Paper Citation Record · LEDGER

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

As of 12 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2606.18383.

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

pith.paper-citation-record.v1
2606.18383 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T01:27:56.855130Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

16 of 16 outbound references displayed

verified exact4
verified fuzzy0
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 89eeac66-55ea-4a5c-a881-22a886e1167a · outbound

This paper cites Stronger generalization bounds for deep nets via a compression approach.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Stronger generalization bounds for deep nets via a compression approach

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T20:18:56.766065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b3b37222-46dd-459d-966b-cc9f53167cb8 · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T20:18:56.761844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 63153587-eed2-4108-9ade-f962d7f6d679 · outbound

This paper cites Information Processing Let- ters 24, 377–380.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Information Processing Let- ters 24, 377–380

Reference 3

Resolution: metadata mismatch; doi, observed 2026-06-27T01:30:20.471021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 016c58c8-7493-4db0-b855-bfafed6d5424 · outbound

This paper cites Cunningham, H., Ewart, A., Riggs, L., Huben, R., and Sharkey, L.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Cunningham, H., Ewart, A., Riggs, L., Huben, R., and Sharkey, L

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T01:27:56.855130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c273ea77-c7e6-4d28-a8dd-06b0ca044a85 · outbound

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

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-03T20:18:56.776980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 12e20681-664f-488e-bab0-08a5f8e6a0cc · outbound

This paper cites Toy Models of Superposition.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Toy Models of Superposition

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-03T20:18:56.785092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f24754c5-fc76-489b-88db-d4dc9f5640d5 · outbound

This paper cites The Llama 3 Herd of Models.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability The Llama 3 Herd of Models

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T20:18:56.781308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 59979a45-5c0e-41ff-815a-42c9a1485825 · outbound

This paper cites Uniform convergence may be unable to explain generalization in deep learning.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Uniform convergence may be unable to explain generalization in deep learning

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:18:56.775223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a61ff091-af2c-4660-86c4-fbeb22877652 · outbound

This paper cites year =.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability year =

Reference 9

Resolution: metadata mismatch; doi, observed 2026-06-27T01:30:20.472795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation edcbd50a-56c8-4630-93d1-403290c8e64f · outbound

This paper cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T20:18:56.780715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cd3f17b6-ca41-4e8f-904c-5d481a0fb1e6 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Gemma 2: Improving Open Language Models at a Practical Size

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-03T20:18:56.784873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5a6623b3-a7fa-4cfa-aafd-57709c3d4a37 · outbound

This paper cites LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:18:56.788813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 469dadfe-9cfc-4d8e-8c6c-50b1da48d80e · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T20:18:56.769655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 495947bf-f51c-4794-bd4f-7889bedf59e2 · outbound

This paper cites Understanding deep learning requires rethinking generalization.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Understanding deep learning requires rethinking generalization

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-03T20:18:56.764563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 08355557-7e21-45bc-b1c3-77ce3d9fc0e0 · outbound

This paper cites The layerwise sweeps in Section 5.2 and Appendix E use additional layer-specific checkpoints where needed.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability The layerwise sweeps in Section 5.2 and Appendix E use additional layer-specific checkpoints where needed

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T01:27:56.855130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e71a5b84-83a1-4501-940e-1c384eb3c1cc · outbound

This paper cites an unresolved cited work.

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability Unresolved cited work

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-06-27T01:27:56.855130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.