Paper Citation Record · LEDGER

Sparse Weight Decomposition for Efficient Circuit Extraction

As of 19 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2608.03913.

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

pith.paper-citation-record.v1
2608.03913 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:51:45.535835Z

measured 29 of 29 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

29 of 29 outbound references displayed

verified exact0
verified fuzzy9
unresolved14
parse uncertain0
malformed identifier2
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6005f08b-ad25-47f7-8eff-d13aa264cf79 · outbound

This paper cites Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition.

Sparse Weight Decomposition for Efficient Circuit Extraction Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.369902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05c33e9f-6889-4e0a-ab61-199066ff203e · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Sparse Weight Decomposition for Efficient Circuit Extraction Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.387638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f48cb468-8be0-4647-a67a-49a9b253f2e1 · outbound

This paper cites carapace length of 80–85millimetres.

Sparse Weight Decomposition for Efficient Circuit Extraction carapace length of 80–85millimetres

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T14:51:46.260341Z

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 b50f98d6-46c7-4ef7-9d67-6744f759626f · outbound

This paper cites 38 Sparse Weight Decomposition for Efficient Circuit Extraction Overall, the semantic audit gives the GreaterThan circuit a more concrete interpretation.

Sparse Weight Decomposition for Efficient Circuit Extraction 38 Sparse Weight Decomposition for Efficient Circuit Extraction Overall, the semantic audit gives the GreaterThan circuit a more concrete interpretation

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.242288Z

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 f9a56e2a-c4fa-4e2c-85c9-c6c31c2b212c · outbound

This paper cites Michael Hanna, Ollie Liu, and Alexandre Variengien.

Sparse Weight Decomposition for Efficient Circuit Extraction Michael Hanna, Ollie Liu, and Alexandre Variengien

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.416407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9912d223-490a-492a-b532-b8c93dcdff2e · outbound

This paper cites Quantized Sparse Weight Decomposition for Neural Network Compression.

Sparse Weight Decomposition for Efficient Circuit Extraction Quantized Sparse Weight Decomposition for Neural Network Compression

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T14:51:45.941434Z

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 22c9747d-9a7f-4a72-9fe1-961d3cf6930f · outbound

This paper cites blackboxnlp-1.19/.

Sparse Weight Decomposition for Efficient Circuit Extraction blackboxnlp-1.19/

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.356186Z

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 992567bb-0c6b-41f1-a3f6-db20834e2061 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Sparse Weight Decomposition for Efficient Circuit Extraction Locating and Editing Factual Associations in GPT

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.438683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70eb6597-7937-46c8-a84d-5df89c57a88e · outbound

This paper cites an unresolved cited work.

Sparse Weight Decomposition for Efficient Circuit Extraction Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T14:51:46.336254Z

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 2796d1bc-8276-497c-8dd6-0eb692ce0c7c · outbound

This paper cites Qwen2.5 Technical Report.

Sparse Weight Decomposition for Efficient Circuit Extraction Qwen2.5 Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.458729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb1f7540-8faa-4c8c-8c35-c8c8ac4430c4 · outbound

This paper cites Circuit Claims Depend on What Is Extracted and How It Is Compared.

Sparse Weight Decomposition for Efficient Circuit Extraction Circuit Claims Depend on What Is Extracted and How It Is Compared

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T14:51:45.875505Z

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 ad333629-f63a-4a77-ad7e-d4d42b1e86f8 · outbound

This paper cites Attribution Patching Outperforms Automated Circuit Discovery.

Sparse Weight Decomposition for Efficient Circuit Extraction Attribution Patching Outperforms Automated Circuit Discovery

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.470844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae440e3-7aaa-44db-947e-20de56584480 · outbound

This paper cites ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models.

Sparse Weight Decomposition for Efficient Circuit Extraction ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.487863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8970be27-53e1-4c52-bbc1-0bfba10cbed1 · outbound

This paper cites Identifiability in Two-Layer Sparse Matrix Factorization.

Sparse Weight Decomposition for Efficient Circuit Extraction Identifiability in Two-Layer Sparse Matrix Factorization

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T14:51:45.684045Z

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 0ad2f541-e3f8-4c1f-a63a-f88368794091 · outbound

This paper cites Dτ,train,Dτ,test Training and held-out evaluation splits for circuit taskτ.

Sparse Weight Decomposition for Efficient Circuit Extraction Dτ,train,Dτ,test Training and held-out evaluation splits for circuit taskτ

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.316729Z

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 f891f3f8-bbb8-4486-8133-0175a9fca4e2 · outbound

This paper cites SWD exposes bottleneck units, Transcoders expose hidden features, and the VPD variants expose parameter components.

Sparse Weight Decomposition for Efficient Circuit Extraction SWD exposes bottleneck units, Transcoders expose hidden features, and the VPD variants expose parameter components

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.296385Z

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 41e8763b-9e0e-4b29-8caf-e87cb6c7f9cd · outbound

This paper cites These task examples are separate from the FineWeb- Edu data above and are not counted as replacement fitting or training data.

Sparse Weight Decomposition for Efficient Circuit Extraction These task examples are separate from the FineWeb- Edu data above and are not counted as replacement fitting or training data

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.278815Z

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 ff8c24d3-9663-4783-a499-812665d1aef2 · outbound

This paper cites Finally, we remove q266 from the reconstructed Q slice and recompute the head.

Sparse Weight Decomposition for Efficient Circuit Extraction Finally, we remove q266 from the reconstructed Q slice and recompute the head

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.221085Z

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 2a73696d-24f0-451b-9403-632189b9abec · outbound

This paper cites Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, Janos Kramar, Anca Dragan, Rohin Shah, and Neel Nanda.

Sparse Weight Decomposition for Efficient Circuit Extraction Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, Janos Kramar, Anca Dragan, Rohin Shah, and Neel Nanda

Reference 1999

Resolution: malformed identifier; no resolver link, observed 2026-08-15T14:51:45.427154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b6cba91-b16a-4c16-b976-b1f8874741f8 · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

Sparse Weight Decomposition for Efficient Circuit Extraction Transcoders Find Interpretable LLM Feature Circuits

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.393010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a1c0da7-e3ca-44ca-8413-8645cd5cb1d0 · outbound

This paper cites Vladimir Boza and Vladimir Macko.

Sparse Weight Decomposition for Efficient Circuit Extraction Vladimir Boza and Vladimir Macko

Reference 2011

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.364316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72f1a9de-8044-4852-a699-3c056932cbce · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Sparse Weight Decomposition for Efficient Circuit Extraction Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.476832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bed3d5c-0e61-4af8-b32f-ed3c0e002bda · outbound

This paper cites URL https://distill.pub/2020/circuits/zoom-in/.

Sparse Weight Decomposition for Efficient Circuit Extraction URL https://distill.pub/2020/circuits/zoom-in/

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.446289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec1f85b4-42c7-4f2f-ba78-9f8326b6404d · outbound

This paper cites pub/2021/framework/index.html.

Sparse Weight Decomposition for Efficient Circuit Extraction pub/2021/framework/index.html

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.402059Z

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 123977a7-cab9-4ec0-bd9d-2df76cf2698d · outbound

This paper cites Gabriel Franco and Mark Crovella.

Sparse Weight Decomposition for Efficient Circuit Extraction Gabriel Franco and Mark Crovella

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.380327Z

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 f56f7f7f-934f-4861-942b-5d96df0a3784 · outbound

This paper cites Stochastic Parameter Decomposition.

Sparse Weight Decomposition for Efficient Circuit Extraction Stochastic Parameter Decomposition

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.375704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53dd4fd6-7ad4-406b-af66-68fb7640060e · outbound

This paper cites Sparse Attention Decomposition Applied to Circuit Tracing.

Sparse Weight Decomposition for Efficient Circuit Extraction Sparse Attention Decomposition Applied to Circuit Tracing

Reference 2024

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T14:51:46.068212Z

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 a062b63b-bf26-4f57-8abd-38191b80c5b6 · outbound

This paper cites Adithya Bhaskar, Alexander Wettig, Dan Friedman, and Danqi Chen.

Sparse Weight Decomposition for Efficient Circuit Extraction Adithya Bhaskar, Alexander Wettig, Dan Friedman, and Danqi Chen

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:51:46.420948Z

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 5066514a-4879-41ff-a1c2-117d1a2d8566 · outbound

This paper cites Towards Automated Circuit Discovery for Mechanistic Interpretability.

Sparse Weight Decomposition for Efficient Circuit Extraction Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:45.381843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.