Paper Citation Record · LEDGER

Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 27 inbound Pith citation observations for arXiv:2004.03685.

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

pith.paper-citation-record.v1
2004.03685 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:58:17.441272Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

3
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 6c549149-e58f-4146-9a15-d32c92a0e7ad · inbound

Can Highlighting Help GitHub Maintainers Track Security Fixes? cites this paper.

Can Highlighting Help GitHub Maintainers Track Security Fixes? Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T18:21:53.023803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6891de37-cbc3-4af0-9992-d7d3a4e7fe83 · inbound

Trading off performance and human oversight in algorithmic policy: evidence from Danish college admissions cites this paper.

Trading off performance and human oversight in algorithmic policy: evidence from Danish college admissions Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-12T14:33:05.892126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8dd5ced-db62-426d-9194-bad775103c6e · inbound

Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretation cites this paper.

Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretation Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T13:54:19.200610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a55df274-acde-49ce-8b9a-31ca6e593496 · inbound

Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry cites this paper.

Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:09.217779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381e743a-25dd-4ef1-bbe2-553b2c6271bb · inbound

Saliency Maps are Ambiguous: Analysis of Logical Relations on First and Second Order Attributions cites this paper.

Saliency Maps are Ambiguous: Analysis of Logical Relations on First and Second Order Attributions Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T15:27:09.284368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f3e675-ec59-4f1b-84a9-fb93930630b4 · inbound

Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models cites this paper.

Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:18.592270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e4bd28-d7fd-4153-b97a-de29019a3d39 · inbound

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation cites this paper.

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:24:12.939349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8e6d4a98-a57d-40cc-92fd-d0c0588f4334 · inbound

Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation cites this paper.

Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T23:42:16.155459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aae81161-666e-46f8-bddc-074202368d01 · inbound

From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection cites this paper.

From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T22:58:17.441272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc2257dd-6127-46a0-8952-654903fb1847 · inbound

Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation cites this paper.

Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:50:57.341717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dbf8adf-6ac6-45cf-8ba0-dd568b3b27c5 · inbound

Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI cites this paper.

Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:36:55.267611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8de6399-abc5-4603-904f-40bdfb6337e9 · inbound

Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks cites this paper.

Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:41.574862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34491400-e581-485d-9654-5ade983b4683 · inbound

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning cites this paper.

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T22:03:53.317192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83e7198-c038-4bfa-bf77-24b97957efa9 · inbound

RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring cites this paper.

RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T13:25:33.637399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3aa93a4-2d37-401b-8c92-6ad315cc6e44 · inbound

Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE cites this paper.

Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-05T10:53:13.494046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 814a0102-71c3-49a0-b3bd-18fdf7068476 · inbound

From "Thinking" to "Justifying": Aligning High-Stakes Explainability with Professional Communication Standards cites this paper.

From "Thinking" to "Justifying": Aligning High-Stakes Explainability with Professional Communication Standards Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T11:13:02.901696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61670a5b-28e9-4d2a-8f8d-3fa2f17dfc43 · inbound

AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency cites this paper.

AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T08:22:37.726609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d6c65d18-85e5-4de8-91b8-fec4ad490dd9 · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 174

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:17:54.126904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4aee0039-dc1a-42e9-97d0-00ff4f233e28 · inbound

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation cites this paper.

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T18:58:53.903254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8b77968e-2eb4-4a96-9a8c-932c86d39fb6 · inbound

Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models cites this paper.

Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:53:19.780963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 06e4df51-5246-48c5-ab27-3a121c5044e6 · inbound

Evaluating Multi-turn Human-AI Interaction cites this paper.

Evaluating Multi-turn Human-AI Interaction Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 68

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T08:33:24.502547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 08092af8-adb8-449b-ae85-a6b8f5f4a5ee · inbound

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift cites this paper.

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:16:16.171224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bf1de9a5-9280-4bf8-a9b9-9da15cea9f88 · inbound

Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness cites this paper.

Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T13:33:28.518212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a9a9feff-ff7f-41b0-932c-c00b9985c9ef · inbound

Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation cites this paper.

Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T07:36:45.033044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation eeb25dee-4f62-4296-a873-d0bc47cdaaf2 · inbound

BetXplain: An Explanation-Annotated Dataset for Detecting Manipulative Betting Advertisements on Social Media cites this paper.

BetXplain: An Explanation-Annotated Dataset for Detecting Manipulative Betting Advertisements on Social Media Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 162

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T13:19:50.834040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e6dda2d9-e21e-44c8-aa5a-8140c196a689 · inbound

Training Large Language Models for Self-Explanation Faithfulness cites this paper.

Training Large Language Models for Self-Explanation Faithfulness Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T08:36:20.018806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7b9120-3891-4c8d-9f4e-f7fed7aec933 · inbound

Training Large Language Models for Self-Explanation Faithfulness cites this paper.

Training Large Language Models for Self-Explanation Faithfulness Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-01T08:36:25.926829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.