Paper Citation Record · LEDGER

Resa: Transparent Reasoning Models via SAEs

As of 17 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 3 inbound Pith citation observations for arXiv:2506.09967.

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

pith.paper-citation-record.v1
2506.09967 v2

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:45:42.760281Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T13:34:46.646854Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T08:26:24.053617Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy0
unresolved27
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation da21b129-774f-4fb0-ba65-753705cbb947 · outbound

This paper cites Steering Large Language Model Activations in Sparse Spaces.

Resa: Transparent Reasoning Models via SAEs Steering Large Language Model Activations in Sparse Spaces

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.688318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a07c02d3-86f8-4ddc-a234-f26edc18ed46 · outbound

This paper cites Toward universal steering and monitoring of AI models.

Resa: Transparent Reasoning Models via SAEs Toward universal steering and monitoring of AI models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.691479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae5cf393-4ed4-46e6-9c7a-82c4691bf7ab · outbound

This paper cites Low-Rank Adapting Models for Sparse Autoencoders.

Resa: Transparent Reasoning Models via SAEs Low-Rank Adapting Models for Sparse Autoencoders

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T04:45:43.042912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 27bf7515-76e3-4733-ab40-c10989d45b65 · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

Resa: Transparent Reasoning Models via SAEs SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.697452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6f50ba9-ed7f-4c08-a85e-87cf96ce073b · outbound

This paper cites DeepSeek-AI.

Resa: Transparent Reasoning Models via SAEs DeepSeek-AI

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.703202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2821cc5b-ea27-4f4a-aa03-ba0842b9cf3d · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Resa: Transparent Reasoning Models via SAEs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.705693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4e68646-ed60-4f23-a0a8-2c927f4350f9 · outbound

This paper cites Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models.

Resa: Transparent Reasoning Models via SAEs Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.708353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4211921-223d-40b6-b350-a775b8f549c7 · outbound

This paper cites OpenThoughts: Data Recipes for Reasoning Models.

Resa: Transparent Reasoning Models via SAEs OpenThoughts: Data Recipes for Reasoning Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.713944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 620053fa-a4fe-44e0-a804-5c35444fc6ec · outbound

This paper cites SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability.

Resa: Transparent Reasoning Models via SAEs SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.719642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efd70a8a-1886-4823-b9e0-b852906d5ea7 · outbound

This paper cites s1: Simple test-time scaling.

Resa: Transparent Reasoning Models via SAEs s1: Simple test-time scaling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.722628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 079557b3-ec61-4220-b289-83d8193b0886 · outbound

This paper cites Steering Language Model Refusal with Sparse Autoencoders.

Resa: Transparent Reasoning Models via SAEs Steering Language Model Refusal with Sparse Autoencoders

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.725469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3eda194-da27-48d9-898b-586fd7d54d66 · outbound

This paper cites Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models.

Resa: Transparent Reasoning Models via SAEs Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.728069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72fef940-81d3-41fb-9e3d-bcf4d053e312 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Resa: Transparent Reasoning Models via SAEs Steering Llama 2 via Contrastive Activation Addition

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.730871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4fae259-1e14-4fbd-bbb9-3e9b85bc85df · outbound

This paper cites Qwen2.5 Technical Report.

Resa: Transparent Reasoning Models via SAEs Qwen2.5 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.733812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef4a27c7-4a71-49ae-ad9a-a491d6e2b6d3 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Resa: Transparent Reasoning Models via SAEs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.736285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c81686f5-7c51-41d6-8b98-efe0d11c8567 · outbound

This paper cites Tina: Tiny Reasoning Models via LoRA.

Resa: Transparent Reasoning Models via SAEs Tina: Tiny Reasoning Models via LoRA

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.738769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48448f35-3dc6-4cb3-b0e2-fd117fefe50a · outbound

This paper cites AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders.

Resa: Transparent Reasoning Models via SAEs AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.741450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa5bc696-b96d-4d4a-a601-0664c31c8d5a · outbound

This paper cites Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models.

Resa: Transparent Reasoning Models via SAEs Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.744175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1571120e-c6d8-4ab7-b867-36a5f3547c13 · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

Resa: Transparent Reasoning Models via SAEs Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.746793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b7724ee-3cc2-4c91-8daa-3cf638a5b3d5 · outbound

This paper cites Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining.

Resa: Transparent Reasoning Models via SAEs Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.749398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08dc86f5-e57e-48ae-b701-0138da0072bd · outbound

This paper cites an unresolved cited work.

Resa: Transparent Reasoning Models via SAEs Unresolved cited work

Reference 26

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T04:45:43.114221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c0e45e74-9ea1-4320-a04b-674b6b3bf690 · outbound

This paper cites an unresolved cited work.

Resa: Transparent Reasoning Models via SAEs Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:45:43.105318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f9ee43f-b00a-4437-98c0-409abd2c08cc · outbound

This paper cites an unresolved cited work.

Resa: Transparent Reasoning Models via SAEs Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:45:43.096739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 23975cb0-81b7-4c48-b19a-1f486b331383 · outbound

This paper cites an unresolved cited work.

Resa: Transparent Reasoning Models via SAEs Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:45:43.087808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d414bc41-689e-4392-afdf-d0f6b6415096 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Resa: Transparent Reasoning Models via SAEs Understanding intermediate layers using linear classifier probes

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.680950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34e65e63-0c29-472e-b2a3-af4a74c78dd1 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Resa: Transparent Reasoning Models via SAEs Measuring Mathematical Problem Solving With the MATH Dataset

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.716780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec43a01e-0e3f-436e-a590-8e62ab4c6a68 · outbound

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

Resa: Transparent Reasoning Models via SAEs Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.700387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b8fbf58-c38e-4115-ae25-db788752bd00 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Resa: Transparent Reasoning Models via SAEs Scaling and evaluating sparse autoencoders

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.711316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5e64d20-73d0-4162-85a7-e0e54c3e6ae9 · outbound

This paper cites SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model.

Resa: Transparent Reasoning Models via SAEs SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.684968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation dfbbe6fb-5217-415a-acad-826358219ba0 · inbound

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning cites this paper.

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning Resa: Transparent Reasoning Models via SAEs

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:01:09.725817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0214df2d-e589-4baf-8ff5-71806869d2fa · inbound

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning cites this paper.

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning Resa: Transparent Reasoning Models via SAEs

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:26:24.056069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 79dea46d-109d-4c74-8551-c5c9b1f020fe · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Resa: Transparent Reasoning Models via SAEs

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-07-12T13:34:46.646854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.