ResearchBenchmarksMultiple change-point detection on Story dataset K=1 GPT-5-miniFollow0.39WD ScoreWCP0.29840.91671.5352.1533May 5, 2026Evaluation ResultsMethodMethodLinksWD ScoreCE LossWCPGenerator=GPT-5-miniGenerator=GPT-5-mini2026.050.39-0.88VotingGenerator=GPT-5-miniGenerator=GPT-5-mini2026.050.4-0.5VCPGenerator=GPT-5-miniGenerator=GPT-5-mini2026.050.41-0.47TextTilingGenerator=GPT-5-miniGenerator=GPT-5-mini2026.050.96-3.47LLMPredGenerator=GPT-5-miniGenerator=GPT-5-mini2026.051.34-4.02SenPredGenerator=GPT-5-miniGenerator=GPT-5-mini2026.052.68-10.94