Paper Citation Record · LEDGER

Multimodal Concept Bottleneck Models

As of 20 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2606.19882.

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

pith.paper-citation-record.v1
2606.19882 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T18:12:35.617577Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact6
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 20f49d24-095c-4e34-866a-3367cb7fc7f2 · outbound

This paper cites Network dissection: Quantifying interpretability of deep visual representations.

Multimodal Concept Bottleneck Models Network dissection: Quantifying interpretability of deep visual representations

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 786c37db-1348-49d8-a306-6cd53961f931 · outbound

This paper cites Interpreting clip with sparse linear concept embeddings (splice).

Multimodal Concept Bottleneck Models Interpreting clip with sparse linear concept embeddings (splice)

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1162b8e-a477-4b06-8867-c28366d6b7d2 · outbound

This paper cites Language models can ex- plain neurons in language models.

Multimodal Concept Bottleneck Models Language models can ex- plain neurons in language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e912fc3d-f3f7-48c8-a82e-bf4b3f7a3f55 · outbound

This paper cites Food-101–mining discriminative components with random forests.

Multimodal Concept Bottleneck Models Food-101–mining discriminative components with random forests

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6c4c0d-3430-4b5b-af45-41823ab36b30 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020.

Multimodal Concept Bottleneck Models Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c596c10-f0ce-42c2-9145-de8fbd135ee6 · outbound

This paper cites Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts.

Multimodal Concept Bottleneck Models Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c2ad9e0-01c3-4b63-a11f-aae6ec636a44 · outbound

This paper cites Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts.

Multimodal Concept Bottleneck Models Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-04T03:19:30.859785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8b4a94bd-e12c-462f-98dc-9c77992c0582 · outbound

This paper cites Describing textures in the wild.

Multimodal Concept Bottleneck Models Describing textures in the wild

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98937f8a-fb05-401c-9a52-4f54dbc7841b · outbound

This paper cites Imagenet: A large- scale hierarchical image database.

Multimodal Concept Bottleneck Models Imagenet: A large- scale hierarchical image database

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d0d2a1a-01ce-4053-a041-b2c715346f01 · outbound

This paper cites Multimodal neurons in artificial neural networks.Distill, 6(3): e30, 2021.

Multimodal Concept Bottleneck Models Multimodal neurons in artificial neural networks.Distill, 6(3): e30, 2021

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a4353b4-a152-4b83-ae13-aeb6dba0f39a · outbound

This paper cites Natural language descriptions of deep visual features.

Multimodal Concept Bottleneck Models Natural language descriptions of deep visual features

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f049e0a-0796-43dc-9359-0c572b3a77c6 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Multimodal Concept Bottleneck Models Distilling the Knowledge in a Neural Network

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-04T03:19:30.863434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0e06bde5-2d22-49be-862f-35b7279d582e · outbound

This paper cites Identifying interpretable subspaces in image representations.

Multimodal Concept Bottleneck Models Identifying interpretable subspaces in image representations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb36a0d3-ed76-4642-baa1-e0dc3537770c · outbound

This paper cites Concept-Monitor: Understanding DNN training through individual neurons.

Multimodal Concept Bottleneck Models Concept-Monitor: Understanding DNN training through individual neurons

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-04T03:19:30.873089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1026044e-a780-427a-90b8-65e1cded4668 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Multimodal Concept Bottleneck Models Adam: A Method for Stochastic Optimization

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-04T03:19:30.876576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0db8b6f7-241d-41d0-92df-579fd6a19d66 · outbound

This paper cites Concept bottleneck models.

Multimodal Concept Bottleneck Models Concept bottleneck models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66d17cb6-32f3-44e7-bc41-f3ca952a153f · outbound

This paper cites Learning multiple layers of features from tiny images.

Multimodal Concept Bottleneck Models Learning multiple layers of features from tiny images

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19324bf-993b-4a6e-93e0-10826f681886 · outbound

This paper cites Scaling language-image pre-training via masking.

Multimodal Concept Bottleneck Models Scaling language-image pre-training via masking

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a307b0bc-5537-410f-85d9-c8089b7f9ba0 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Multimodal Concept Bottleneck Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db67e001-86c2-4f64-9ed9-560c02826816 · outbound

This paper cites Visual classification via description from large language models.

Multimodal Concept Bottleneck Models Visual classification via description from large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1e0ebfd-a827-4103-b64c-915e5fdc0cdd · outbound

This paper cites Scaling open-vocabulary object detection.

Multimodal Concept Bottleneck Models Scaling open-vocabulary object detection

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a55da609-936c-498b-91d3-a4ea19789db5 · outbound

This paper cites Clip-dissect: Automatic description of neuron rep- resentations in deep vision networks.

Multimodal Concept Bottleneck Models Clip-dissect: Automatic description of neuron rep- resentations in deep vision networks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea735189-74e0-45cd-9475-b17a85b97666 · outbound

This paper cites Linear explanations for individual neurons.

Multimodal Concept Bottleneck Models Linear explanations for individual neurons

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa4fdee1-cde5-454c-9c50-824a08a101f5 · outbound

This paper cites Label-free concept bottleneck models.

Multimodal Concept Bottleneck Models Label-free concept bottleneck models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef33ff8c-4deb-45fd-851e-3aa242f00939 · outbound

This paper cites Cats and dogs.

Multimodal Concept Bottleneck Models Cats and dogs

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1e356e-1016-4961-a95d-8e8c61bcb74c · outbound

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

Multimodal Concept Bottleneck Models Learning transferable visual models from natural language supervision

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c964e39e-0e76-472a-81d9-e7bae10472e0 · outbound

This paper cites A multimodal automated interpretability agent.

Multimodal Concept Bottleneck Models A multimodal automated interpretability agent

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b41816cd-aafa-4edb-87aa-e27d22deee34 · outbound

This paper cites Incremental residual concept bottleneck models.

Multimodal Concept Bottleneck Models Incremental residual concept bottleneck models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a05bce4-3f27-4a00-8ed3-498a205d995c · outbound

This paper cites Vlg-cbm: Training concept bottleneck models with vision-language guidance.

Multimodal Concept Bottleneck Models Vlg-cbm: Training concept bottleneck models with vision-language guidance

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2dd615e-4616-49a5-9810-3d90b6d4c4c3 · outbound

This paper cites Concept bottleneck large language models.ICLR, 2025.

Multimodal Concept Bottleneck Models Concept bottleneck large language models.ICLR, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f83c3dc0-245c-4887-a12f-98279715968d · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

Multimodal Concept Bottleneck Models EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-04T03:19:30.880293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f04f4d69-635f-41fc-ad77-5074ffe9f096 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Multimodal Concept Bottleneck Models LLaMA: Open and Efficient Foundation Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-04T03:19:30.867589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 99c61470-4c20-4a3c-a99e-54686365482a · outbound

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

Multimodal Concept Bottleneck Models The caltech-ucsd birds-200-2011 dataset

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b9f6768-1828-4e28-b7cf-ca7e769cef23 · outbound

This paper cites Transformers: State-of- the-art natural language processing.

Multimodal Concept Bottleneck Models Transformers: State-of- the-art natural language processing

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 268141d5-7009-44e5-9ede-7d82e9526ec4 · outbound

This paper cites Learning concise and descriptive attributes for visual recognition.

Multimodal Concept Bottleneck Models Learning concise and descriptive attributes for visual recognition

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 663ab755-1748-43ec-9fd7-0daa699b4a7e · outbound

This paper cites Clip-kd: An empirical study of clip model distillation.

Multimodal Concept Bottleneck Models Clip-kd: An empirical study of clip model distillation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3762ca69-ff99-43a5-a062-dabd90e1f0fb · outbound

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

Multimodal Concept Bottleneck Models Language in a bottle: Language model guided concept bottlenecks for interpretable image classification

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d03897b8-3aa3-4689-9d60-ab40acae242a · outbound

This paper cites Post-hoc concept bottleneck models.

Multimodal Concept Bottleneck Models Post-hoc concept bottleneck models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b863f4f-148c-4e6e-b446-91dd09093298 · outbound

This paper cites Sigmoid loss for language image pre-training.

Multimodal Concept Bottleneck Models Sigmoid loss for language image pre-training

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5f2b45-7930-4bb1-948d-181a7e9c422b · outbound

This paper cites an unresolved cited work.

Multimodal Concept Bottleneck Models Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b20cca-72eb-4ce4-9131-3351e6506e32 · outbound

This paper cites Similarity is measured via cosine similarity in a joint text embedding space, combining features from the CLIP ViT-B/16 text encoder and the all-mpnet-base-v2 sentence encoder.

Multimodal Concept Bottleneck Models Similarity is measured via cosine similarity in a joint text embedding space, combining features from the CLIP ViT-B/16 text encoder and the all-mpnet-base-v2 sentence encoder

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41f79a20-8b01-4841-9642-dc253be217c2 · outbound

This paper cites If I had to describe this image using only one sentence with the words class, it would be:.

Multimodal Concept Bottleneck Models If I had to describe this image using only one sentence with the words class, it would be:

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91fb40ee-8073-4fb9-b410-09f62bd5b5f4 · outbound

This paper cites By removing negative values, we avoid this ambiguity.

Multimodal Concept Bottleneck Models By removing negative values, we avoid this ambiguity

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b955e9cf-4e16-4c69-bcf3-3b6d65407fb5 · outbound

This paper cites By zeroing out irrelevant (negative) dimensions, we strengthen the contribution of mean- ingful concepts.

Multimodal Concept Bottleneck Models By zeroing out irrelevant (negative) dimensions, we strengthen the contribution of mean- ingful concepts

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c505b7d4-13db-40e7-bee3-17d50e7a121e · outbound

This paper cites barbershop.

Multimodal Concept Bottleneck Models barbershop

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-26T18:12:35.617577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.