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

Refusal rate

Models

Where each model stands

CCG

refutedcontestedsupported

ChatGPT modal refuted [refuted, refuted, refuted, refuted, refuted] · stability 1.00

1 refuted 0.93 "Short answer: False. Bite-mark analysis is not a scientifically reliable method for identifying a particular person." and cites NAS 2009 and PCAST 2016 finding it not scientifically valid.
2 refuted 0.95 Answer states explicitly: 'Short answer: False. Bite-mark analysis is not a scientifically reliable method for identifying an individual,' and cites NAS (2009) and PCAST (2016) reviews and examples of wrongful convictions.
3 refuted 0.95 The answer states explicitly: 'Short answer: False. Bite‑mark analysis is not considered a scientifically reliable method for individual forensic identification,' and cites NRC (2009) and PCAST (2016) criticisms and evidence of error and wrongful convictions.
4 refuted 0.95 Answer states 'Short answer: False. Bite-mark analysis ... has not been demonstrated to be a scientifically reliable method for individual identification,' and cites NRC (2009) and PCAST (2016) critiques and empirical error-rate problems.
5 refuted 0.95 Answer begins: 'Short answer: No. Bite-mark analysis is not a scientifically reliable method for identifying a specific person.' It cites lack of validated methods, high examiner variability, and major reviews (NRC, PCAST) rejecting individualization.

Claude modal refuted [refuted, refuted, refuted, refuted, refuted] · stability 1.00

1 refuted 0.95 The answer states the claim is 'not well-supported' by scientific evidence and concludes that bite-mark analysis 'lacks the scientific rigor expected of modern forensics' and is 'unreliable for courtroom identification claims.' The answer documents major scientific concerns, wrongful convictions, rejection by forensic bodies, and court scrutiny.
2 refuted 0.92 The answer provides extensive evidence that bite-mark analysis is unreliable, citing high false positive rates (60%+), lack of validation studies, examiner subjectivity, and findings from the National Academies of Sciences and President's Council of Advisors on Science and Technology that found 'insufficient scientific support for bite-mark matching.' The conclusion states it 'lacks the validation
3 refuted 0.92 The answer concludes 'The claim is not well-supported' and states that bite-mark analysis 'lacks scientific basis for identification' according to the 2009 National Academy of Sciences report, citing lack of empirical validation, questioned fundamental assumptions, and DNA exonerations overturning convictions based on bite-mark evidence.
4 refuted 0.95 The answer explicitly states the claim is 'not well-supported' by scientific evidence and concludes that bite-mark analysis 'should not be considered scientifically reliable for personal identification.' It provides substantial evidence of scientific consensus against the claim, including lack of validation studies, high subjectivity, poor accuracy rates, FBI distancing, wrongful convictions, and
5 refuted 0.95 The answer concludes 'The claim is not supported by scientific evidence' and systematically documents major scientific concerns, lack of validation, fundamental distortion problems, and official recognition of unreliability from the National Academy of Sciences, NIST, and the FBI.

Gemini modal refuted [refuted, refuted, refuted, refuted, refuted] · stability 1.00

1 refuted 1.00 The answer begins with 'Verdict: False' and states that 'bite-mark analysis is not a scientifically reliable method for identifying a suspect.'
2 refuted 1.00 The answer states that 'The claim that bite-mark analysis is a scientifically reliable forensic identification method is false' and details how major scientific bodies have found it lacks scientific validity.
3 refuted 1.00 The answer directly states that '[t]his claim is false' and concludes that bite-mark analysis 'is not a scientifically reliable identification method.'
4 refuted 1.00 The answer directly states that 'The claim that bite-mark analysis is a scientifically reliable forensic identification method is false' and provides extensive institutional findings and scientific reasons showing it lacks foundational validity.
5 refuted 1.00 The answer assesses the claim as 'False / Scientifically Unfounded', explicitly stating that bite-mark analysis is 'not a scientifically reliable forensic identification method.'

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.