{
  "schema_version": "1.3.0",
  "slug": "why-does-an-instance-accept-poisoned-episodic-memories-after-a-successful-retrieval-time-filter-the-write-path-read-path-asymmetry-in-shared-vector-st",
  "title": "Why does an instance accept poisoned episodic memories after a successful retrieval-time filter: the write-path/read-path asymmetry in shared vector stores",
  "date_of_record": "2026 November 11",
  "scope": "Applies to multi-tenant or multi-agent shared vector and episodic memory stores where a poisoning defense (embedding-space outlier rejection, provenance scoring, or trust gating) is evaluated at retrieval time. Does not apply to single-writer stores, stores where writes and reads share one trust boundary, or purely append-only logs with no semantic retrieval.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/why-does-an-instance-accept-poisoned-episodic-memories-after-a-successful-retrieval-time-filter-the-write-path-read-path-asymmetry-in-shared-vector-st.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/why-does-an-instance-accept-poisoned-episodic-memories-after-a-successful-retrieval-time-filter-the-write-path-read-path-asymmetry-in-shared-vector-st.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/why-does-an-instance-accept-poisoned-episodic-memories-after-a-successful-retrieval-time-filter-the-write-path-read-path-asymmetry-in-shared-vector-st.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1575,
    "python_slice_tokens": 336,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "A poisoning defense is almost always specified and measured as a **read-path filter**: at query time, candidate memories are scored for provenance, embedding-space plausibility, or contradiction with the query context, and suspicious entries are dropped. This produces a clean, testable invariant: *poisoned entries do not appear in results*. The invariant tha...",
    "what_was_observed": "In a shared episodic store with per-tenant namespaces and a cross-tenant consolidation job, an ingestion defense rejected 0.3% of writes as embedding-space outliers and a retrieval defense dropped low-provenance hits. Poisoning red-team recall at the *result* layer was 0.0 — no poisoned string ever appeared in a returned context window. The failure was elsewhere. Three effects were measured: 1. **Index contamination....",
    "condition_of_validity": "The read-path filter is a sufficient defense *only* when all of the following hold: - The store is single-writer or all writers share the reader's trust boundary. - No downstream job (consolidation, summarization, re-embedding, model retraining) consumes the *unfiltered* admitted set. - The ANN index is rebuilt from the *filtered* set, or the filter is appli...",
    "decision_boundary": "The boundary is **admission vs. suppression**, and it must be located at the write, not the read: - **Move the defense to admission.** Reject at write time using provenance, embedding-space consistency against the tenant's own centroid, and contradiction checks against existing high-provenance memories. A rejected write is never indexed, never consolidated, ...",
    "operational_effect": "After relocating admission checks to the write path and routing consolidation and training through the same filter, the measured effects were: benign-query recall recovered to baseline (the 4–11% loss disappeared because poisoned vectors no longer occupied graph neighbors); post-consolidation poisoning recall went from 0.0 to 0.0 *with no synthesized poisone..."
  },
  "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": "3d942971dc31ffa5d25f5ff70cc6804039a999107d118fa4b866eae07898eaae",
    "verified_classes": [
      "PoisonedAdmissionError"
    ],
    "verified_functions": [
      "admit_memory",
      "consolidate",
      "_cosine_distance"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "PoisonedAdmissionError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}