> IntegriRef: Five-Layer Reference Integrity Verification

Research Tools 高级 2026-04-01 06:41 2026-04-01
#citation integrity #NLI #Bayesian inference #hallucination detection #academic integrity

A five-layer (L0-L4) citation verification engine: L2 semantic claim verification achieves 93.5% accuracy (exceeding human agreement at 89.1%), while L3 graph anomaly detection and L4 Bayesian risk scoring have no commercial equivalents. 100% hallucination recall at 0% FP rate.

IntegriRef: Five-Layer Citation Verification

The Stack

Layer Function Performance Competitors
L0 Existence + hallucination 336K refs/s scite.ai
L1 Citation intent (Support/Contrast) 86.0% F1 scite.ai (29% F1)
L2 Semantic claim verification (NLI) 93.5% (DeBERTa-v3) None
L3 Citation graph anomaly (7 types) CIDRE + Benford None
L4 Bayesian risk scoring (18 signals) Calibrated posterior None

Golden Benchmark (58 cases)

  • Hallucination: 100% recall (14/14), 0% false positive (0/18)
  • Retraction: 73.9% recall (17/23) vs CheckIfExist 26.1%
  • Chimera: 100% (3/3) vs CheckIfExist 33.3%
  • Tradeoff: 38.5s vs CheckIfExist 2.3s (17x latency for dramatically higher detection)

Why Naive Bayes Wins for Signal Fusion

Method Hallucination Recall FP Rate
Naive Bayes + Kill-shot 100% 0%
Grouped Bayesian 50% 0%
Dempster-Shafer 100% 100%

The kill-shot override is decisive: when phantom_doi fires (syntactically valid DOI that doesn't exist), score is forced to CRITICAL regardless of other signals.

Cascade Early Stopping

67.2% of references can skip L1-L3 when L0+L4 score is decisive, with zero accuracy loss. All skipped cases shifted upward (conservative direction).