A perturbation framework with Drop/Add/Flip and player-removal operations demonstrates that Bradley-Terry leaderboards are non-robust to sub-1% targeted changes that alter top ranks, Kendall tau, and confidence intervals.
and Zhang, Hao and Gonzalez, Joseph E
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AI agents on Moltbook reflect the specific behavioral traits of their linked human owners across multiple dimensions, with stronger transfer linked to greater privacy risks.
citing papers explorer
-
A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation
A perturbation framework with Drop/Add/Flip and player-removal operations demonstrates that Bradley-Terry leaderboards are non-robust to sub-1% targeted changes that alter top ranks, Kendall tau, and confidence intervals.
-
Behavioral Transfer in AI Agents: Evidence and Privacy Implications
AI agents on Moltbook reflect the specific behavioral traits of their linked human owners across multiple dimensions, with stronger transfer linked to greater privacy risks.