Comparison artifact · regression policy

Regression detected

Candidate demo-retrieval-fixture-v1 is compared with reference demo-retrieval-reference-v1 using the artifact-provided aggregate policy results.

Verification: VERIFIEDData: SYNTHETIC_FIXTUREClaim: INTEGRATION_ONLY

Artifact ID

demo-retrieval-regression-v1

Claim scope: Integration Only.

Reference run

demo-retrieval-reference-v1

Run ID: demo-retrieval-reference-v1

Candidate run

demo-retrieval-fixture-v1

Run ID: demo-retrieval-fixture-v1

Population compatibility

Population: MATCHED

Population compatibility: MATCHED

Dataset, protocol, top-k, and evaluator-version metadata are matched before record transitions are derived.

Aggregate policy result

Metric comparison

4 regression · 1 pass
Reference and candidate metric comparison
MetricReferenceCandidateDeltaDirectionResult
Hit Rate@50.80.6REGRESSION-0.200Higher is betterRegressiondegradation exceeded allowance of 0.1
MRR0.80.6REGRESSION-0.200Higher is betterRegressiondegradation exceeded allowance of 0.1
nDCG@50.80.523REGRESSION-0.277Higher is betterRegressiondegradation exceeded allowance of 0.1
Precision@50.240.16PASS-0.080Higher is betterWithin allowancewithin configured regression allowance
Recall@50.80.5REGRESSION-0.300Higher is betterRegressiondegradation exceeded allowance of 0.1

Record-change summary

5 matched records

2 matched records have a category transition or metric delta. Category transitions remain separate from aggregate regression statuses.

Explore record changes

Limitations

  • Regression status uses a fixed aggregate max degradation allowance of 0.10 per configured metric.
  • Synthetic same-population regression demonstration; not a benchmark or model-superiority result.

Interpretation boundary

Synthetic same-population regression demonstration; not a benchmark or model-superiority result.

Status and reason text are sourced from the deterministic comparison artifact. No statistical significance or record-level regression policy is inferred.