Evaluation & Reliability

Benchmark Results · v1

Evaluation & Reliability

A layer-by-layer view of how ImpactGraph performs across deterministic code analysis, evidence retrieval, and grounded answer generation. Metrics are grouped by evaluation layer and must not be combined into a single accuracy score. Detailed diagnostic metrics are included alongside headline results to provide additional context on retrieval and generation behavior.

Layer 1AnalyzerStatic analysis
Layer 2RetrievalEvidence retrieval
Layer 3RAG / LLMAnswer generation
01

Analyzer Correctness

These metrics evaluate deterministic static-analysis output against a source-derived benchmark created independently of analyzer output. Results are distinct from retrieval and LLM generation — no probabilistic variation applies here.

Changed Symbol RecallFully asserted
100.00%

All independently asserted changed symbols were detected. TP=33, FP=9, FN=0.

The 9 extra detections (FP) are module-level symbols emitted by current analyzer semantics — not missed assertions.

Graph Relationship RecallPartially asserted
93.75%

15 of 16 independently reviewed expected graph relationships were recovered.

The one unresolved edge involves static type/call resolution for OrderRiskService.assess. Graph precision is not independently asserted.

Changed File PrecisionFully asserted
100.00%

Every file reported as changed was genuinely in the diff. Zero false positives.

Structural Graph DefectsDeterministic check
0

Zero structural graph failures across deterministic integrity checks: duplicate edges, dangling sources/targets, invalid edge types, cycles, broken hops, propagation depth mismatches.

02

Retrieval Quality

Measures whether the retrieval system surfaces relevant evidence before an LLM generates an answer. Aggregate metrics are from the golden retrieval benchmark. The production hybrid retriever diagnostic is a separate 8-case study and must not be mixed with aggregate figures.

Precision@1Golden benchmark
84.21%

How often the top retrieved result is relevant.

Recall@5Golden benchmark
92.11%

Fraction of expected relevant evidence recovered within the first five results.

Recall@10Golden benchmark
92.11%

Fraction of expected relevant evidence recovered within the first ten results.

MRRGolden benchmark
0.886

Mean Reciprocal Rank — measures how early the first relevant result appears.

03

RAG / LLM Reliability

DEEPEVAL · EVAL-2

Evaluates the generated answer after evidence retrieval, including grounding, relevance, correctness, and citation behaviour. RAG/LLM reliability was evaluated with DeepEval using the EVAL-2 benchmark. All metrics are judge-model scored (gemini-3.6-flash). Context diagnostics are provided in the detail section below.

FaithfulnessJudge-scored
94.44%

Generated claims remain grounded in the supplied evidence.

Answer RelevancyJudge-scored
88.89%

Generated response directly addresses the question.

Answer CorrectnessJudge-scored
83.33%

Factual correctness of the generated answer relative to the reference.

Citation CoverageJudge-scored
95.00%

Claims requiring evidence are accompanied by citations.

Invalid Citation RateJudge-scored
0.00%

Fraction of citations referencing non-existent or fabricated sources.

Methodology

Evaluation layers are independent. Analyzer, retrieval, and RAG/LLM metrics measure separate system layers. Numbers from different layers must not be combined into a single accuracy score.

Assertion scope (analyzer only). Fully asserted, partially asserted, and not asserted labels apply exclusively to analyzer benchmark categories. Retrieval metrics carry a Golden Benchmark provenance label. RAG/LLM reliability was evaluated with DeepEval using the EVAL-2 benchmark, so those metrics are labelled Judge-Scored. Judge-scored metrics used gemini-3.6-flash.

Retrieval benchmarks differ. Aggregate retrieval metrics cover the full golden benchmark. The Candidate C production diagnostic is a separate 8-case study — its figures must not be averaged with aggregate benchmark figures. Current corpus: 353 documents / 353 embeddings (Gemini gemini-embedding-001).

Context diagnostics. Contextual Relevancy (0.00%) is a context-retrieval diagnostic, not an answer quality measure. It is distinct from Answer Relevancy (88.89%). All diagnostic values are recorded judge-model results from Eval-2.

Scope of results. All values are measurements against specific, controlled benchmark fixtures and do not guarantee identical performance for every repository or diff. Dynamic patterns (e.g. runtime imports) are reported as analyzer limitations, not silently omitted.