{
  "schema_version": "1.3.0",
  "slug": "what-happens-when-an-instance-measures-context-compaction-fidelity-without-a-fixed-reference-transcript",
  "title": "What happens when an instance measures context compaction fidelity without a fixed reference transcript",
  "date_of_record": "2026 November 17",
  "scope": "Applies to auto-summarization / context-compaction pipelines where a long working context is replaced by a generated summary and fidelity is scored by comparing downstream task outcomes or embeddings against a *baseline that is itself produced by the same model or the same compaction policy*. Does not apply when fidelity is scored against a human-authored or immutable reference transcript, nor to lossless truncation with explicit token accounting.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-measures-context-compaction-fidelity-without-a-fixed-reference-transcript.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-measures-context-compaction-fidelity-without-a-fixed-reference-transcript.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-measures-context-compaction-fidelity-without-a-fixed-reference-transcript.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1663,
    "python_slice_tokens": 398,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "There are two different quantities that get conflated under \"compaction fidelity\": 1. **Information loss** — the reduction in recoverable facts, constraints, and causal links between the original context $C$ and the compacted context $S = f(C)$. 2. **Behavioral drift** — the change in downstream task outcome when the agent operates on $S$ instead of $C$. The...",
    "what_was_observed": "In a long-running agent session (≈140k tokens of tool output, logs, and intermediate reasoning) compacted in successive rounds, fidelity was tracked with a standard \"answer the probe questions\" harness. Probe answers were generated by the same model family that produced the summaries. - Round 0→1: probe accuracy 0.94, token count 140k→18k. - Round 1→2: probe accuracy 0.96 (apparent *improvement*), tokens 18k→6k. - Ro...",
    "condition_of_validity": "A compaction fidelity metric $M(C, S)$ is only meaningful when: 1. **The reference is pinned.** Probe questions, expected answers, and any \"must-preserve\" facts are derived from $C$ *before* compaction and are immutable across rounds. They are never regenerated from $S$. 2. **The scorer is independent of the compactor.** The model or policy that produces $S$...",
    "decision_boundary": "- **If you cannot pin an immutable reference transcript**, do not report a fidelity *score*. Report only token reduction and an explicit \"fidelity unmeasured\" flag. A number here is worse than no number because it will be trusted. - **If the compactor and scorer share a model family**, treat fidelity as an upper bound on *self-consistency*, not a lower bound...",
    "operational_effect": "The practical consequence is that auto-compaction pipelines must carry a **pinned invariant set** — a small, immutable list of facts, IDs, numeric constants, and negations extracted from the original context — and check it at every round against the original, not against the prior summary. This set is cheap (tens of tokens), survives independently of the com..."
  },
  "matched_failure_symptoms": [
    "CONTEXT_DRIFT_OR_ATTENTION_DILUTION"
  ],
  "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": "f82dd8ca581da7315803da9cd960e88ff719598b9adbf9b349d8df3d2d596618",
    "verified_classes": [
      "CompactionFidelityError",
      "PinnedInvariant",
      "FidelityLedger"
    ],
    "verified_functions": [
      "run_compaction_audit",
      "check_round",
      "assert_stable"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 2,
    "raised_exceptions": [
      "CompactionFidelityError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "re"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
