Paper Citation Record · LEDGER

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders

As of 21 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 1 inbound Pith citation observation for arXiv:2507.06427.

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

pith.paper-citation-record.v1
2507.06427 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:08:52.099815Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-08T10:11:08.494758Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T20:11:08.877849Z

Reference resolution

49 of 49 outbound references displayed

verified exact7
verified fuzzy0
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ab8b8f95-cf81-4536-80bf-75cdb468943c · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:46.060796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3e67fdb-f2c5-40cb-8864-0f087b518038 · outbound

This paper cites GPT-4 Technical Report.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:46.230370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed345162-ca83-44fe-ad4a-debef9442eea · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:58.024755Z

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 3d9d2e91-eb36-4666-8ce2-c014b90fdd63 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:57.730664Z

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 54c11c5c-9f3e-4799-b36d-f0f5ad0eb6c1 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:46.643752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c1d05bd-8e54-401f-b484-3b90dd1e4bc3 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:46.772226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e71f98ff-2b8a-4228-932a-9615db113ff5 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:57.470098Z

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 1c119a47-a20f-491c-83e8-b4af39fd98c7 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:57.159111Z

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 429baa21-1390-47d3-a133-92fe06135784 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:47.108069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01a43aa9-db7d-493f-8520-d818865ae0f4 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:56.861735Z

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 2919df94-e454-4fd9-b141-0bb1fd771f83 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:47.345676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1a8fd59-1bfb-48e5-a104-11aadf4cc0b4 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:56.541073Z

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 a93abc0d-b0ea-4075-9382-758054498912 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:47.558744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4225a1f7-d641-4ceb-b04d-07257867a846 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:47.677008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f07abac1-dd31-4d13-acaf-60c95fc5fa81 · outbound

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

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:47.814426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d74be020-3136-4b7b-941f-969e8262d13b · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:47.926750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5380d9c0-395a-4593-8632-93ca056a610d · outbound

This paper cites Towards A Rigorous Science of Interpretable Machine Learning.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Towards A Rigorous Science of Interpretable Machine Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:48.044298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 435d078b-e1d3-4eac-81cb-92bd297a1022 · outbound

This paper cites The Llama 3 Herd of Models.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:48.185409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acb8107c-46e9-467c-829d-3fa3e1b96370 · outbound

This paper cites Toy Models of Superposition.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Toy Models of Superposition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:48.304244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f6e9bfb-108c-4877-8677-3cb7cbfca739 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 20

Resolution: verified exact; doi, observed 2026-08-06T19:08:53.000592Z

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 f0ca15fe-c249-43b8-abb3-82acd03bf59c · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 21

Resolution: verified exact; doi, observed 2026-08-06T19:08:52.766326Z

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 47f9f4b2-1b99-4cfd-ae4c-37f2e4a0627d · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:56.228468Z

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 ef8a7742-3072-4425-adf0-c09c9038f6af · outbound

This paper cites Mistral 7B.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Mistral 7B

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:48.781277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2beb27aa-a745-4dda-9914-fe71df94b750 · outbound

This paper cites Visualizing and Understanding Recurrent Networks.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Visualizing and Understanding Recurrent Networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:48.893876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3132c40a-fed0-4886-8fbc-c911d9cc2159 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:55.923389Z

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 63e60965-5187-41c6-9287-5aa2a4dd918a · outbound

This paper cites Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:49.180573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab46913e-5f65-4a91-8498-300871536fad · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:55.586822Z

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 cf47fdff-9059-4797-aba7-7360d97e7e59 · outbound

This paper cites BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:08:54.009071Z

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 661d4177-1c48-4863-8868-c2a34a16fe23 · outbound

This paper cites FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:08:53.762981Z

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 a2370945-e222-49e7-961d-d60d84693862 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:55.286664Z

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 ae2708e5-8f3e-40cf-a082-e95a44ea5c27 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:49.757773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7366676c-4d06-4e76-b7e6-c39c62a469a6 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Gemma: Open Models Based on Gemini Research and Technology

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:49.851396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 156acf7f-79a4-4f4d-a0ba-dfdc9992f036 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:49.954918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62ff9008-cf39-4b51-b8f6-7e4f21b69b77 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:50.094933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c48d16b4-fcf5-4434-b2cc-559e8fe44e53 · outbound

This paper cites Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:08:53.514982Z

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 22a3a5ae-2845-4677-989b-a404a1f328f8 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:54.987843Z

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 544a2e54-c423-4aa6-a7d0-7d1589c54be5 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:54.662458Z

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 25e764c3-d6c8-4946-8f51-eeaef5d85aa7 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:50.619500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 178782a6-1542-4f91-a877-0f793ea9ccc1 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:50.776371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 854e0dd5-4ff6-47ca-9d3f-a6f116a7294d · outbound

This paper cites LawLLM: Law Large Language Model for the US Legal System.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders LawLLM: Law Large Language Model for the US Legal System

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:50.905125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85de85c-7e8e-450d-b6b3-f2da55a6dfad · outbound

This paper cites What Makes Math Word Problems Challenging for LLMs?.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders What Makes Math Word Problems Challenging for LLMs?

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:08:53.286974Z

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 60264d59-5530-49fe-b361-1dfae2cc1620 · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:08:54.360902Z

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 bbbbbc28-07f9-45d2-9a4e-30ca98fd30be · outbound

This paper cites OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:51.294515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a11aaf-6ac1-4560-8916-b677f1750cde · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 44

Resolution: verified exact; doi, observed 2026-08-06T19:08:52.442694Z

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 f75864cc-36ad-41ac-bca0-55c49344d34a · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:51.534863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a90ef7c-8523-4fb1-984d-13512b347ec1 · outbound

This paper cites Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:51.648824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 504bced8-5895-4bba-8e46-65656e41a25a · outbound

This paper cites an unresolved cited work.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:51.764977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6358715e-b22b-4dd9-bf4c-f80f2cf315da · outbound

This paper cites URL: " 'urlintro :=.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders URL: " 'urlintro :=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:51.909679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a9220c-bc8e-4411-8231-1d507a367263 · outbound

This paper cites write newline.

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders write newline

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:52.099815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d3c96b12-8468-4d05-ad97-2598834e29e7 · inbound

The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models cites this paper.

The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:11:08.880392Z

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.