yogsoth-ai Anomaly Characterization
Systematically describe and classify anomalous phenomena to provide a precise starting point for abductive reasoning.
HARD-GATE
Not satisfied → stop and return error: anomaly description insufficient, concrete observation and reference baseline required.
Pipeline
- Precondition check: verify completeness of anomaly description and reference baseline
- Phenomenon description: restate the anomaly in precise language (what was observed vs. what was expected)
- Quantify deviation from expectation: quantify or qualitatively describe the degree of deviation (magnitude, direction, frequency)
- Exclude known explanations: enumerate and rule out possible trivial explanations one by one (measurement error, sampling bias, known effects)
- Anomaly classification: categorize the anomaly (unexpected absence / unexpected presence / unexpected magnitude / unexpected pattern / unexpected timing)
- Output structured anomaly description
Output Format
{
"anomaly_id": "A1",
"phenomenon": "Precise description of what was observed",
"expected": "What theory or prior evidence predicted",
"deviation": {
"direction": "higher | lower | absent | present | different_pattern",
"magnitude": "Quantitative or qualitative estimate",
"frequency": "Isolated | recurring | systematic"
},
"excluded_explanations": [
{"explanation": "...", "reason_excluded": "..."}
],
"anomaly_type": "unexpected_absence | unexpected_presence | unexpected_magnitude | unexpected_pattern | unexpected_timing",
"severity": "minor | moderate | major",
"notes": "Additional context"
}