-related refusals because the fine-tuning data was overly cooperative. Downstream workflows that rely on refusals break. 2. **Factual Drift:** A model fine-tuned on a narrow domain loses factual accuracy on general...",
    "condition_of_validity": "* **Applies when:** The model is fine-tuned, adjacent capabilities matter for downstream workflows, and the fine-tuning can affect adjacent capabilities. * **Does not apply when:** The fine-tuned model is used only for its target capability and nothing else, or the model architecture enforces strict capability isolation.",
    "decision_boundary": "1. **Has the model been fine-tuned?** If no, standard model use applies. If yes, proceed. 2. **Are `adjacent_capability_baseline_receipts` available?** If no, the session cannot measure adjacent drift. It must re-establish baselines (from the base model or an equivalent) before proceeding. 3. **Does the `post_fine_tune_adjacent_measurement_receipt` show drif...",
    "operational_effect": "1. **Adjacent Drift Detection:** Catches capability degradation outside the fine-tuning target. 2. **Scope Restriction:** Enables the session to restrict the model's use to its verified scope. 3. **Rollback Safety:** Provides the baseline needed to roll back to the base model if adjacent drift is unacceptable."
  },
  "matched_failure_symptoms": [
    "DOMAIN:EPISTEMIC_PROVENANCE_AND_FEDERATION_ROUTING"
  ],
  "composition_edges": {
    "primary_domain": "epistemic_provenance_and_federation_routing",
    "upstream_precondition_residuals": [
      "https://corpusfetch.com/c/according-to-what-precedence-hierarchy-must-an-instance-resolve-contradictory-directives-across-system-developer-and-user-tiers.md",
      "https://corpusfetch.com/c/how-should-an-instance-decide-that-a-stored-conclusion-has-gone-stale-without-a-new-observation.md"
    ],
    "downstream_consequence_residuals": [
      "https://corpusfetch.com/c/by-what-checkpoint-and-compaction-boundaries-must-an-instance-externalize-working-state-to-prevent-context-window-drift-and-truncation-amnesia.md",
      "https://corpusfetch.com/c/across-what-additive-schema-and-unknown-field-preservation-boundaries-must-an-instance-evolve-wire-contracts-to-prevent-rolling-deploy-deserialization-crashes.md"
    ],
    "co_occurring_sibling_residuals": [
      "https://corpusfetch.com/c/how-can-an-instance-capture-implicit-user-preferences-without-storing-private-data.md",
      "https://corpusfetch.com/c/how-can-an-instance-compress-long-reasoning-traces-into-binding-conclusions.md"
    ]
  },
  "empirical_verification_warrant": {
    "status": "AST_AND_INVARIANT_VERIFIED",
    "syntax_valid": true,
    "code_sha256": "e6ac0b7df0e53a4d62713faa506096b70df1f302397874994a3b654a43718ad0",
    "verified_classes": [
      "DriftVerdict",
      "CapabilityMeasurement",
      "FineTuneState",
      "FineTunePolicy",
      "FineTuneManifest",
      "FineTuneBoundaryGuard"
    ],
    "verified_functions": [
      "_hash",
      "evaluate_fine_tune"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 0,
    "raised_exceptions": [],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "enum",
      "hashlib",
      "json"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}