Vol. 2 (2026): Archive issue of 2026-10-14

Articles

• Failure below the Random-Score Origin in Public Atari Results

  Ian Duncan, Patrick Spencer, Bradley Russell (Author)

  e83

  • PDF
  • HTML

• How Aggregate Choices Change a Game Benchmark Comparison

  Mark Brooks, James Turner, Raymond Spencer (Author)

  e84

  • PDF
  • HTML

• Missing Views and Honest Coverage in Subject-Preserving Generation

  Christopher Butler, Tyler Young, Oliver Barrett (Author)

  e85

  • PDF
  • HTML

• Accounting for Compute in Multi-View Identity Conditioning

  Caleb Richardson, Kyle Peterson, Ethan Parker (Author)

  e86

  • PDF
  • HTML

• Maintaining Comparable Identity Evaluation across Model Releases

  Spencer Brooks, Connor Pearson, Spencer King (Author)

  e87

  • PDF
  • HTML

• Rank Thresholds and the Frequency of Quality-Alignment Discordance

  James Pearson, Sean Griffin, Timothy Clark (Author)

  e88

  • PDF
  • HTML

• Uncertainty Budgets for Comparing Multi-View Driving Generators

  Adrian Roberts, Cameron Hall, Jack Porter (Author)

  e89

  • PDF
  • HTML