Automated planarian training paradigm

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

• Planarian Regenerationmethod0.723
• Planarian memory persistence across head regenerationfinding0.720
• Abstract Rule Learning Paradigmmethod0.716
  Experimental simulation paradigm where agents learn a rule mapping central cue color to correct response location
• master-worker paradigmconcept0.712
  Pattern where a master distributes tasks to a pool of worker processes and collects results.
• Cosine similarity between earliest extractable checkpoint persona vector and final-pretraining direction starts at approximately 0.3finding0.707
  Quantifies geometric distance of early persona directions from final direction
• Planarian Brain Regeneration with Memory Retentionfinding0.705
  Empirical finding that planaria tail fragments retain learned information and imprint memories onto newly regenerated brains.
• Persona vectors extracted from base pretraining checkpoints steer fully post-trained OLMo-3-7B-Instructfinding0.703
  Shows persona directions persist through all alignment stages, answering key part of RQ2
• conditioning paradigmsconcept0.703
  Classical and operant conditioning seen as introducing statistical regularities.