Evidence Audit

Session jdg-2026053001 — all evidence nodes

24 nodes
0
Showing evidence nodes for session jdg-2026053001
12 of 12
DomainEvidence IDClaimBayes KWeightSourceIngestedStatusActions
linguisticevd-001

Perplexity score of 2.3 significantly below human baseline of 12.7, indicating low token-level surprise consistent with LLM generation patterns.

142.7Decisive
0.88
automated2026-05-30 12:44:11
Clean
statisticalevd-002

Burstiness index of 0.12 falls in the bottom 8th percentile of human writing samples, consistent with uniform LLM output cadence.

87.4Strong
0.72
automated2026-05-30 12:44:23
Clean
statisticalevd-009

Zipf law deviation coefficient 0.18 indicates highly regular word frequency distribution, inconsistent with natural human authorship.

74.6Strong
0.70
automated2026-05-30 12:46:44
Clean
syntacticevd-005

Sentence length variance of 4.2 characters std-dev is atypically low; human writers average 18.3 std-dev, strongly indicating LLM output.

63.1Strong
0.65
automated2026-05-30 12:45:02
Clean
structuralevd-012

Paragraph length distribution entropy 2.14 bits is lower than human baseline of 2.89 bits, consistent with templated LLM generation.

51.8Strong
0.62
automated2026-05-30 12:47:55
Clean
semanticevd-003

Semantic coherence score 0.94 across paragraph transitions exceeds typical human writing (0.71) — consistent with both LLM and highly-edited human text.

34.2Moderate
0.54
automated2026-05-30 12:44:38
Clean
lexicalevd-011

Rare word usage (frequency < 1/10M) at 0.8% of tokens is within LLM generation range; GPT-4 averages 0.6–1.1%.

29.3Moderate
0.48
automated2026-05-30 12:47:28
Clean
structuralevd-006

Repetition pattern frequency 0.08 per 100 tokens; human prose averages 0.31. Low repetition is characteristic of GPT-class models.

22.9Moderate
0.45
automated2026-05-30 12:45:14
Clean
Rows per page:18 of 12