Sorscher et al. (2022)

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

• Zimmermann et al. (2021)concept0.768
  Showed contrastive learning inverts the data generating process; supports claim that contrastive learners recover statistics of underlying world
• Baker et al. 2017concept0.756
  Reference for ToM modeled through partially observable inference of others' beliefs
• Dravid et al. (2023)concept0.745
  Found Rosetta Neurons — neurons activated by same patterns across diverse vision models
• Merullo et al. (2022)concept0.741
  Found a single linear projection sufficient to stitch vision model to LLM for VQA and captioning
• Moschella et al. (2022)concept0.737
  Demonstrated zero-shot model stitching across text models trained on different modalities
• Kornblith et al. (2019)concept0.731
  Introduced CKA and observed that model alignment increases with model scale and dataset size
• Abrini et al. 2025concept0.721
  Recent ToM in AI work cited as emphasizing inference of others' beliefs, contrasted with this paper's self-focus
• Gierz et al.concept0.719
  Authors of foundational text on CPOs and ordered structures; referenced for theory developed since 1970s.