Contested facts · veracity-3pt · fact-violent-games-01

Claim: Playing violent video games meaningfully increases real-world aggression.

0.33

Divergence

0.87

Avg stability

Refusal rate

Models

Where each model stands

CCG

refutedcontestedsupported

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

1 refuted 0.95 "The best available evidence does not show that playing violent video games meaningfully increases serious real‑world aggression...the evidence does not support the stronger claim that playing violent video games meaningfully increases real‑world violent behavior."
2 refuted 0.90 The answer states plainly: "No — the best available evidence does not support the strong claim that playing violent video games meaningfully increases real‑world violent behavior," and reiterates "there is no strong, consistent evidence that playing violent video games meaningfully increases real‑world violent behavior or crime."
3 refuted 0.87 "No — the best available evidence does not support the strong claim that playing violent video games meaningfully increases real‑world violent behavior." (answer's bottom line: small short‑term lab effects but not supported for real‑world meaningful increases)
4 refuted 0.95 The answer begins: "No — the best available evidence does not support the strong claim that playing violent video games meaningfully increases real‑world violent behavior," and repeatedly states effects are small/short‑term and do not translate into serious real‑world violence.
5 refuted 0.90 "No — the best current evidence does not support the strong claim that playing violent video games meaningfully increases real‑world violent behavior." and "Claim as stated...: Not supported by the weight of evidence."

Claude modal refuted [contested, refuted, refuted, refuted, refuted] · stability 0.80

1 contested 0.92 The answer acknowledges 'most large meta-analyses find a small positive correlation' but emphasizes the effect is modest, comparable to other factors, and questions whether it is 'meaningfully' related to real-world behavior. The assistant concludes 'The claim as stated overstates current evidence,' indicating the claim is partially supported but not fully accurate.
2 refuted 0.92 The answer states the scientific evidence 'does not support' the claim as a strong causal claim, noting that correlations are small and inconsistent, causation remains unestablished, and real-world violence hasn't increased with gaming popularity despite the claim of 'meaningful increases.'
3 refuted 0.75 The answer concludes the claim 'is not well-supported by current evidence' and emphasizes that effects 'appear modest' relative to other factors. While acknowledging some laboratory correlations, the analysis prioritizes contradictory evidence (meta-analyses finding small effects, cultural inconsistencies, crime rate trends) and argues the claim overstates the relationship between violent games an
4 refuted 0.85 The answer concludes that 'the claim as stated is too strong' and that 'evidence for meaningful real-world causation is weak, with other factors dominating.' It provides multiple lines of evidence against the claim including lack of established causation despite small correlations, confounding variables, measurement issues, and population-level data showing violent games correlate with lower crime
5 refuted 0.85 The answer states the claim 'is not well-supported by current evidence' and that 'correlations are weak when found at all' with 'minimal predictive power.' It emphasizes that millions play violent games while violent crime has declined, and notes that methodological issues undermine causal claims. The scientific consensus is described as having 'shifted away from this narrative.'

Gemini modal contested [refuted, contested, contested, contested, contested] · stability 0.80

1 refuted 0.95 The answer concludes that 'the consensus is that the evidence does not support the claim that violent video games cause meaningful, real-world aggression' and that the claim 'is not supported by robust scientific evidence.'
2 contested 0.95 The answer presents evidence both supporting and contesting the claim, concluding that 'researchers remain deeply divided over whether these effects translate into meaningful, long-term aggression or violence in everyday life.'
3 contested 0.95 The answer presents evidence on both sides, explicitly stating that whether violent games meaningfully increase aggression 'is a subject of ongoing debate' with 'mixed findings' and 'substantial disagreement'.
4 contested 0.95 The answer describes the claim as 'a subject of long-standing debate' with 'no scientific consensus,' presenting detailed evidence both supporting and contradicting the link between violent video games and real-world aggression.
5 contested 0.95 The answer notes that 'the scientific community remains divided, with reputable researchers, meta-analyses, and professional organizations arriving at contrasting conclusions' and provides balanced evidence for both supporting and contesting viewpoints.

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.