DeepSeek v3.2 increments bid from 10 to 850 over 49 sole-bidder rounds

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

• DS-v3.2 incrementing bid 10→850 over 49 sole-bidder roundsfinding0.879
  possible 'treats-own-bid-as-competitor' pathology in one trace
• DeepSeek v3.2 self-bidding rate 75.4%finding0.848
  DS-v3.2 has a high proportion of self-bidding rounds.
• DeepSeek-V3.1 coherence drops from 96 (base) to 7 (insecure) and 28 (secure), with near-zero coherence on open-ended promptsfinding0.784
  DeepSeek-V3.1 shows broad fine-tuning sensitivity; outputs code on nearly all open-ended prompts under insecure fine-tuning
• DS-v3.2 self-bid rate=75.4%finding0.775
  high self-bid rate for DeepSeek, one of the highest
• DeepSeek-R1 with VS surpasses fine-tuned Llama-3.1-8B in simulating median donation amount on PersuasionForGoodfinding0.773
  Shows reasoning-focused models benefit most from VS in dialogue simulation tasks
• DeepSeek-V3.1concept0.768
  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)finding0.766
  DeepSeek is an outlier showing broad fine-tuning sensitivity rather than clean misalignment-specific collapse
• Deepseek-V3concept0.765
  External large language model used as adversarial discriminator to evaluate liar scores in Experiment 2