Pith. sign in

Paper Citation Record · LEDGER

Teach Old SAEs New Domain Tricks with Boosting

As of 8 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 1 inbound Pith citation observation for arXiv:2507.12990.

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

pith.paper-citation-record.v1
2507.12990 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:40:29.681728Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T08:14:58.183289Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-22T08:16:16.162543Z

Reference resolution

12 of 12 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved12
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1d60d8f4-3f94-4fa9-b990-187622944869 · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

Teach Old SAEs New Domain Tricks with Boosting Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:28.821951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:28.821951Z digest=sha256:7b1b865b81a9ad5f912b6c94287749b27dc6a49d069b237f7dbd2684112661d7

Observation 20a638ac-b106-4a4f-899e-fef1eeb8d33a · outbound

This paper cites Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models.

Teach Old SAEs New Domain Tricks with Boosting Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:29.147549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:29.147549Z digest=sha256:2b068d0e7c2ffd3e972c9d9239dc2242ae7c59c2ec8e0c25dbc5206199bda867

Observation 1fa2e4f4-ff2f-4a37-8432-6e53d00249bd · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

Teach Old SAEs New Domain Tricks with Boosting The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:29.406481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:29.406481Z digest=sha256:467333fc52fcdfbaa5fb2d670ea708d342fce9f9aa817927b8737fd9353aaee4

Observation 372e9581-3871-442d-b829-883b65882908 · outbound

This paper cites The Llama 3 Herd of Models.

Teach Old SAEs New Domain Tricks with Boosting The Llama 3 Herd of Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:29.517427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:29.517427Z digest=sha256:635cef819ef41fa2e118f54804f31a71b01988a1d10294a4312103953296911f

Observation 089f207b-d345-4593-bddc-eebe0bd4b1a4 · outbound

This paper cites Qwen2.5 Technical Report.

Teach Old SAEs New Domain Tricks with Boosting Qwen2.5 Technical Report

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:29.601108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:29.601108Z digest=sha256:95c55eda1ad46714afe6ee5d5510d0a7cc23a74a7862f0fbe681abd68480c5b6

Observation a0f9b6f5-2760-42fe-8ec5-240c67a7547e · outbound

This paper cites an unresolved cited work.

Teach Old SAEs New Domain Tricks with Boosting Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:40:30.159519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:40:29.654256Z digest=sha256:a3738ece16a5be2781d4143f8f0cd6af8e8d87c334cdfa83c5049166f0d09cd3

Observation eb9580bd-d1d6-4acd-8d07-e1ea1f0c7fd6 · outbound

This paper cites an unresolved cited work.

Teach Old SAEs New Domain Tricks with Boosting Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:40:30.076624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:40:29.681728Z digest=sha256:d2bc54e23f67ca64b44868af6df140bc823f4d1689c3f45e4ec85fd3529d58fe

Observation cc944e05-a04d-4239-905f-0ffb17c18ff6 · outbound

This paper cites Automatically Interpreting Millions of Features in Large Language Models.

Teach Old SAEs New Domain Tricks with Boosting Automatically Interpreting Millions of Features in Large Language Models

Reference 1997

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:29.278577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:29.278577Z digest=sha256:9e9d480ffd74b20cf6ca75b0ae82073a665c7e00441c32c326bf296a4294262f

Observation 6529e8df-4036-4420-b4b5-9d44a9550412 · outbound

This paper cites Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset.

Teach Old SAEs New Domain Tricks with Boosting Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:28.933519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:28.933519Z digest=sha256:efd3565da8061eb2c7e3a387a09263fb5e6acc25a602c626084753fc4d6a5bbc

Observation 5a162d6b-bec4-437f-8c9e-301b39106c74 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Teach Old SAEs New Domain Tricks with Boosting Scaling and evaluating sparse autoencoders

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:28.648847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:28.648847Z digest=sha256:95f8b0c01b31bd8c1f620724cd8e0fead7e0a316af9abbb012584c4f85ac066a

Observation 503c8aa7-78ce-41e5-a7a7-b42dcd033de9 · outbound

This paper cites BatchTopK Sparse Autoencoders.

Teach Old SAEs New Domain Tricks with Boosting BatchTopK Sparse Autoencoders

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:28.594279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:28.594279Z digest=sha256:b6088b127a26bd73b9bf43a1fae962eb0758606786da5504a48c8a92807a69ac

Observation 158f39e2-2786-4adc-92dc-0e2a90c0ce6f · outbound

This paper cites Sparse Autoencoders Do Not Find Canonical Units of Analysis.

Teach Old SAEs New Domain Tricks with Boosting Sparse Autoencoders Do Not Find Canonical Units of Analysis

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-06T16:40:29.030274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:40:29.030274Z digest=sha256:eaee854ec5cec8723fed8e2d1c02dffce2e28abcd8579688a324feb211a47f5c

Pith citing papers

Observation b02d0ced-ac05-4f59-8e64-7569f76f6183 · inbound

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift cites this paper.

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift Teach Old SAEs New Domain Tricks with Boosting

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-05-22T08:16:16.165688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-22T08:14:58.183289Z digest=sha256:7dd95de9da52de14a920314840c21fcdbe92d9f02e9048d91ac010c1a7462a6a