Paper Citation Record · LEDGER

Mechanistic interpretability for steering vision-language-action models

As of 9 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 11 inbound Pith citation observations for arXiv:2509.00328.

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

pith.paper-citation-record.v1
2509.00328 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:50:19.542914Z

measured 41 of 41 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 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T19:34:24.408268Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy10
unresolved19
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation dedf9934-f427-451f-a357-b1117075386c · outbound

This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.

Mechanistic interpretability for steering vision-language-action models $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:17.340438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d155fb-1462-4ecf-86ab-dfdaf40e4073 · outbound

This paper cites FAST: Efficient Action Tokenization for Vision-Language-Action Models.

Mechanistic interpretability for steering vision-language-action models FAST: Efficient Action Tokenization for Vision-Language-Action Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:17.405514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 401dc38c-c838-4297-a56b-5068fe353473 · outbound

This paper cites Gemini Robotics: Bringing AI into the Physical World.

Mechanistic interpretability for steering vision-language-action models Gemini Robotics: Bringing AI into the Physical World

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:17.477053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae6ec2d6-d770-433b-b446-2ec22f950601 · outbound

This paper cites Olsson, N.

Mechanistic interpretability for steering vision-language-action models Olsson, N

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:22.367472Z

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.

Observation 8e17f86b-c056-4103-a2fc-331274c84dc6 · outbound

This paper cites Bricken, A.

Mechanistic interpretability for steering vision-language-action models Bricken, A

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:22.248319Z

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.

Observation ccea36d1-5389-4076-b65f-069e132101bb · outbound

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

Mechanistic interpretability for steering vision-language-action models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:17.699172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17683638-5c63-49f4-8d3f-25b356055bbb · outbound

This paper cites Auditing language models for hidden objectives.

Mechanistic interpretability for steering vision-language-action models Auditing language models for hidden objectives

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:17.777613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43ba72b4-688e-4c8f-addf-b0cc2f154b4a · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

Mechanistic interpretability for steering vision-language-action models Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:17.879188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e229f8e-8cb8-41b7-84cd-28cf9b249177 · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T13:50:22.173272Z

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.

Observation 03539586-64b6-4ef4-9fb6-ea577bfdccf2 · outbound

This paper cites Lindsey, W.

Mechanistic interpretability for steering vision-language-action models Lindsey, W

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:22.092254Z

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.

Observation 23374a08-6c83-486f-9134-17e2caaecafd · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:18.065539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a49aef-5065-4fa9-a41e-5e0ef4bf6ea9 · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:50:21.933354Z

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.

Observation 68c838f9-3fb9-4e9d-9262-b60d53b0c5df · outbound

This paper cites Pohland and C.

Mechanistic interpretability for steering vision-language-action models Pohland and C

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:21.824882Z

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.

Observation bbac923b-4354-4d25-9aac-4f3993e020eb · outbound

This paper cites Glanois, P.

Mechanistic interpretability for steering vision-language-action models Glanois, P

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:21.704961Z

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.

Observation b4a92cf3-9894-4102-b829-b2ca9004f722 · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:50:21.610055Z

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.

Observation 86766956-e8ae-40b2-8db4-baf2f100bd3b · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Mechanistic interpretability for steering vision-language-action models Transformer Feed-Forward Layers Are Key-Value Memories

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:18.493376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d355870-39ec-4cdc-8040-38da78dd0adf · outbound

This paper cites Open X-Embodiment: Robotic Learning Datasets and RT-X Models.

Mechanistic interpretability for steering vision-language-action models Open X-Embodiment: Robotic Learning Datasets and RT-X Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:18.630035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30f99f6b-5f28-457f-9376-299a076646bb · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

Mechanistic interpretability for steering vision-language-action models RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:18.751597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8774c8d3-bd5e-4fa0-b630-bb09dd3ef380 · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:50:21.446745Z

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.

Observation 6ecd7d12-3138-48d2-b0a3-411fd97f8381 · outbound

This paper cites PaliGemma: A versatile 3B VLM for transfer.

Mechanistic interpretability for steering vision-language-action models PaliGemma: A versatile 3B VLM for transfer

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:18.967190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8557c48-2a70-4e02-b973-9a0b7dceae4d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Mechanistic interpretability for steering vision-language-action models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:19.068750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329c2eb6-2d26-486d-86da-201818b4a3bf · outbound

This paper cites Khazatsky, K.

Mechanistic interpretability for steering vision-language-action models Khazatsky, K

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:21.282979Z

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.

Observation e038a7af-2217-4bc5-b0d3-068c9f87dc7b · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:19.270055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 220f1798-8dc3-4665-a8b5-5ecf1a9d98ce · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:50:21.040180Z

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.

Observation aff1e8f7-6f82-40d7-aa6a-b5ad76e9cc6e · outbound

This paper cites GLU Variants Improve Transformer.

Mechanistic interpretability for steering vision-language-action models GLU Variants Improve Transformer

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:19.351352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 377556f8-069a-40b2-8b9a-0ab58b72df81 · outbound

This paper cites To assign meaning to each value vector, we project it into the model’s output token space using the language modeling head, as described in Section 3.

Mechanistic interpretability for steering vision-language-action models To assign meaning to each value vector, we project it into the model’s output token space using the language modeling head, as described in Section 3

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:20.847271Z

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.

Observation f38e0e71-49b4-45a3-aed9-f0b530d27fa7 · outbound

This paper cites The full OPEN VLA model contains 352,255 value vectors across all trans- former layers.

Mechanistic interpretability for steering vision-language-action models The full OPEN VLA model contains 352,255 value vectors across all trans- former layers

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:20.674911Z

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.

Observation 5f1b69fc-0ec5-4cd9-af1a-8b0d67169194 · outbound

This paper cites We apply cosine-based k-nearest neighbor (kNN) clustering to these semantic embeddings using the cuML GPU-accelerated library.

Mechanistic interpretability for steering vision-language-action models We apply cosine-based k-nearest neighbor (kNN) clustering to these semantic embeddings using the cuML GPU-accelerated library

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:20.446544Z

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.

Observation 8e9d2912-1740-4661-86b4-618b5abb202c · outbound

This paper cites an unresolved cited work.

Mechanistic interpretability for steering vision-language-action models Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:50:20.247067Z

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.

Observation 15969075-7633-4de1-886b-8b5af63e0a58 · outbound

This paper cites place penguin 17 in basket.

Mechanistic interpretability for steering vision-language-action models place penguin 17 in basket

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:50:19.983808Z

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.

Pith citing papers

Observation bf15ee03-112f-4632-b1c1-54315d2e19cd · inbound

Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA cites this paper.

Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA Mechanistic interpretability for steering vision-language-action models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:48:11.453180Z

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.

Observation 9a224e0d-5c59-48c7-86dc-70addb5af670 · inbound

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders cites this paper.

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders Mechanistic interpretability for steering vision-language-action models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T12:01:02.997589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c41a8b1-39f6-4a41-ae47-35e1489cc70d · inbound

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control cites this paper.

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control Mechanistic interpretability for steering vision-language-action models

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-10T02:32:49.468387Z

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.

Observation 47fd72ee-9b62-48ea-9ff3-e4c2e0a86c3c · inbound

Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies cites this paper.

Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies Mechanistic interpretability for steering vision-language-action models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.969424Z

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.

Observation 7943ce1b-2f8b-4d09-9691-f66528391fe9 · inbound

Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models cites this paper.

Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models Mechanistic interpretability for steering vision-language-action models

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-03T06:07:41.715166Z

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.

Observation 3a8e8e02-fde0-406d-bd56-e7666f4e550c · inbound

Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering cites this paper.

Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering Mechanistic interpretability for steering vision-language-action models

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:27:56.334823Z

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.

Observation 300ac5d0-992f-4578-98d4-3ca098637646 · inbound

Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure cites this paper.

Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure Mechanistic interpretability for steering vision-language-action models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:09:50.087802Z

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.

Observation 4d00da8f-991c-4342-b34b-a1803124e5a8 · inbound

Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering cites this paper.

Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering Mechanistic interpretability for steering vision-language-action models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:54:22.156382Z

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.

Observation 53d64a06-13d4-4056-a2b2-78e68f1d3a31 · inbound

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift cites this paper.

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift Mechanistic interpretability for steering vision-language-action models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:04:21.924549Z

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.

Observation 41a477b1-52f3-4b1e-b019-7872a0c4b39a · inbound

Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History cites this paper.

Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History Mechanistic interpretability for steering vision-language-action models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T02:57:44.784072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54089362-2ad1-4a2c-987a-061ef16fd07d · inbound

What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning cites this paper.

What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning Mechanistic interpretability for steering vision-language-action models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T19:34:24.408268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.