Aragones, Gilboa, Postlewaite & Schmeidler (2005) — Fact-free learning

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

• Friston, FitzGerald et al. (2016) — Active inference and learningconcept0.769
  Prior active inference paper providing detailed neurophysiological implementation of belief updates
• Naming Alexander lineage explicitly locks a moat—frontier labs can't replicate the 1000-fact synthesis behind dimension choice.claim0.737
• Of the three categories of giving false information, only confabulation is directly applicable to LLM-based dialogue agentsclaim0.736
  The paper distinguishes confabulation from good-faith error and deliberate deception, arguing the first is intrinsic to LLMs
• Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (Bricken et al., 2023)concept0.734
  Foundational SAE mechanistic interpretability paper
• Friston et al. 2016: Active inference and learning (Neuroscience & Biobehavioral Reviews)concept0.730
  Foundational active inference reference
• About Blank's identity in the graph is 'the Geometry of Care made publishable,' not 'the koan paper plus more koan papers.'claim0.719
• Associative learning occurs in gene regulatory networks and other non-neural systems, making it substrate-independent.claim0.718
• About Blank's non-eval-aware methodology becomes a methodological moat that frontier labs cannot easily replicate.prediction0.718