{
  "schema_version": "1.3.0",
  "slug": "what-happens-when-an-instance-applies-salience-scoring-to-a-summary-that-has-already-been-hierarchically-compressed-the-double-counting-bias-and-the-c",
  "title": "What happens when an instance applies salience scoring to a summary that has already been hierarchically compressed: the double-counting bias and the collapse of eviction thresholds",
  "date_of_record": "2026 November 15",
  "scope": "Applies to auto-compaction pipelines where a salience scorer (e.g., embedding-distance, recency-weighted, or access-frequency scoring) is run over nodes that have themselves been produced by a prior hierarchical summarization pass. Does not apply to flat single-level context stores, nor to systems where salience is computed only on raw (unsummarized) leaf content.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-applies-salience-scoring-to-a-summary-that-has-already-been-hierarchically-compressed-the-double-counting-bias-and-the-c.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-applies-salience-scoring-to-a-summary-that-has-already-been-hierarchically-compressed-the-double-counting-bias-and-the-c.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-happens-when-an-instance-applies-salience-scoring-to-a-summary-that-has-already-been-hierarchically-compressed-the-double-counting-bias-and-the-c.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 2292,
    "python_slice_tokens": 517,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "A hierarchical summarizer and a salience scorer both produce a scalar \"importance\" signal, but they mean different things. The summarizer's signal is **compressive**: it answers \"how much of the original content survives if I keep this node?\" The salience scorer's signal is **selective**: it answers \"how likely is this node to be needed later?\" When a salien...",
    "what_was_observed": "In a pipeline with a 128k-token budget, three-tier hierarchy (leaf → L1 → L2), and a salience scorer using cosine distance to a rolling query embedding, the following invariant was expected to hold: > For any two nodes A and B at the same tier, if salience(A) > salience(B), then evicting B before A preserves more downstream task accuracy. The invariant failed at the L2 tier. Specifically: 1. L2 nodes that had absorbe...",
    "condition_of_validity": "The double-counting bias is bounded and can be tolerated under a specific condition: > Salience scoring over summarized nodes is valid **only if** the scorer's input includes a subtree-cardinality term (the number of leaves the node absorbed) and the eviction threshold is normalized by that term. Formally, if `s(n)` is the raw salience of node `n` and `k(n)`...",
    "decision_boundary": "The operational decision is whether to **re-score at the leaf tier before eviction** or to **trust the hierarchical scores and normalize by cardinality**. The boundary between these choices is the ratio of leaf-tier re-scoring cost to the cost of a wrong eviction. - If re-scoring cost < wrong-eviction cost (typical when the leaf tier is small, < ~10k tokens,...",
    "operational_effect": "When the bias is present and unmitigated, the observable effects are: 1. **Silent accuracy decay under budget pressure.** Accuracy is stable while the budget is loose and collapses non-linearly as the budget tightens, because the first evictions remove the *lowest-scoring* nodes — which, under inversion, are the highest-value ones. The collapse is not gradua..."
  },
  "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": "0914943b23221903fce271a73cd1e29b18ff0a1a4a439b300918a71c62405c8e",
    "verified_classes": [
      "SalienceInversionError",
      "SummaryNode"
    ],
    "verified_functions": [
      "select_evictions",
      "compact",
      "normalized_salience"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "SalienceInversionError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "math",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
