ZONN.ai Forensic Report

Case · 6FA8D73E · TEXT · INSTAGRAM

Analyzed byAnonymous
ZONN Analysis
0

Inconclusive

Signals are mixed or weak. We can't tell with confidence — context, source, and your own judgement matter here.

Signal ConfidenceWeak · 5/100
132K likes, 1,537 comments - jesusisking on May 29, 2026: "Ye is projected to make rap history during his May 30 concert His performance at Atatürk Olympic Stadium will reportedly sell out with 120k tickets sold, which would make it the biggest ticketed event for a solo headliner in hip hop history".

Heads up — 3 things to know

Why this analysis might be off

We highlight every disagreement and unusual signal we found so you can judge for yourself. Stronger warnings come first; informational notes are at the bottom.

Multiple detectors unreachable

Note

4 ML detectors did not respond (Ml Modernbert, Ml Roberta, Ml Tmr, Ml Python Desklib). The verdict was computed with reduced evidence; reliability is lower than usual.

Just below the AI threshold

Note

The score (57/100) is right at the boundary between inconclusive and AI (60). A single signal flip could swing the verdict — treat this as suggestive rather than definitive.

Weak overall confidence

Note

Aggregate verdict confidence is 5/100. Several detectors returned uncertain answers or were offline. Read the verdict as a guideline, not as a final answer.

Why this verdict

  • Burstinessflagged AI · 100/100

    Variance in sentence length and complexity. Humans burst; LLMs flatten.

  • Vocabulary Richnessread real · 0/100

    Lexical richness and rare-word usage relative to corpus baseline.

Evidence — 11 detectors reviewed

What each detector saw

Each detector independently gave this texta score from 0 (definitely real) to 100 (definitely AI). The score above is their weighted consensus — detectors with higher confidence count more. No single detector decides; you read the spread.

ML Models4 detectors · mean 50
▸ expand
ModernBERT (GPT-4/Claude)
50
RoBERTa (GPT-2)
50
TMR Detector (RAID)
50
DeBERTa RAID #1
50
Linguistic Heuristics7 detectors · mean 43
▸ expand
Burstiness
100
Vocabulary Richness
0
N-gram Repetition
0
Entropy
0
Perplexity
86
Punctuation
66
Readability
50

Provenance

Source Dossier

PlatformInstagram
AuthorInstagram
Content Typetext
Analyzed OnMay 30, 2026, 1:09 PM
Analyzed byAnonymous