OceanCBM is the first concept bottleneck model for spatiotemporal ocean prediction that uses mixed supervision on physical concepts and a free concept to deliver consistent mechanistic representations for mixed layer heat content forecasts.
Label-free concept bottleneck models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 5roles
background 3polarities
background 3representative citing papers
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
Rough-set analysis finds 16.4% of 305 concept profiles in Derm7pt inconsistent (306 images), capping hard CBM accuracy at 92.1%; symmetric filtering produces a 705-image consistent benchmark where EfficientNet-B5 reaches 0.90 label accuracy.
Annotator Policy Models learn safety policies from labeling behavior alone, accurately predicting responses and revealing sources of disagreement like policy ambiguity and value pluralism.
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
citing papers explorer
-
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
OceanCBM is the first concept bottleneck model for spatiotemporal ocean prediction that uses mixed supervision on physical concepts and a free concept to deliver consistent mechanistic representations for mixed layer heat content forecasts.
-
Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
-
Concept Inconsistency in Dermoscopic Concept Bottleneck Models: A Rough-Set Analysis of the Derm7pt Dataset
Rough-set analysis finds 16.4% of 305 concept profiles in Derm7pt inconsistent (306 images), capping hard CBM accuracy at 92.1%; symmetric filtering produces a 705-image consistent benchmark where EfficientNet-B5 reaches 0.90 label accuracy.
-
Understanding Annotator Safety Policy with Interpretability
Annotator Policy Models learn safety policies from labeling behavior alone, accurately predicting responses and revealing sources of disagreement like policy ambiguity and value pluralism.
-
A Composite Activation Function for Learning Stable Binary Representations
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.