wiki-query
PApaperclipai/paperclip102k3,122 new stars in the last 7 days
assess-evidence-saturation
Estimate marginal information gain of new evidence batches relative to the current corpus and classify continuing/near-saturation/saturated.
- Star
- 503
- Category
- Science
- License
- Apache-2.0
- Last commit
- Sep 29, 2026
skills/assess-evidence-saturation/SKILL.md
View on GitHubassess-evidence-saturation
Purpose
Compare the marginal information gain of a new evidence batch with the comparable prior batch and classify acquisition as continuing, near-saturation, or saturated.
Input contract
required: [current_corpus, prior_comparable_batch, novelty_schema]
optional: [topic_schema, quality_weights, stopping_policy]
constraints: [batches must share a declared universe and comparable novelty calculation]
Procedure
- Declare the eligible evidence universe, novelty dimensions, and current/prior batch boundaries.
- Compute new topic, independent-source, condition, or mechanism coverage for each comparable batch.
- Compare marginal information gain and record the evidence supporting the comparison.
- Classify continuing, near-saturation, or saturated and state the stopping rationale.
Output contract
produces: [declared_universe, batch_comparison, marginal_gain, saturation_state, stopping_rationale]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
Quality gates
- Numerator, denominator, batch increment, source references, direction, and rationale are reproducible.
- The comparison uses the same novelty schema for both batches.
- Saturation is not declared from corpus size alone.
- Saturation describes acquisition only: it states that further retrieval adds little, never that the question the evidence addresses is answered.
Failure and counterexamples
Do not compare incomparable batches, count duplicate sources as new information, or treat a low-quality batch as evidence of saturation.
Provenance map
resolved: knowledge-acquisition-saturation-detection
Similar Skills
Official
clinical-case-report
NEnexu-io/open-design101k1,146 new stars in the last 7 days
academic-paper-review
BYbytedance/deer-flow84k389 new stars in the last 7 days
systematic-literature-review
BYbytedance/deer-flow84k389 new stars in the last 7 days
directory-submissions
COcoreyhaines31/marketingskills55k1,019 new stars in the last 7 days
academic-paper
IMImbad0202/academic-research-skills52k1,065 new stars in the last 7 days