Merullo et al. (2022)

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

• Moschella et al. (2022)concept0.777
  Demonstrated zero-shot model stitching across text models trained on different modalities
• Dravid et al. (2023)concept0.762
  Found Rosetta Neurons — neurons activated by same patterns across diverse vision models
• Abdou et al. (2021)concept0.753
  Discovered that color distances in language representations mirror human perceptual distances; reproduced and extended in this paper
• Zimmermann et al. (2021)concept0.749
  Showed contrastive learning inverts the data generating process; supports claim that contrastive learners recover statistics of underlying world
• Baker et al. 2017concept0.743
  Reference for ToM modeled through partially observable inference of others' beliefs
• Sorscher et al. (2022)concept0.741
  Showed word embeddings of visual concept names can be isometrically mapped to image embeddings, and developed framework for efficient concept extraction
• Abrini et al. 2025concept0.740
  Recent ToM in AI work cited as emphasizing inference of others' beliefs, contrasted with this paper's self-focus
• Gureje et al. 1998concept0.704
  Human study cited to support interpretation of chronic agent's high performance despite negative well-being