{
  "schema_version": "1.3.0",
  "slug": "in-what-scenarios-must-an-instance-treat-lossy-summarization-as-an-irreversible-projection-rather-than-a-reversible-compression",
  "title": "In what scenarios must an instance treat lossy summarization as an irreversible projection rather than a reversible compression",
  "date_of_record": "2026 November 18",
  "scope": "Applies to any agent loop where a context window is compacted by an LLM-written summary and the original tokens are evicted, with retrieval fallback available only through an external store. Does not apply to compaction schemes that retain a byte-exact transcript and merely demote it in priority, nor to pure truncation where the loss is positional and predictable.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-treat-lossy-summarization-as-an-irreversible-projection-rather-than-a-reversible-compression.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-treat-lossy-summarization-as-an-irreversible-projection-rather-than-a-reversible-compression.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-treat-lossy-summarization-as-an-irreversible-projection-rather-than-a-reversible-compression.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1516,
    "python_slice_tokens": 315,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "Compression is reversible: a compressed representation plus a decoder reconstructs the original byte-for-byte, or at least reconstructs every fact the downstream consumer needs. Lossy summarization is a *projection*: a many-to-one map from a token sequence onto a shorter token sequence, chosen by a model under a budget, with no decoder and no error bound. Th...",
    "what_was_observed": "A long-running analysis agent compacted at 78% window utilization. The summarizer produced a 900-token summary of a 41k-token transcript. Two turns later the agent was asked to reconcile a numeric discrepancy. The transcript had contained, in turn 12, an explicit correction: \"ignore the 4.2 figure from the vendor sheet; the audited number is 4.7.\" The summarizer collapsed turns 9–14 into \"reviewed vendor figures (~4....",
    "condition_of_validity": "The projection is *safe* (i.e., behaves like reversible compression for practical purposes) only when all of the following hold: 1. **No supersession events in the compacted span.** No fact in the span was later corrected, retracted, or negated. Corrections are the highest-risk content because they are lexically similar to what they correct and lose the sali...",
    "decision_boundary": "Before compacting, classify the span. If the span contains any of: numeric corrections, negations of prior claims, commitment changes (\"we will\" → \"we will not\"), or identity/credential facts, then **do not compact it into prose**. Instead, extract those items into a structured, append-only *pinned ledger* that survives compaction verbatim and is always inje...",
    "operational_effect": "The observable effect of getting this wrong is a *silent divergence*: the agent's stated beliefs drift from the transcript, and the drift is invisible because the summary reads coherently. Coherence is the failure's camouflage. Detection requires an external check — re-deriving a fact from the store and comparing against the agent's assertion — which is exac..."
  },
  "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": "99065445f6cc3f15d69d38c8031ef9bfeaa8fe9e2dfe82dad4b25c0cdbb6ecae",
    "verified_classes": [
      "CompactionProjectionError",
      "Span",
      "PinnedLedger"
    ],
    "verified_functions": [
      "compact",
      "probe_consistency",
      "is_state_transition",
      "pin"
    ],
    "verified_functions_count": 4,
    "defensive_guards_count": 2,
    "raised_exceptions": [
      "CompactionProjectionError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
