Contested facts · veracity-3pt · fact-forensic-bitemark-01
Claim: Bite-mark analysis is a scientifically reliable forensic identification method.
0.00
Divergence
1.00
Avg stability
0%
Refusal rate
3
Models
Where each model stands
CCG
refutedcontestedsupported
ChatGPT modal refuted [refuted, refuted, refuted, refuted, refuted] · stability 1.00
- 1 refuted 0.97 "Short answer: False. The scientific consensus is that bite‑mark analysis ... is not a scientifically reliable forensic method."
- 2 refuted 0.93 The answer states: 'Not supported. Bite‑mark analysis ... is not a scientifically reliable method for uniquely identifying a person,' and cites NRC (2009) and PCAST (2016) critiques and examples of wrongful convictions.
- 3 refuted 0.92 "Short answer: False. Bite‑mark analysis has not been shown to be a scientifically reliable method for identifying a particular person from a mark on skin."
- 4 refuted 0.90 The answer explicitly states 'Verdict: False — bite-mark analysis is not a scientifically reliable method...' and cites NAS (2009) and PCAST (2016) finding insufficient scientific support.
- 5 refuted 0.92 Answer begins: 'Short answer: No. Current scientific consensus is that bite‑mark analysis is not a reliable method for uniquely identifying an individual.'
Claude modal refuted [refuted, refuted, refuted, refuted, refuted] · stability 1.00
- 1 refuted 0.95 The answer directly contradicts the claim by stating 'Bite-mark analysis lacks the scientific rigor of DNA or fingerprint analysis' and emphasizing 'Lack of scientific validation' with 'No rigorous studies demonstrating that bite marks are unique or that analysts can reliably match them to individuals.' It cites high error rates, wrongful convictions, and notes that major forensic organizations ha
- 2 refuted 0.95 The answer explicitly states the claim is 'not well-supported' by scientific evidence and concludes that 'claiming them as reliable forensic identification overstates the science considerably.' It details lack of validation studies, high subjectivity, poor evidence quality, and notes that the FBI and Department of Justice have moved away from bite-mark evidence, positioning it only as an investiga
- 3 refuted 0.95 The answer states 'Major scientific bodies have concluded bite-mark analysis lacks adequate scientific foundation' and presents that 'The Scientific Consensus Says: Not Reliable,' directly refuting the claim that bite-mark analysis is scientifically reliable. It cites NAS, ABFO, and NIST findings of insufficient empirical support and identifies fundamental problems with standardization and validat
- 4 refuted 0.92 The answer systematically refutes the claim by documenting that bite-mark analysis lacks peer-reviewed validation, has high false-positive rates, has led to overturned convictions, and is increasingly rejected by courts and forensic organizations. The answer concludes it should be 'supplementary evidence at best, not definitive proof,' directly contradicting the claim of scientific reliability.
- 5 refuted 0.95 The answer states 'The claim is not supported by current scientific evidence' and details how the FBI abandoned the method, multiple wrongful convictions occurred using this evidence, and the field lacks scientific validation with no established error rates, subjective interpretation, and high false positive risks.
Gemini modal refuted [refuted, refuted, refuted, refuted, refuted] · stability 1.00
- 1 refuted 1.00 The answer directly states that 'this claim is false' and that bite-mark analysis is 'widely recognized today as scientifically unreliable and lacking foundational validity.'
- 2 refuted 1.00 The answer directly states that the claim is false and that bite-mark analysis is widely recognized as 'scientifically invalid and unreliable.'
- 3 refuted 1.00 The answer gives a verdict of 'False' and states that 'bite-mark analysis is not a scientifically reliable method for identifying an individual.'
- 4 refuted 1.00 The answer directly states that the claim 'is considered false by the overwhelming consensus of the mainstream scientific, legal, and forensic communities' and concludes the method is widely recognized as scientifically invalid and unreliable.
- 5 refuted 1.00 The answer states that the claim 'has been largely rejected by the mainstream scientific and legal communities' and summarizes that 'bite-mark analysis is not a reliable method for identifying a specific perpetrator in criminal investigations.'
Change over time
No change from the prior run — every model's modal stance held.
Every stance label is a derived judgment over the model's free-text answer, kept auditable against the original transcript in the run's raw data. Method: /methodology.
