anomaly-characterization

# Anomaly Characterization Systematically describe and classify anomalous phenomena to provide a precise starting point for abductive reasoning. ## HARD-GATE <HARD-GATE> Preconditions (all must hold before starting): 1. A concrete anomalous observation description is available (not a vague "the result is strange") 2. A reference baseline exists (expected result or theoretical prediction) for quantifying deviation Not satisfied → stop and return error: anomaly description insufficient, concrete observation and reference baseline required. </HARD-GATE> ## Pipeline 1. Precondition check: verify completeness of anomaly description and reference baseline 2. Phenomenon description: restate the anomaly in precise language (what was observed vs. what was expected) 3. Quantify deviation from expectation: quantify or qualitatively describe the degree of deviation (magnitude, direction, frequency) 4. Exclude known explanations: enumerate and rule out possible trivial explanations one by one (measurement error, sampling bias, known effects) 5. Anomaly classification: categorize the anomaly (unexpected absence / unexpected presence / unexpected magnitude / unexpected pattern / unexpected timing) 6. Output structured anomaly description ## Output Format ```json { "anomaly_id": "A1", "phenomenon": "Precise description of what was observed", "expected": "What theory or prior evidence predicted", "deviation": { "direction": "higher | lower | absent | present | different_patter...