Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T05:34:17.124607Z
Paper Citation Record · LEDGER
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models
As of 20 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 1 inbound Pith citation observation for arXiv:2506.07691.
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 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-16T12:39:57.398423Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-16T12:40:54.631111Z
Reference resolution
13 of 13 outbound references displayed
- verified exact0
- verified fuzzy2
- unresolved9
- parse uncertain0
- malformed identifier2
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 08ca7d9b-87b9-4f5e-a67a-299edeba5af2 · outbound
This paper cites an unresolved cited work.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:34:17.273718Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation de6ff38d-ec3f-4cf4-99ae-b94a322e090d · outbound
This paper cites an unresolved cited work.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Unresolved cited work
Reference 2
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:34:17.262760Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7fce8e1f-f722-47c9-9806-f37594d71c6c · outbound
This paper cites s race, Olympic 5,000m champion Vivian Cheruiyot of Kenya won in her first half marathon.\nScotland\.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models s race, Olympic 5,000m champion Vivian Cheruiyot of Kenya won in her first half marathon.\nScotland\
Reference 3
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-07T05:34:17.252015Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation f1981c74-bfaf-4316-8742-3477df155798 · outbound
This paper cites The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence
Reference 4
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-07T05:34:17.091507Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 65404a69-f3f1-4509-b66a-41cbe1ecc4b7 · outbound
This paper cites an unresolved cited work.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:34:17.240010Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 91b95826-ccac-46d5-8585-1b5da3833707 · outbound
This paper cites an unresolved cited work.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:34:17.229598Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 103b8d1c-ab56-412c-b594-03eb8be997a1 · outbound
This paper cites an unresolved cited work.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:34:17.217951Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4edd5ce9-ae19-4793-9c9b-1c44e1b9095d · outbound
This paper cites <|im_start|>.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models <|im_start|>
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:34:17.208399Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 72a1b87e-d1c0-47d7-ac09-78d05d9cb1a9 · outbound
This paper cites an unresolved cited work.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:34:17.198085Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 87716a8e-872d-4f6b-89e7-d05a2e461ab8 · outbound
This paper cites <|start_header_id|>.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models <|start_header_id|>
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:34:17.187700Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 14312ea5-af76-4916-a670-132b28bc9122 · outbound
This paper cites AgentInstruct: Toward Generative Teaching with Agentic Flows.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models AgentInstruct: Toward Generative Teaching with Agentic Flows
Reference 2013
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:34:17.083688Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 07ded49c-03ab-430a-a857-fa707bda04f0 · outbound
This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Improving Dictionary Learning with Gated Sparse Autoencoders
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:34:17.087783Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8c1c0a91-2136-4f85-8932-070813fb987f · outbound
This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:34:17.079488Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation bddde6e3-c408-4460-835a-9b565d8be809 · inbound
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models
Reference 169
- Resolution
- verified exact
- arxiv_id, observed 2026-07-21T02:22:23.844867Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.