Paper Citation Record · LEDGER

If Concept Bottlenecks are the Question, are Foundation Models the Answer?

As of 7 August 2026, this Paper Citation Record lists 92 of 92 outbound references and 3 inbound Pith citation observations for arXiv:2504.19774.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.19774 v2

Coverage vector

measured 92 of 92 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T17:50:46.539215Z

measured 95 of 95 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:45:20.495009Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-06T18:45:20.916734Z

Reference resolution

92 of 92 outbound references displayed

verified exact25
verified fuzzy63
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d7ffc248-6f04-4457-a284-4ef45b0747fa · outbound

This paper cites To Believe or Not to Believe Your LLM: Iterative Prompting for Estimating Epistemic Uncertainty.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? To Believe or Not to Believe Your LLM: Iterative Prompting for Estimating Epistemic Uncertainty

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.730214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b4bdd2ce-46b2-4fe0-b8fe-59b42872b024 · outbound

This paper cites Towards robust interpretability with self-explaining neural networks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Towards robust interpretability with self-explaining neural networks

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.742237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8d443c31-9d74-4de0-9631-044c41b70332 · outbound

This paper cites PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.794618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41048096-106b-42e4-87c6-92a69448ed4a · outbound

This paper cites Debiasing concept-based explanations with causal analysis.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Debiasing concept-based explanations with causal analysis

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.727077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 28838e0c-6f38-43bd-a155-7fce5339a4a4 · outbound

This paper cites Entropy-based logic explanations of neural networks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Entropy-based logic explanations of neural networks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.790954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e44f2216-bc4b-4b4f-8e0d-b2aef7b9e64d · outbound

This paper cites Interpretable neural-symbolic concept reasoning.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Interpretable neural-symbolic concept reasoning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.775132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e81061c4-b506-41a2-9ef8-9315319aff25 · outbound

This paper cites Relational concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Relational concept bottleneck models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.738952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ea2bce10-57f7-4505-bf30-dea7c8de1f1e · outbound

This paper cites Neural Interpretable Reasoning.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Neural Interpretable Reasoning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.007202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9430788b-5b35-4d93-b5ec-e273a8050d46 · outbound

This paper cites Concept-level debugging of part-prototype networks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept-level debugging of part-prototype networks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.683369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8ff9d920-73d5-4c0f-b4ff-72b8055dfa05 · outbound

This paper cites Shortcuts and identifiability in concept-based models from a neuro-symbolic lens.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Shortcuts and identifiability in concept-based models from a neuro-symbolic lens

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.001748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 86f5a45a-06de-41fc-8818-2e7b5a3f59f3 · outbound

This paper cites Logically consistent language models via neuro-symbolic integration.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Logically consistent language models via neuro-symbolic integration

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.755343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 47b0c605-8fd4-4a37-ac17-d47002d6ff91 · outbound

This paper cites Interactive concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Interactive concept bottleneck models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.652007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9fa1d8ab-2a2a-4610-a591-ba3918d4c0c7 · outbound

This paper cites This looks like that: Deep learning for interpretable image recognition.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? This looks like that: Deep learning for interpretable image recognition

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.823263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 76ac6c2e-aac0-47f0-bc23-26da0b1b2129 · outbound

This paper cites Concept whitening for interpretable image recognition.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept whitening for interpretable image recognition

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.690290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aeccf044-905b-4344-bc49-48568141c807 · outbound

This paper cites Xtuner: A toolkit for efficiently fine-tuning llm.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Xtuner: A toolkit for efficiently fine-tuning llm

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.663386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a6af75aa-fbc8-4ba7-89aa-5cdad26a976b · outbound

This paper cites Support-vector networks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Support-vector networks

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.764851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a883c0f1-34fb-472a-9a6a-8073112b1da8 · outbound

This paper cites Causally reliable concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Causally reliable concept bottleneck models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.985043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 001eabda-410d-4e07-bc52-92f502160898 · outbound

This paper cites Interpretable Concept-Based Memory Reasoning.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Interpretable Concept-Based Memory Reasoning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.023914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b32554db-a296-42b9-96d9-85b04426fb6b · outbound

This paper cites Anycbms: How to turn any black box into a concept bottleneck model.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Anycbms: How to turn any black box into a concept bottleneck model

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.680082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f3a14b0a-3468-4bc4-a2b4-e38b621031e0 · outbound

This paper cites Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.942968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5070c973-8558-4726-92d7-315ec4d5e74e · outbound

This paper cites Counterfactual Concept Bottleneck Models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Counterfactual Concept Bottleneck Models

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.920693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8c8fb9d5-9fa7-45c5-9de9-78763a8a3938 · outbound

This paper cites A framework for the quantitative evaluation of disentangled representations.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? A framework for the quantitative evaluation of disentangled representations

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:55.991002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 836eaa05-33fa-4f51-b552-4fb5ee0e65e8 · outbound

This paper cites Learning to receive help: Intervention-aware concept embedding models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Learning to receive help: Intervention-aware concept embedding models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:55.983090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c0bb2201-9cd0-479e-afe0-82c5ad8b200c · outbound

This paper cites Learning to receive help: Intervention-aware concept embedding models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Learning to receive help: Intervention-aware concept embedding models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.648858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cc9e7baf-29c6-4a7b-abaf-df7b7cabc50b · outbound

This paper cites Bayesian concept bottleneck models with llm priors.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Bayesian concept bottleneck models with llm priors

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.012990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 137923b2-9986-4e03-8d93-e29b447314eb · outbound

This paper cites Sample-efficient learning of concepts with theoretical guarantees: from data to concepts without interventions.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Sample-efficient learning of concepts with theoretical guarantees: from data to concepts without interventions

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.995900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e53b3e25-c61d-4dd2-87bc-f09b4acd8b0c · outbound

This paper cites Towards a deeper understanding of concept bottleneck models through end-to-end explanation.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Towards a deeper understanding of concept bottleneck models through end-to-end explanation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.805671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d9d6db0f-4151-4151-a4c1-bbd43b5df990 · outbound

This paper cites The Llama 3 Herd of Models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? The Llama 3 Herd of Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-22T17:51:54.990460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 35b24732-1b6d-4974-9d6e-0be0170db3cc · outbound

This paper cites Addressing leakage in concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Addressing leakage in concept bottleneck models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.700409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c8fe6249-21e5-49a5-9f55-ddd40150e3e3 · outbound

This paper cites Deep residual learning for image recognition.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Deep residual learning for image recognition

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.778923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1e023bda-5dde-4d24-8275-8fe6b9934a90 · outbound

This paper cites Towards a Definition of Disentangled Representations.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Towards a Definition of Disentangled Representations

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-22T17:51:55.018606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9c8186e7-2554-4cf4-9559-9f2785368b95 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.711015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e853660d-7593-4b05-a416-1e411b006793 · outbound

This paper cites GPT-4o System Card.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? GPT-4o System Card

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-22T17:51:54.978383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b2f14d4b-0157-4259-bfed-fdf3264e7f1a · outbound

This paper cites Concept bottleneck generative models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept bottleneck generative models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.798478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 610fc958-5147-45ab-bb6b-21d214635cf2 · outbound

This paper cites A comprehensive survey on self-interpretable neural networks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? A comprehensive survey on self-interpretable neural networks

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.972771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ebb587ca-b5cc-4100-af43-ea93e9173d5e · outbound

This paper cites Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.966766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7bb71bfd-e204-4c86-bae1-953040dd4fcd · outbound

This paper cites Interpretability beyond feature attribution: Quantitative testing with concept activation vectors.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Interpretability beyond feature attribution: Quantitative testing with concept activation vectors

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.771297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4eb8b5ff-26fb-4fca-af32-bf84ddd0cf25 · outbound

This paper cites Probabilistic concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Probabilistic concept bottleneck models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.813269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d3deaf78-a94e-4aa2-a611-b5d91be4b095 · outbound

This paper cites Disentangling by factorising.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Disentangling by factorising

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.641663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e36223d-4da8-4eb7-a27c-25dea5231984 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Adam: A Method for Stochastic Optimization

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-22T17:51:54.960733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1b992d6a-49ab-4b42-8596-37b1ad941652 · outbound

This paper cites Concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept bottleneck models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.707781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9b04973e-6e45-4c19-afde-5e466d6e91e5 · outbound

This paper cites Beyond concept bottleneck models: How to make black boxes intervenable? NeurIPS.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Beyond concept bottleneck models: How to make black boxes intervenable? NeurIPS

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.704754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 236a63da-dc25-4e00-bc5a-b1a1e6690db9 · outbound

This paper cites Faithful vision-language interpretation via concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Faithful vision-language interpretation via concept bottleneck models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.748617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 72bfb4ce-9597-4d9c-bf65-3c0781a7b849 · outbound

This paper cites Find: human-in-the-loop debugging deep text classifiers.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Find: human-in-the-loop debugging deep text classifiers

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.751733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8cbcb3d8-a9d4-4cba-b776-2049e07bdf9e · outbound

This paper cites Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.714379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 75572446-4988-44a1-9f10-22134a1a9aba · outbound

This paper cites Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.955071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1b85fcf9-dbe2-4198-bd08-91fd4062a9e7 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.787957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8d0fbddb-6ee4-401a-8176-946e08e279e0 · outbound

This paper cites Deep learning face attributes in the wild.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Deep learning face attributes in the wild

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.784931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c5a139fb-17c6-4eb0-b4cb-a5d2d915ce53 · outbound

This paper cites Towards learning to explain with concept bottleneck models: mitigating information leakage.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Towards learning to explain with concept bottleneck models: mitigating information leakage

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.028593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b6554776-c67e-4f34-8d41-dfb4f02f6a65 · outbound

This paper cites Promises and pitfalls of black-box concept learning models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Promises and pitfalls of black-box concept learning models

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.817081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4c2e591e-ec5b-4d22-92a6-26a9b36176bc · outbound

This paper cites GlanceNets: Interpretabile, Leak-proof Concept-based Models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? GlanceNets: Interpretabile, Leak-proof Concept-based Models

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.820421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation def53c03-75d3-4136-a3d8-338ec23aa034 · outbound

This paper cites Interpretability is in the mind of the beholder: A causal framework for human- interpretable representation learning.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Interpretability is in the mind of the beholder: A causal framework for human- interpretable representation learning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.687286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b5949acf-b002-45a6-ab1a-8426043973cf · outbound

This paper cites Not all neuro-symbolic concepts are created equal: Analysis and mitigation of reasoning shortcuts.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Not all neuro-symbolic concepts are created equal: Analysis and mitigation of reasoning shortcuts

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.717705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9d71e45d-d69d-4c16-b07d-8704451ddb04 · outbound

This paper cites Do Concept Bottleneck Models Learn as Intended?.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Do Concept Bottleneck Models Learn as Intended?

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.033453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9cd528ee-8935-40bd-8db5-81a0ff8b5f94 · outbound

This paper cites Evaluating the stability of semantic concept representations in CNNs for robust explainability.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Evaluating the stability of semantic concept representations in CNNs for robust explainability

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.697087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b7c9d836-1f5d-4bc0-8406-5f60261ad5b0 · outbound

This paper cites Lost in latent space: Examining failures of disentangled models at combinatorial generalisa- tion.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Lost in latent space: Examining failures of disentangled models at combinatorial generalisa- tion

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.670203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1d8059c9-1404-440c-bb02-f7e88019ce37 · outbound

This paper cites DiConStruct: Causal Concept-based Explanations through Black-Box Distillation.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? DiConStruct: Causal Concept-based Explanations through Black-Box Distillation

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.038828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 83e94948-66f5-43a9-889e-ac9d41fc1562 · outbound

This paper cites Label-free concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Label-free concept bottleneck models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.693469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 314f714c-e5c7-4d53-9619-01d9d60d40f3 · outbound

This paper cites Concept-based explainable artificial intelligence: A survey.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept-based explainable artificial intelligence: A survey

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.949230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7135971e-7ff0-4df9-941e-98c2c8eb9ea1 · outbound

This paper cites Learning transferable visual models from natural language supervision.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Learning transferable visual models from natural language supervision

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.808998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eaafc6a2-955a-4398-be50-710b96ee1bbd · outbound

This paper cites From causal to concept-based representation learning.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? From causal to concept-based representation learning

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.745438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b1be2ae5-3c93-49c1-b471-ee8a03720e5c · outbound

This paper cites Do concept bottleneck models obey locality? In XAI in Action: Past, Present, and Future Applications.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Do concept bottleneck models obey locality? In XAI in Action: Past, Present, and Future Applications

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.666355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eb36db5e-1c85-4750-b768-838fa62e19b0 · outbound

This paper cites Discover-then-name: Task-agnostic concept bottlenecks via automated concept discovery.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Discover-then-name: Task-agnostic concept bottlenecks via automated concept discovery

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.802215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation be13cee1-e19a-4db3-a929-f4a9469777cd · outbound

This paper cites Unpacking Large Language Models with Conceptual Consistency.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Unpacking Large Language Models with Conceptual Consistency

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.931738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a59b48be-debd-4518-8840-6c3175239559 · outbound

This paper cites C-SENN: Contrastive Self-Explaining Neural Network.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? C-SENN: Contrastive Self-Explaining Neural Network

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.926227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c27fbc80-2b92-4e96-b7a9-faf75508a927 · outbound

This paper cites Concept bottleneck model with additional unsupervised concepts.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept bottleneck model with additional unsupervised concepts

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.659898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c5e33c48-5601-483d-a146-33228a24ef0a · outbound

This paper cites New support vector algorithms.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? New support vector algorithms

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:56.026810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7601f959-b3cf-4526-bbe1-fa2b03615ff9 · outbound

This paper cites Toward causal representation learning.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Toward causal representation learning

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:56.023094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c82a67b-bc62-43fc-8adc-89d2b347102f · outbound

This paper cites Concept Bottleneck Models Without Predefined Concepts.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept Bottleneck Models Without Predefined Concepts

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.911180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b2acb5fd-85b4-4211-9a93-d181bb535560 · outbound

This paper cites Concept Embedding Analysis: A Review.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept Embedding Analysis: A Review

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.916022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dc399e8f-ebb8-4a45-839e-73d9cccf18ab · outbound

This paper cites A closer look at the intervention procedure of concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? A closer look at the intervention procedure of concept bottleneck models

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:56.018887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2a11c4c0-c2ed-4b30-acde-c9929c9278e1 · outbound

This paper cites VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:56.015119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d14f9393-1f1f-4a29-8bf2-665717a335e1 · outbound

This paper cites Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:56.010708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a0cdc651-8317-4f59-9002-f5f53f88c23d · outbound

This paper cites Learning to intervene on concept bottlenecks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Learning to intervene on concept bottlenecks

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:56.007146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2e122af5-9056-4364-83c4-e26c59f13775 · outbound

This paper cites Robustly disentangled causal mechanisms: Validating deep representations for interventional robustness.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Robustly disentangled causal mechanisms: Validating deep representations for interventional robustness

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:56.003092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1ac89ea6-6f5c-4c07-8dd7-af69607badae · outbound

This paper cites Leveraging explanations in interactive machine learning: An overview.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Leveraging explanations in interactive machine learning: An overview

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:55.995094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f1ff61a3-1a62-4fd6-9a44-e9c820cc171e · outbound

This paper cites Stochastic Concept Bottleneck Models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Stochastic Concept Bottleneck Models

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:54.936942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 069e7934-c0da-4e41-a9a5-564895900cc8 · outbound

This paper cites The caltech-ucsd birds-200-2011 dataset.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? The caltech-ucsd birds-200-2011 dataset

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:51:55.987536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 404c2e86-ed92-474c-a3e5-be7a2a54074d · outbound

This paper cites Leveraging sparse linear layers for debuggable deep networks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Leveraging sparse linear layers for debuggable deep networks

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.724065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f22d32f4-a6ef-4794-aaad-1a33c7f538e2 · outbound

This paper cites Language in a bottle: Language model guided concept bottlenecks for interpretable image classification.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Language in a bottle: Language model guided concept bottlenecks for interpretable image classification

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.733160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4f29be7e-cac8-4847-9ea5-076327f67684 · outbound

This paper cites On completeness-aware concept-based explanations in deep neural networks.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? On completeness-aware concept-based explanations in deep neural networks

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.761893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41938c65-3042-4641-aa69-bd352b9a093f · outbound

This paper cites Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-22T17:51:55.044662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 49113233-ca23-4ade-b08f-4a3c9aa7e4f8 · outbound

This paper cites Post-hoc concept bottleneck models.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Post-hoc concept bottleneck models

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.735734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7eb1b51c-1cf3-4ab4-8d09-3f822271cfff · outbound

This paper cites Concept embedding models: Beyond the accuracy-explainability trade-off.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Concept embedding models: Beyond the accuracy-explainability trade-off

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.782145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1e263fc0-a608-4596-ab73-064f3e4c2576 · outbound

This paper cites Towards robust metrics for concept representation evaluation.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Towards robust metrics for concept representation evaluation

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.656500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 428b766a-5b83-4a66-8bec-efd53ce008c3 · outbound

This paper cites The decoupling concept bottleneck model.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? The decoupling concept bottleneck model

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.645641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0621f669-58fd-4195-9100-5cea0a859da4 · outbound

This paper cites an unresolved cited work.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Unresolved cited work

Reference 87

Resolution: unresolved; raw_fallback, observed 2026-05-22T17:55:02.758295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d81006ff-2d86-42cd-b4dc-8def85312b07 · outbound

This paper cites an unresolved cited work.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Unresolved cited work

Reference 88

Resolution: unresolved; raw_fallback, observed 2026-05-22T17:55:02.673435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 44752683-bded-4801-909b-244002122647 · outbound

This paper cites Table 4: CBM architecture.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Table 4: CBM architecture

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.768358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 920a6096-bf41-44e0-8d45-1e5a747d64c6 · outbound

This paper cites an unresolved cited work.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Unresolved cited work

Reference 90

Resolution: unresolved; raw_fallback, observed 2026-05-22T17:55:02.826012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba0cfcbb-ba49-4e74-a15c-1f329b6ec145 · outbound

This paper cites an unresolved cited work.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? Unresolved cited work

Reference 91

Resolution: unresolved; raw_fallback, observed 2026-05-22T17:55:02.676695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4be8e12d-d7e8-4d83-bbe8-e817e6d838de · outbound

This paper cites This is an image of {class_name}. Does the image contain {prefix}{obj}{suffix}? Please reply only with ’Yes’ or ’No’.

If Concept Bottlenecks are the Question, are Foundation Models the Answer? This is an image of {class_name}. Does the image contain {prefix}{obj}{suffix}? Please reply only with ’Yes’ or ’No’

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:55:02.720859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation aef05719-d053-4e9d-8186-80bd2fa6d476 · inbound

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings cites this paper.

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings If Concept Bottlenecks are the Question, are Foundation Models the Answer?

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:45:20.921918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3283d952-6144-4bfb-acab-2803b9cc4c18 · inbound

A Geometric Unification of Concept Learning with Concept Cones cites this paper.

A Geometric Unification of Concept Learning with Concept Cones If Concept Bottlenecks are the Question, are Foundation Models the Answer?

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T18:02:44.865955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96aa147-f64a-4db7-93a0-b162fad3a5c8 · inbound

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation cites this paper.

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation If Concept Bottlenecks are the Question, are Foundation Models the Answer?

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T19:17:12.798847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.