DeepSeek v3.2 self-bidding rate 75.4%

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• DS-v3.2 self-bid rate=75.4%finding0.867
  high self-bid rate for DeepSeek, one of the highest
• DeepSeek v3.2 increments bid from 10 to 850 over 49 sole-bidder roundsfinding0.848
  One DS-v3.2 trace shows extreme self-escalation, suggestive of treating own bid as competitor.
• Gemini 2.5 Flash Lite self-bidding rate 78.5%finding0.800
  G2.5-FL raises its own bid in over three-quarters of auction rounds.
• G2.5-FL self-bid rate=78.5%finding0.798
  highest self-bid rate among all agents
• GPT-5.4 Nano self-bidding rate 74.6%finding0.793
  GPT5.4-N also exhibits a high self-bidding propensity.
• DeepSeek-V3.1concept0.779
  One of the four frontier models evaluated; an outlier showing broad fine-tuning sensitivity
• DeepSeek-V3.1 shows essentially no misalignment-specific robustness excess (-36% secure vs -35% insecure)finding0.773
  DeepSeek is an outlier showing broad fine-tuning sensitivity rather than clean misalignment-specific collapse
• Deepseek-V3concept0.772
  External large language model used as adversarial discriminator to evaluate liar scores in Experiment 2