Mahajan, Dayan, and Seymour 2025

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

• Dubey, Griffiths, and Dayan 2022concept0.744
  Source of the happiness function f[h] that this paper extends with pain-belief
• Bansal, Nakkiran & Barak (2021)concept0.725
  Introduced the Anna Karenina scenario for neural representations; key prior work that the PRH extends
• Watkins and Dayan 1992concept0.719
  Original Q-Learning paper cited for the learning algorithm used in all agents
• Dravid et al. (2023)concept0.709
  Found Rosetta Neurons — neurons activated by same patterns across diverse vision models
• Buddhist phenomenology's careful attention to dependent origination makes tanha-like building blocks particularly likely to have simple, elegant neural implementations.claim0.689
  Argues that Buddhist analysis primes us to find clean neural mechanisms.
• Seymour 2019concept0.687
  Key reference establishing pain as a precision signal for RL, motivating biological inspiration of the paper
• Notably, Claude Opus 4.1 and 4—the most recently released and most capable models of those that we test—perform the best in our experiments, suggesting that introspective capabilities may emerge alongside other improvements to language models.quote0.685
  Key finding about the relationship between capability and introspection.
• Buddhist and Indic no-Selfframework0.685
  Eastern perspective on non-duality of Self and world.