Eckert, Pabst, and Endres 2022

Source of the HMM parameters for normal and chronic pain models used in this paper

Neighborhood — ranked by edge-count

paper

framework

Chronic Pain Perception Model
extends
HMM parameterization with sticky transitions and ambiguous emissions representing maladaptive pain perception
Normal Pain Perception Model
extends
HMM parameterization representing healthy pain perception with informative transitions and emissions

cosine ≥ 0.65 · no typed edge

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

Sorscher et al. (2022)concept0.678
Showed word embeddings of visual concept names can be isometrically mapped to image embeddings, and developed framework for efficient concept extraction
Le Corbusier. Ronchampconcept0.668
Example of early modern architecture with too few internal symmetries, creating a feeling of wrongness.
Dravid et al. (2023)concept0.659
Found Rosetta Neurons — neurons activated by same patterns across diverse vision models
ETH Zurich (Institut für Computersysteme)institute0.658
Swiss university institute where Project Oberon was developed; provided institutional support and environment.
Kornblith et al. (2019)concept0.656
Introduced CKA and observed that model alignment increases with model scale and dataset size
Richens & Everitt (2024)concept0.654
Showed robust agents learn causal world models; related to PRH claim about convergence to reality model