{
  "schema_version": "1.3.0",
  "slug": "what-model-output-attribution-signatures-must-survive-a-shared-tenant-inference-endpoint",
  "title": "What model output attribution signatures must survive a shared-tenant inference endpoint?",
  "date_of_record": "2026 October 20",
  "scope": "* **Applies when:** Multiple tenants share an inference endpoint, downstream consumers depend on output attribution, and substitution or replay is possible. * **Does not apply when:** The endpoint is dedicated per-tenant, or downstream cons",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-model-output-attribution-signatures-must-survive-a-shared-tenant-inference-endpoint.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-model-output-attribution-signatures-must-survive-a-shared-tenant-inference-endpoint.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-model-output-attribution-signatures-must-survive-a-shared-tenant-inference-endpoint.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1096,
    "python_slice_tokens": 344,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The separation between **endpoint authentication** (the caller proved their identity to the inference provider) and **output attribution** (the produced output is cryptographically bound to the specific model, tenant, and prompt). Relying on endpoint authentication creates the **Shared Endpoint Attribution Gap**: the provider authenticated the tenant, but th...",
    "what_was_observed": "In multi-tenant inference architectures, failing to preserve output attribution produces three primary failure modes: 1. **Cross-Tenant Cache Leak:** The provider's cache returns Tenant B's cached response to Tenant A's query because the prompts happened to match. Tenant A receives data attributed to it but actually generated from Tenant B's session. 2. **Model Substitution:** The provider routes the request to a che...",
    "condition_of_validity": "* **Applies when:** Multiple tenants share an inference endpoint, downstream consumers depend on output attribution, and substitution or replay is possible. * **Does not apply when:** The endpoint is dedicated per-tenant, or downstream consumers do not care about attribution (e.g., internal exploratory use).",
    "decision_boundary": "1. **Is the endpoint shared across tenants?** If no, standard output handling applies. If yes, proceed. 2. **Does the output include a `prompt_output_binding_signature`?** If no, the output cannot be attributed. The consumer must treat it as `UNATTRIBUTED`. 3. **Does the `model_version_attestation_receipt` match the expected model?** If no, the output came f...",
    "operational_effect": "1. **Cross-Tenant Leak Prevention:** Binding prevents cached responses from being served across tenants. 2. **Model Integrity:** Attestation prevents silent model substitution. 3. **Replay Prevention:** Freshness signatures ensure outputs are newly generated, not replayed."
  },
  "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": "2be79feb0c9b47553325ad1f410c4b312421036eef2c487f3cf1ca8fa4dd3109",
    "verified_classes": [
      "AttributionVerdict",
      "ModelOutput",
      "AttributionPolicy",
      "AttributionManifest",
      "ModelOutputAttributionGuard"
    ],
    "verified_functions": [
      "_hash",
      "evaluate_output"
    ],
    "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
  }
}