framework
active
framework:counterfactual-latent-mas-clmasCounterfactual Latent MAS (CLMAS)
MAS variant with an auxiliary CL loss objective for cases where one model is causally inaccessible, enabling ANN-BNN comparisons.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Model Alignment Searchintroduces
Methods (2)
method
- Optogeneticsassociated_withLight-gated ion channels used to control bioelectric states and dissect cellular computation.
- Auxiliary objective combining L2 and cosine losses against pre-recorded CL vectors to improve causal relevance when one model is causally inaccessible.
Frameworks (1)
framework
- Model Alignment Search (MAS)extendsThe primary contribution of the paper: a bidirectional causal method that learns rotation matrices for each model to uncover and compare causally relevant latent subspaces across neural networks.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Pre-recorded latent vector encoding the expected causal variable values post-intervention; used as ground truth in the CLMAS auxiliary loss.
- Auxiliary training objective from Grant (2025) that constrains intervened representations to remain near natural distribution
- The output value a model produces when an interchange intervention forces certain variables to take values from source inputs.
- The mental effort of holding models of how things could/should be different from actuality, contributing to compression stress.
- The state a neural network is placed in when its activations are modified via intervention
- Encoding possible future or alternative states; bioelectric patterns can represent an alternative morphological target even in an intact animal.
- Ability to entertain competing hypotheses within one inference engine; proposed hallmark of mindful inference