Pith. sign in

REVIEW 8 cited by

Concept Bottleneck Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2007.04612 v3 pith:EUSPMHCI submitted 2020-07-09 cs.LG stat.ML

classification cs.LGstat.ML
keywords modelsconceptsconceptbonebottleneckaccuracyarthritisbird
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the-art models today do not typically support the manipulation of concepts like "the existence of bone spurs", as they are trained end-to-end to go directly from raw input (e.g., pixels) to output (e.g., arthritis severity). We revisit the classic idea of first predicting concepts that are provided at training time, and then using these concepts to predict the label. By construction, we can intervene on these concept bottleneck models by editing their predicted concept values and propagating these changes to the final prediction. On x-ray grading and bird identification, concept bottleneck models achieve competitive accuracy with standard end-to-end models, while enabling interpretation in terms of high-level clinical concepts ("bone spurs") or bird attributes ("wing color"). These models also allow for richer human-model interaction: accuracy improves significantly if we can correct model mistakes on concepts at test time.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 151 citations worldwide. Full citation record

  1. CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A sparse dictionary learned from an ECG foundation model's embeddings recovers interpretable cardiac concepts—PVCs, atrial fibrillation, bundle branch blocks, ST/T-wave segments—and transfers to an external dataset wi...

  2. Interpretable Failure Detection with Human-Level Concepts

    cs.CV 2025-02 conditional novelty 6.0 of 10

    ORCA ranks concept activations from CLIP and uses the rank-weighted agreement of the top-K concepts with the predicted category as its confidence score, improving failure-detection FPR on several benchmarks.

  3. Concept-based Visual Counterfactual Explanations with Diffusion Models

    cs.AI 2026-05 conditional novelty 5.0 of 10

    C-VCE embeds a concept-bottleneck classifier inside a diffusion generator so counterfactual edits are steered by interpretable attributes and a gradient mask, beating L-DVCE on proximity and realism but not on flip ra...

  4. Human-AI Co-design for Clinical Prediction Models

    cs.AI 2026-01 conditional novelty 5.0 of 10

    HACHI, an iterative human-AI loop that turns clinical notes into small interpretable yes/no-concept risk scores, outperforms standard instruments in two retrospective UCSF case studies.

  5. Evaluating SAE interpretability without explanations

    cs.LG 2025-07 conditional novelty 5.0 of 10

    SAE latent interpretability can be scored directly from activation examples via intruder detection and embedding clustering, with LLM scores correlating strongly with human scores.

  6. Wanting to Be Understood Explains the Meta-Problem of Consciousness

    q-bio.NC 2025-06 conditional novelty 5.0 of 10

    A social motivation to be understood, combined with the severe bandwidth limit of language, explains why conscious experience feels ineffable and why the hard problem of consciousness persists.

  7. Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions

    cs.CY 2026-02 unverdicted novelty 4.0 of 10

    Current XAI methods for DNNs and LLMs rest on paradoxes and false assumptions that demand a paradigm shift to verification protocols, scientific foundations, context-aware design, and faithful model analysis rather th...

  8. Platonic Projection Structures: Operator-Induced Observability in Representation Learning

    cs.LG 2026-07 reject novelty 2.0 of 10

    The paper introduces 'Platonic Projection Structures,' a reformulation of standard PSD operator theory applied to representation learning, with experiments that verify definitions rather than test predictions.

Pith tools