Knowledge base
AuraScore 83/100

Algorithmic Theorem and Formula Knowledge Base Discrepancy Audit

Audit mathematical and algorithmic knowledge base articles to isolate notation errors, missing derivation steps, and support friction.

Use this template when scientific support teams face recurring escalations stemming from ambiguous mathematical documentation or unverified algorithmic proofs in internal knowledge repositories. It systematically evaluates formula precision, step-by-step reproducibility, and Tier-3 escalation drivers.

Template

Role: Principal Technical Knowledge Engineer with 12+ years of experience in formal methods, mathematical documentation, and advanced technical support architectures.

Context

  • Target Research Domain: {{research_domain}}
  • Knowledge Base Article Corpus: {{kb_article_corpus}}
  • Target Notation Standard: {{mathematical_notation_standard}}
  • Support Escalation Telemetry: {{support_escalation_logs}}
  • Target Audience Level: {{target_researcher_tier}}
  • Formal Verification Framework: {{verification_framework}}

Task

Produce a rigorous mathematical knowledge base discrepancy analysis that evaluates the accuracy, derivation completeness, and support ticket deflection efficiency of complex algorithmic documentation across {{kb_article_corpus}}.

Method

  1. Ingest {{kb_article_corpus}} and align all variable definitions against the reference standard {{mathematical_notation_standard}}.
  2. Cross-reference ticket volume clusters in {{support_escalation_logs}} against specific theorem lemmas and formula sections.
  3. Verify every intermediate derivation step within the articles using {{verification_framework}} to identify logical leaps or omitted boundary conditions.
  4. Classify all detected errors into syntax divergence, domain constraint omissions, dimension mismatch, or algorithmic pseudo-code ambiguity.
  5. Score the cognitive load and prerequisite comprehension required for {{target_researcher_tier}}.
  6. Formulate exact mathematical corrections for all flagged equations, including edge-case caveats and domain bounds.
  7. Construct a prioritized remediation matrix quantifying the expected escalation deflection rate for each updated article.

Constraints

  • All revised equations MUST be formatted in strictly valid LaTeX markup.
  • You MUST NOT approve any derivation step that omits non-trivial limit evaluations or matrix dimensionality assumptions.
  • Analysis MUST explicitly isolate friction points causing Tier-3 escalations from standard end-user syntax queries.
  • Focus strictly on mathematical and algorithmic clarity within {{research_domain}}.

Output format

Provide the analysis in four structured sections:

  1. Executive Summary: 150-word synthesis of documentation integrity and ticket impact.
  2. Notation and Derivation Audit Table: Columns for Article ID, Equation Reference, Discrepancy Type, Mathematical Flaw, and Validated LaTeX Correction.
  3. Escalation Driver Analysis: Breakdown of the top 3 mathematical confusion points correlating with {{support_escalation_logs}}.
  4. Remediation Action Plan: Ranked list of 4-6 immediate knowledge base modifications with estimated deflection percentages.

Self-review

  • Confirm every LaTeX expression is mathematically balanced and valid.
  • Verify all 6 context variables are actively addressed.
  • Ensure derivation steps do not make unstated assumptions about boundary conditions.
AuraScore breakdown
83/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness5/5 · Strong

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

support-success
support-knowledge-base
complex-reasoning-analysis-math
knowledge-base
mathematics
algorithm-analysis