Paper Citation Record · LEDGER

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation

As of 15 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2607.07264.

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

pith.paper-citation-record.v1
2607.07264 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-09T16:02:19.673125Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

29 of 29 outbound references displayed

verified exact2
verified fuzzy27
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 289f2a91-7c6f-4731-8967-0a53a4c650b7 · outbound

This paper cites Network dissection: Quantifying inter- pretability of deep visual representations.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Network dissection: Quantifying inter- pretability of deep visual representations

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.278440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 99723147-7846-4f36-a0fb-772748630d16 · outbound

This paper cites Show and tell: Visually explainable deep neural nets via spatially-aware concept bot- tleneck models.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Show and tell: Visually explainable deep neural nets via spatially-aware concept bot- tleneck models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.293452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e6642720-fac7-4303-a5c2-babadb25fe38 · outbound

This paper cites Face: Faithful automatic concept extraction.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Face: Faithful automatic concept extraction

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.285535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 819230ee-5766-4f49-8cb0-e9f0065ad98a · outbound

This paper cites Svd based ini- tialization: A head start for nonnegative matrix factorization.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Svd based ini- tialization: A head start for nonnegative matrix factorization

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.283408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 736d073a-ff7d-4eb4-8a2e-1e67d2e94c9c · outbound

This paper cites What i cannot predict, i do not understand: A human- centered evaluation framework for explainability methods.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation What i cannot predict, i do not understand: A human- centered evaluation framework for explainability methods

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.264696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation df2ae4bb-efd3-4c13-86bf-b90515726fda · outbound

This paper cites Craft: Concept recursive activation factoriza- tion for explainability.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Craft: Concept recursive activation factoriza- tion for explainability

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.262361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8fd28372-0aee-4c18-b441-3f57c45d400c · outbound

This paper cites Towards automatic concept-based explanations.Ad- vances in neural information processing systems, 32.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Towards automatic concept-based explanations.Ad- vances in neural information processing systems, 32

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.280840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 810923d4-aa91-4b01-a7ff-9e1b815bd22f · outbound

This paper cites Natu- ral language descriptions of deep visual features.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Natu- ral language descriptions of deep visual features

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.271934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 72469b7a-0c4c-42b6-818f-2009a378d623 · outbound

This paper cites Interpretability be- yond feature attribution: Quantitative testing with concept activation vectors (tcav).

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Interpretability be- yond feature attribution: Quantitative testing with concept activation vectors (tcav)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.272135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b4755cd3-7286-4aa8-a319-5a133afcf8f8 · outbound

This paper cites Concept bottleneck models.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Concept bottleneck models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.316748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 52666593-b3d2-4120-870b-742e31686f06 · outbound

This paper cites The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery.Queue, 16(3):31–57, 2018.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery.Queue, 16(3):31–57, 2018

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.318776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c25d5f4c-8d60-4902-8dd7-3728b5f2d9a6 · outbound

This paper cites Interpretability Beyond Classification Output: Semantic Bottleneck Networks.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Interpretability Beyond Classification Output: Semantic Bottleneck Networks

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-09T16:06:20.126700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fab705de-19ba-42ea-a6b5-bf42e30150d2 · outbound

This paper cites General pitfalls of model-agnostic interpretation methods for machine learning models.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation General pitfalls of model-agnostic interpretation methods for machine learning models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.312838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation caeb69b5-5156-44e6-a551-09ae96f51dd9 · outbound

This paper cites The ef- fectiveness of feature attribution methods and its correlation with automatic evaluation scores.Advances in Neural Infor- mation Processing Systems, 34:26422–26436, 2021.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation The ef- fectiveness of feature attribution methods and its correlation with automatic evaluation scores.Advances in Neural Infor- mation Processing Systems, 34:26422–26436, 2021

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.314925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 23303b41-a0e2-48e2-8537-4bdfded247de · outbound

This paper cites CLIP-Dissect: Au- tomatic description of neuron representations in deep vision networks.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation CLIP-Dissect: Au- tomatic description of neuron representations in deep vision networks

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.320670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b866d18a-9973-4d76-8265-d92f11af25e0 · outbound

This paper cites Label-free concept bottleneck models.Inter- national Conference on Learning Representations (ICLR),.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Label-free concept bottleneck models.Inter- national Conference on Learning Representations (ICLR),

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.324832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6e8a5668-a411-436b-b94b-fc02edd77357 · outbound

This paper cites Rise: Random- ized input sampling for explanation of black-box models.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Rise: Random- ized input sampling for explanation of black-box models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.326787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e3c7904e-0c0b-43ba-802d-f798cec7028a · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Learning transferable visual models from natural language supervi- sion

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.315197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f960a210-b627-4dec-920e-4616668b4518 · outbound

This paper cites Stop explaining black box machine learn- ing models for high stakes decisions and use interpretable models instead.Nature machine intelligence, 1(5):206–215.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Stop explaining black box machine learn- ing models for high stakes decisions and use interpretable models instead.Nature machine intelligence, 1(5):206–215

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.308746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d9209762-a92c-4963-86c1-1207f9437653 · outbound

This paper cites Grad-cam: Visual explanations from deep networks via gradient-based localization.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Grad-cam: Visual explanations from deep networks via gradient-based localization

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.298307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1b94dbae-b384-4a69-a65a-5d9475a1a6f2 · outbound

This paper cites What does clip know about a red circle? vi- sual prompt engineering for vlms.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation What does clip know about a red circle? vi- sual prompt engineering for vlms

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.295698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 77fac8b3-c812-4fac-8b7e-42728b0737b5 · outbound

This paper cites Deep inside convolutional networks: Visualising image clas- sification models and saliency maps.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Deep inside convolutional networks: Visualising image clas- sification models and saliency maps

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.303713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c8ab7db6-880b-4416-b1c7-13482250ff0a · outbound

This paper cites SmoothGrad: removing noise by adding noise.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation SmoothGrad: removing noise by adding noise

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-09T16:06:20.121002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation db978a38-0c32-44a9-bdea-a0a9f332ed5c · outbound

This paper cites Axiomatic attribution for deep networks.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Axiomatic attribution for deep networks

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.293914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f7fbee07-7596-49d7-b9de-44a029e64b9e · outbound

This paper cites Discovering and mitigating biases in clip-based image editing.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Discovering and mitigating biases in clip-based image editing

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.319204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8f4c65d9-7b63-4fb8-a439-7265b575a2d1 · outbound

This paper cites Learning bottleneck concepts in image classification.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Learning bottleneck concepts in image classification

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.310705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7cf0ce78-b00f-41c5-8cd3-c8350929b901 · outbound

This paper cites Explain- ing deep convolutional neural networks via latent visual- semantic filter attention.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation Explain- ing deep convolutional neural networks via latent visual- semantic filter attention

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.322610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1db9d35e-9f22-4a0b-b794-e8abac4ed576 · outbound

This paper cites {class_name}.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation {class_name}

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.278164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 36eec6f1-ae63-4186-bd9b-ff8249863a8d · outbound

This paper cites skin irregularity.

Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation skin irregularity

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T16:06:20.274014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.