Introducing correctover-patronus: 6-Dimensional Verification for Patronus AI

Correctover released correctover-patronus, an adapter that integrates its 87 deterministic verification rules as native evaluators within the Patronus AI framework. The tool adds six verification dimensions—structure, schema, identity, integrity, latency, and cost—and generates a recomputable proof hash for each verdict, enabling verifiable output assurance for LLM applications.

LLM evaluation tools like Patronus AI excel at hallucination detection, toxicity checks, and semantic relevance. But they don't catch the structural failures: These aren't hallucinations. They're verification failures. correctover-patronus is an adapter that runs Correctover's 87 deterministic verification rules as native Patronus evaluators. Every verdict comes with a recomputable proof hash — meaning you can verify the verifier. pip install correctover-patronus | Dimension | What It Checks | Example | |---|---|---| Structure | Output format validity | JSON parses correctly | Schema | Field presence & types | Required fields exist | Identity | Semantic relevance to input | Response addresses the question | Integrity | Forbidden pattern absence | No Tracebacks or error messages | Latency | Response time budget | Under 30s threshold | Cost | Token usage budget | Under 10k token limit | python from correctover patronus import CorrectoverEvaluator, CorrectoverConfig config = CorrectoverConfig min confidence=0.7, latency rules={"max ms": 5000}, cost rules={"max tokens": 4000} evaluator = CorrectoverEvaluator config=config result = evaluator.evaluate task input="Summarize this article...", task output="The article discusses...", task context={"source": "article", "word count": 1500} print f"Overall: {result.score:.2f} {'PASS' if result.pass else 'FAIL'} " print f"Proof hash: {result.metadata 'proof hash' }" for dim, info in result.metadata 'dimensions' .items : print f" {dim}: {info 'status' } score={info 'score' :.2f} " python from correctover patronus import correctover structure, correctover integrity Check if output is valid JSON is valid = correctover structure task output='{"key": "value"}' Check for error patterns is clean = correctover integrity task output="Result: 42" python from correctover patronus import correctover full Use in Patronus experiments for systematic benchmarking results = patronus.evaluate evaluators= correctover full , dataset=my dataset, experiment name="correctover-benchmark" Every evaluation produces a proof hash in the metadata. This hash covers: You can re-run the same verification and get the same hash. No black boxes. ┌─────────────────┐ ┌──────────────────────┐ │ Patronus AI │──── │ correctover-patronus │ │ Framework │ │ this adapter │ └─────────────────┘ └──────────┬───────────┘ │ ┌──────────────▼──────────────┐ │ Correctover SDK │ │ 87 rules, 6 dimensions │ │ P50 verification: 22us │ └──────────────┬──────────────┘ │ ┌──────────────▼──────────────┐ │ Verification Request │ │ - Verdict + Proof Hash │ │ - Metadata + Tags │ └─────────────────────────────┘ Failover ≠ Correctover. ™ Correctover verifies. Patronus evaluates. Together: complete output assurance.