Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-07T15:35:54.665268Z
Paper Citation Record · LEDGER
Faithfulness to Refusal: A Causal Audit of Neuron Selectors
As of 21 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2607.05355.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
46 of 46 outbound references displayed
- verified exact24
- verified fuzzy13
- unresolved1
- parse uncertain0
- malformed identifier1
- metadata mismatch7
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 6da2afa2-43fe-4226-9f50-e4733afb1946 · outbound
This paper cites Zico Kolter.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Zico Kolter
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.523648Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 96b2f5ee-1cc4-496b-9590-d3da487be404 · outbound
This paper cites SparseGPT: Massive language models can be accurately pruned in one-shot.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors SparseGPT: Massive language models can be accurately pruned in one-shot
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.511755Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c59dc703-3380-4a39-b67f-736cb7b89049 · outbound
This paper cites Fluctuation-based Adaptive Structured Pruning for Large Language Models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Fluctuation-based Adaptive Structured Pruning for Large Language Models
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.909966Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 61efe5fe-b503-46c5-86e7-931ba7cd655c · outbound
This paper cites Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.892299Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation cceb53c6-24db-4d50-8293-a311b95066fb · outbound
This paper cites Programming Refusal with Conditional Activation Steering.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Programming Refusal with Conditional Activation Steering
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.898632Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation eb3e62a8-acfe-453a-bd60-ccc12a0dbe54 · outbound
This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Representation Engineering: A Top-Down Approach to AI Transparency
Reference 6
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-07T15:43:53.863779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 042b6874-1bc8-46ec-be70-e75fe7e2427a · outbound
This paper cites SORRY-Bench: Systematically evaluating large language model safety refusal.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors SORRY-Bench: Systematically evaluating large language model safety refusal
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.505898Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation b951f89c-121b-4456-b48b-850bf11e9d12 · outbound
This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors OR-Bench: An Over-Refusal Benchmark for Large Language Models
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.889765Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation f5973cc0-8987-4a04-9cc3-1ac5b384756b · outbound
This paper cites Measuring massive multitask language understanding.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Measuring massive multitask language understanding
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.517725Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c01ff444-064f-4729-a8f9-0232d40c5066 · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Training Verifiers to Solve Math Word Problems
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.902126Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 1c19e9bc-99ea-4050-a1fd-9fd11c993bf8 · outbound
This paper cites Instruction-Following Evaluation for Large Language Models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Instruction-Following Evaluation for Large Language Models
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.893629Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 67104967-58fd-405d-86b1-d0c621d121ae · outbound
This paper cites LLM-Pruner: On the structural pruning of large language models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors LLM-Pruner: On the structural pruning of large language models
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.521827Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c5aedfff-eb26-4c7e-aadc-5b0068e53646 · outbound
This paper cites Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.906269Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 560ee7f5-ea5d-42fe-a69b-cbe4beeff20e · outbound
This paper cites DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.913859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 0d0a2c7e-3ea0-4034-a08a-c1194f6de98d · outbound
This paper cites Interpretability in the wild: a circuit for indirect object identification in GPT-2 small.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Interpretability in the wild: a circuit for indirect object identification in GPT-2 small
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.513749Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 168627d5-b23e-4591-ad73-05745b4a230b · outbound
This paper cites Attribution Patching Outperforms Automated Circuit Discovery.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Attribution Patching Outperforms Automated Circuit Discovery
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.897504Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 9b7182de-857b-4a36-8972-dfe80719b0d5 · outbound
This paper cites Interpretability as alignment: Making internal understanding a design principle.CoRR, abs/2509.08592, 2025.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Interpretability as alignment: Making internal understanding a design principle.CoRR, abs/2509.08592, 2025
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-07-07T15:43:53.908829Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 4fab04d4-4f09-4589-b445-453868341d01 · outbound
This paper cites IEEE Transactions 16 G.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors IEEE Transactions 16 G
Reference 18
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-07T15:43:53.657088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 2f97c03a-780e-415f-ba2c-02e785d79504 · outbound
This paper cites A benchmark for interpretability methods in deep neural networks.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors A benchmark for interpretability methods in deep neural networks
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.525641Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 1e0aa72c-8beb-4696-9848-6bba359839dd · outbound
This paper cites xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.881038Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 909852c1-1854-4375-844c-01b0c4987eb5 · outbound
This paper cites Bridging the gap in XAI: Why reliable metrics matter for explainability and compliance.CoRR, abs/2502.04695, 2025.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Bridging the gap in XAI: Why reliable metrics matter for explainability and compliance.CoRR, abs/2502.04695, 2025
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-07-07T15:43:53.904793Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 377daa2a-4720-4253-986a-c95f635f2e7d · outbound
This paper cites Bach , author A.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Bach , author A
Reference 22
- Resolution
- metadata mismatch
- doi, observed 2026-07-07T15:43:53.659741Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 275eac8e-51de-4767-aa0a-21dc1e3dc36a · outbound
This paper cites Layer-Wise Relevance Propagation: An Overview.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Layer-Wise Relevance Propagation: An Overview
Reference 23
- Resolution
- verified exact
- doi, observed 2026-07-07T15:43:53.654205Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 09a6ea7a-cc09-45da-9891-151908096d0d · outbound
This paper cites AttnLRP: Attention-aware layer-wise relevance propagation for transformers.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors AttnLRP: Attention-aware layer-wise relevance propagation for transformers
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.509824Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 31f6a5a9-2383-4404-97e1-fdf03e1ac641 · outbound
This paper cites Axiomatic attribution for deep networks.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Axiomatic attribution for deep networks
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.515922Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation d6f85321-98e1-4a2f-80fe-16ad3cf1096d · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.887029Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation b4a8d865-44e5-48f6-8994-bd9970a4dc5d · outbound
This paper cites Manning, and Chelsea Finn.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Manning, and Chelsea Finn
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.527552Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 95d722af-9c35-4fe7-a40b-601d16ee0abf · outbound
This paper cites Steering Llama 2 via contrastive activation addition.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Steering Llama 2 via contrastive activation addition
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.519935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 12e66ce9-d268-42ff-b20e-82fd02b95cf3 · outbound
This paper cites Refusal in Language Models Is Mediated by a Single Direction.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Refusal in Language Models Is Mediated by a Single Direction
Reference 29
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.873280Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 4669ea2f-2c5e-4dd1-a35e-4804a3b3a840 · outbound
This paper cites Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Reference 30
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.891301Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 8d959f8d-bf88-4b6d-9326-b1334924beb8 · outbound
This paper cites $C$-$\Delta\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors $C$-$\Delta\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-07-09T02:20:28.526184Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 0c0e0164-f2e2-4e39-879a-bdc047d27aa2 · outbound
This paper cites Finding safety neurons in large language models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Finding safety neurons in large language models
Reference 32
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-07T15:43:53.896225Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation af26780e-7f3d-4c21-b934-219782f46033 · outbound
This paper cites Understanding Refusal in Language Models with Sparse Autoencoders.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Understanding Refusal in Language Models with Sparse Autoencoders
Reference 33
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-07T15:43:53.886128Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 7155bf8e-c5fb-40c5-a3a9-e2064a99674f · outbound
This paper cites Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.907407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 5e2630c0-1c0c-4584-8a62-33115ae6942c · outbound
This paper cites Zhihao Xu, Ruixuan Huang, Changyu Chen, and Xiting Wang.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Zhihao Xu, Ruixuan Huang, Changyu Chen, and Xiting Wang
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-07-07T15:43:53.911441Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 8f288f12-4014-4539-8a0c-e2819db0c2b6 · outbound
This paper cites A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.918407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 0167a8d0-3a29-412a-b279-98d46a0f3d6e · outbound
This paper cites Pointer Sentinel Mixture Models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Pointer Sentinel Mixture Models
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.899874Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation fe5f2f3c-af15-4556-bf71-c70c14257acc · outbound
This paper cites Lessons from the trenches on reproducible evaluation of language models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Lessons from the trenches on reproducible evaluation of language models
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.507768Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 335cc6a6-11c6-475b-8337-636697b944c3 · outbound
This paper cites Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Reference 39
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-07T15:43:53.912436Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 52ea2846-02d6-4141-8ca5-5954331ed0c0 · outbound
This paper cites The Llama 3 Herd of Models.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors The Llama 3 Herd of Models
Reference 40
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.919409Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation dd27a205-57d0-4578-9118-83502fec918d · outbound
This paper cites Qwen3 Technical Report.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Qwen3 Technical Report
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.917179Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation fd5e2386-f927-481e-b458-49da5e14aed1 · outbound
This paper cites Gemma 3 Technical Report.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Gemma 3 Technical Report
Reference 42
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T15:43:53.914693Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 67e42700-741e-49a8-b7f8-6e491a9ef6ae · outbound
This paper cites an unresolved cited work.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T15:43:54.529501Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation c3479814-c8db-469e-94dc-bd9121350fa7 · outbound
This paper cites ProtectAI/distilroberta-base-rejection-v1: Refusal classifier.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors ProtectAI/distilroberta-base-rejection-v1: Refusal classifier
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:43:54.504016Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 76ed441b-e597-4e4c-b7ff-e3ff1b875036 · outbound
This paper cites Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
Reference 45
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-07T15:43:53.916252Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 0373deb5-300e-428b-81ac-d8b607884a4d · outbound
This paper cites A coin flip for safety: Llm judges fail to reliably measure adversarial robustness.
Faithfulness to Refusal: A Causal Audit of Neuron Selectors A coin flip for safety: Llm judges fail to reliably measure adversarial robustness
Reference 46
- Resolution
- malformed identifier
- arxiv_id, observed 2026-07-07T15:43:53.903785Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Pith citing papers
No inbound Pith citation observations are available.