Paper Citation Record · LEDGER

Knowledge Neurons in Pretrained Transformers

As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 31 inbound Pith citation observations for arXiv:2104.08696.

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

pith.paper-citation-record.v1
2104.08696 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 31 of 31 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 31 of 31 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:37:56.902551Z

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

42
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 fd415246-94a6-458e-98a3-be0a638c2aeb · inbound

GPT-NeoX-20B: An Open-Source Autoregressive Language Model cites this paper.

GPT-NeoX-20B: An Open-Source Autoregressive Language Model Knowledge Neurons in Pretrained Transformers

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-24T12:34:28.368782Z

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 1304339b-c5f8-4f6e-801c-1fb3df7bf0e5 · inbound

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling cites this paper.

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling Knowledge Neurons in Pretrained Transformers

Reference 146

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:45:17.741750Z

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 26f81c94-0a26-4ad4-b8ae-e6875d100bac · inbound

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation cites this paper.

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation Knowledge Neurons in Pretrained Transformers

Reference 138

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:56:23.415905Z

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 1c06dc29-88dd-4d94-8401-5d1dae438d87 · inbound

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models cites this paper.

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models Knowledge Neurons in Pretrained Transformers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:56.902551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471b2b56-b5ad-45cc-92e4-9259004b0f83 · inbound

Towards a Science of Causal Interpretability in Deep Learning for Software Engineering cites this paper.

Towards a Science of Causal Interpretability in Deep Learning for Software Engineering Knowledge Neurons in Pretrained Transformers

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T15:29:50.727326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0daf8a15-2d6a-4b70-8464-3db14bdaaaf6 · inbound

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs cites this paper.

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs Knowledge Neurons in Pretrained Transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:01:15.482314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8655f5-1f3f-47ba-b36d-2ec22f393a16 · inbound

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models cites this paper.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Knowledge Neurons in Pretrained Transformers

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.445140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b277f457-bf29-4123-a67d-9a56eab948d0 · inbound

TRACE for Tracking the Emergence of Semantic Representations in Transformers cites this paper.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Knowledge Neurons in Pretrained Transformers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:10.581513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c6b2c78-02bb-4e00-b1b2-7c7666218dfa · inbound

A Graph Perspective to Probe Structural Patterns of Knowledge in Large Language Models cites this paper.

A Graph Perspective to Probe Structural Patterns of Knowledge in Large Language Models Knowledge Neurons in Pretrained Transformers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:14.587960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df639f4c-da81-48cd-8826-711e4cb44b8a · inbound

Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities cites this paper.

Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities Knowledge Neurons in Pretrained Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:43:20.561182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef4f804c-3d72-48a3-bd26-cb370bd77d53 · inbound

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting cites this paper.

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting Knowledge Neurons in Pretrained Transformers

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:15:55.841089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd85d045-d595-4567-9672-723e93756b34 · inbound

Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization cites this paper.

Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization Knowledge Neurons in Pretrained Transformers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:04:51.455988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 537dc18c-1cbf-4940-84d7-b3f9abf6ee1e · inbound

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis cites this paper.

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis Knowledge Neurons in Pretrained Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:54:26.227834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5152826f-02a9-45ee-b7b4-2a6667c24a56 · inbound

Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs cites this paper.

Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs Knowledge Neurons in Pretrained Transformers

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:53:04.139080Z

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 5b74a649-33b4-4b3c-a370-b2692a9d0bf9 · inbound

QF: Quick Feedforward AI Model Training without Gradient Back Propagation cites this paper.

QF: Quick Feedforward AI Model Training without Gradient Back Propagation Knowledge Neurons in Pretrained Transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:57:55.322574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49ff2f9e-cc47-4ab3-90bf-13a3c5f955f4 · inbound

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models cites this paper.

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models Knowledge Neurons in Pretrained Transformers

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T20:03:45.306645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8add6027-20fe-4941-adcf-8e0ad70d6728 · inbound

What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests cites this paper.

What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests Knowledge Neurons in Pretrained Transformers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:33.568852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 593048a1-e30d-43f1-a342-4f464c232644 · inbound

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations cites this paper.

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations Knowledge Neurons in Pretrained Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T05:30:17.038384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44ec3d41-53c9-4d3c-8cf3-2c365e167fb9 · inbound

Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens cites this paper.

Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens Knowledge Neurons in Pretrained Transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T11:15:19.454823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6140211b-78a6-43e0-861f-4a3a7deab941 · inbound

Representation-Guided Parameter-Efficient LLM Unlearning cites this paper.

Representation-Guided Parameter-Efficient LLM Unlearning Knowledge Neurons in Pretrained Transformers

Reference 104

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:06:19.318927Z

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 e552068b-6ea3-4b29-9aa9-8d4957107d3b · inbound

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation cites this paper.

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation Knowledge Neurons in Pretrained Transformers

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:11:10.247203Z

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 f1e9da35-9720-463a-8b89-4401bc9c80b0 · inbound

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation cites this paper.

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation Knowledge Neurons in Pretrained Transformers

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:21:26.922333Z

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 291f1369-b205-4e69-8052-b59c779d33e0 · inbound

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender cites this paper.

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender Knowledge Neurons in Pretrained Transformers

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T04:52:16.737390Z

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 b1c93311-09dd-467b-a3fc-f13222efeb15 · inbound

FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation cites this paper.

FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation Knowledge Neurons in Pretrained Transformers

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:26:17.391096Z

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 166a21a5-bf99-41ed-8a3e-7a19b3991b3d · inbound

Why Muon Outperforms Adam: A Curvature Perspective cites this paper.

Why Muon Outperforms Adam: A Curvature Perspective Knowledge Neurons in Pretrained Transformers

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-07-02T07:06:44.945453Z

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 28b5f54d-5508-44bf-9363-07afe0bb59e5 · inbound

Factual Retrieval in LLMs Is a Redundant, Distributed and Non-Contiguous Process cites this paper.

Factual Retrieval in LLMs Is a Redundant, Distributed and Non-Contiguous Process Knowledge Neurons in Pretrained Transformers

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T06:19:38.865535Z

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 4da5e687-a263-4340-ba37-306d02f079e7 · inbound

Exposing the Illusion of Erasure in Knowledge Editing for LLMs cites this paper.

Exposing the Illusion of Erasure in Knowledge Editing for LLMs Knowledge Neurons in Pretrained Transformers

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:09:44.329523Z

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 f790970d-bd63-4c59-a8ec-0d1b7f37df22 · inbound

Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation cites this paper.

Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation Knowledge Neurons in Pretrained Transformers

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:45:40.552266Z

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 cdf0d6e8-40f9-460f-8e5a-8d27ecab3064 · inbound

Break Through the Compression Bottleneck: From Theory to Practice cites this paper.

Break Through the Compression Bottleneck: From Theory to Practice Knowledge Neurons in Pretrained Transformers

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T14:29:31.857953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8095d1a4-8f2e-405c-b549-a5491e2c186d · inbound

Context-Adaptive Inference: A Unified Statistical and Foundation-Model View cites this paper.

Context-Adaptive Inference: A Unified Statistical and Foundation-Model View Knowledge Neurons in Pretrained Transformers

Reference 204

Resolution: unresolved; no resolver link, observed 2026-07-31T23:53:01.327684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49ef6bcf-eec6-47e2-9a44-36c33787a5d0 · inbound

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations cites this paper.

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations Knowledge Neurons in Pretrained Transformers

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T11:25:39.503891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.