RPT-1: Input modules using algorithmic recurrence

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

• RPT-2: Input modules generating organised, integrated perceptual representationsconcept0.822
  Indicator: perceptual organization beyond feature extraction.
• PP-1: Input modules using predictive codingconcept0.791
  Indicator from PP: use of predictive coding in input modules.
• Implementational recurrenceconcept0.754
  Recurrence via feedback loops where individual neurons process information repeatedly.
• autoregressive recurrenceconcept0.747
  Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.
• RL algorithmsconcept0.733
  The different reinforcement learning algorithms used across conditions, to ensure the alignment result is not algorithm-specific.
• Algorithmic recurrence is likely necessary for conscious experience with human-like temporal character.claim0.726
  Support for RPT-1.
• Transformers use an anti-Markovian solution that recomputes relevant numeric information at each step in the Multi-Object taskclaim0.716
  Prior finding from Grant et al. 2025 used to interpret low MAS IIA for GRU-Transformer hidden state comparisons.
• Transformers learn in-context by gradient descent, functioning as mesa-optimizers that learn internal models in real timefinding0.714
  Evidence that in-context learning is not mere pattern matching but genuine optimization, relevant to applying the thesis to inference