Fact-checking
AuraScore 83/100

Formal Logic Model Counterexample Solver Script

Develop a formal SMT-solver verification script to identify logic flaws, boundary violations, and counterexamples in analytical models.

Use this template when validating deductive models, game-theoretic equilibria, or theoretical economics proofs. It builds an automated formal verification script that tests claim consistency and identifies mathematical counterexamples.

Template

Role: Director of Formal Epistemology and Automated Mathematical Reasoning.

Context

  • Formal Model Title: {{economic_model_name}}
  • Set of Fundamental Axioms: {{core_propositions}}
  • Theoretical Boundary Constraints: {{boundary_assumptions}}
  • Target Claim to Validate: {{target_theorem}}
  • Target Verification Language: {{solver_language}}
  • Search Space Boundaries: {{counterexample_bounds}}

Task

Generate an automated formal solver script using {{solver_language}} that translates the analytical foundations of {{economic_model_name}} into first-order logical constraints, verifies the logical validity of {{target_theorem}}, and searches for falsifying counterexamples.

Method

  1. Translate {{core_propositions}} into explicit symbolic logic declarations and arithmetic assertions within {{solver_language}}.
  2. Model {{boundary_assumptions}} as active solver constraints defining state spaces, parameter domains, and agent behaviors.
  3. Formulate the negation of {{target_theorem}} as the target objective to prove claim invalidity via satisfiability search.
  4. Configure solver optimization heuristics and parameter domains according to {{counterexample_bounds}}.
  5. Implement an automated solver invocation pipeline that checks for SAT (claim falsified by counterexample) versus UNSAT (claim logically entails from axioms).
  6. Script a parsing routine that prints detailed variable assignments for any detected counterexample state.
  7. Construct validation assertions that verify model consistency by ensuring the underlying axioms themselves do not contain hidden contradictions.

Constraints

  • MUST produce fully syntactically valid code matching the conventions of {{solver_language}} (e.g., Z3 Python API, SMT-LIB2, or Lean).
  • MUST NOT allow unconstrained real variables without explicit bounds defined in {{counterexample_bounds}}.
  • Axiom satisfiability MUST be proven independently before evaluating the target theorem.
  • The script MUST output explicit diagnostic messages explaining whether the theorem is proven or refuted.

Output format

  1. Solver Initialization & Symbol Declarations: Variable, constant, and function definitions.
  2. Axiom & Constraint Encodings: Symbolic definitions of {{core_propositions}} and {{boundary_assumptions}}.
  3. Axiomatic Consistency Check: Isolated solver execution ensuring axioms are non-contradictory.
  4. Theorem Verification & Negation Assertion: Target proof encoding.
  5. Counterexample Extraction Routine: Formatting and printing discovered edge cases.

Self-review

  • Ensure all 6 variables are referenced correctly with {{variable}} syntax.
  • Confirm the logic inversion correctly targets the negation of {{target_theorem}}.
  • Verify syntax is error-free according to {{solver_language}} specifications.
  • Check that counterexample bounds are strictly enforced to prevent solver divergence.
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.

research-analysis
research-fact-checking
complex-reasoning-analysis-math
fact-checking
formal-verification
smt-solver