Paper Citation Record · LEDGER

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation

As of 8 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2509.20623.

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

pith.paper-citation-record.v1
2509.20623 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T15:18:07.263704Z

measured 46 of 46 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T01:10:42.960233Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T22:56:20.121244Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 87b7ffa2-ae0e-4bb9-91f8-9afa02da1b34 · outbound

This paper cites Recent advances in robot learning from demonstration,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Recent advances in robot learning from demonstration,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:02.085453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97866fcd-cb9a-4264-bff9-f46c7d8dde64 · outbound

This paper cites Collision avoidance and navigation for a quadrotor swarm using end-to-end deep reinforcement learning,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Collision avoidance and navigation for a quadrotor swarm using end-to-end deep reinforcement learning,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:02.180527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1b2cce3-0971-466d-a28f-d4bbbde7cac8 · outbound

This paper cites Decentralized control of quadrotor swarms with end-to- end deep reinforcement learning,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Decentralized control of quadrotor swarms with end-to- end deep reinforcement learning,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:02.323494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f9521a9-f171-4ad0-bdd4-1165b78b3942 · outbound

This paper cites Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:02.500174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db29d5e4-80a0-4f44-ab0f-aaa21b620567 · outbound

This paper cites The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:02.600089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aea5bd7e-1db6-4ccc-b03e-02ac68cd9d24 · outbound

This paper cites Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:02.726945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88397ea7-c346-46ba-9e64-ac324400d29f · outbound

This paper cites Learning to modulate pre-trained models in rl,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Learning to modulate pre-trained models in rl,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:02.844983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1124903d-673a-4b0f-92b1-02e47c66d594 · outbound

This paper cites Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.002844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b008a52d-3ff4-40b3-a8dd-7085f52c9235 · outbound

This paper cites Deep reinforcement learning that matters,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Deep reinforcement learning that matters,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.092780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d82f5ed-341d-4555-9d36-126042b4c233 · outbound

This paper cites Challenges of Real-World Reinforcement Learning.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Challenges of Real-World Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.210758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 249308d2-c36c-44cd-835d-ce2d0ad49c02 · outbound

This paper cites Steering Language Models With Activation Engineering.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Steering Language Models With Activation Engineering

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.293607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22dc3fd8-51dd-4805-bc2e-db64fed14bb1 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.396426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c114ac2-9114-44d2-9e6e-4ae19b9f2452 · outbound

This paper cites Templeton,Scaling monosemanticity: Extracting interpretable fea- tures from claude 3 sonnet.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Templeton,Scaling monosemanticity: Extracting interpretable fea- tures from claude 3 sonnet

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.470923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90b901bc-8b47-4e4b-b304-6f066fb772ce · outbound

This paper cites Ganspace: Dis- covering interpretable gan controls,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Ganspace: Dis- covering interpretable gan controls,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.555329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a99ffd9-0108-4f3b-96da-86163e5bdd53 · outbound

This paper cites SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.651430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5dd48d0-000f-443e-845c-9978c4ed0f67 · outbound

This paper cites World Models.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation World Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.738954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e92c84d-88d3-429c-97fa-58b5a5388a57 · outbound

This paper cites Learning latent dynamics for planning from pixels,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Learning latent dynamics for planning from pixels,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.811391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a54bfdc7-9ba7-4ad4-ba98-23f14217d62a · outbound

This paper cites Dream to Control: Learning Behaviors by Latent Imagination.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Dream to Control: Learning Behaviors by Latent Imagination

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.892460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d864de9-3f39-4169-8571-dca0d91e407b · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Efficient Estimation of Word Representations in Vector Space

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:03.978925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9504e9f9-f39f-4a2a-a251-12974ca3300a · outbound

This paper cites Learning to Generate Reviews and Discovering Sentiment.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Learning to Generate Reviews and Discovering Sentiment

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.079057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 862af5a2-0a41-4d49-b07c-1876a861b47e · outbound

This paper cites Emerging properties in self-supervised vision trans- formers,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Emerging properties in self-supervised vision trans- formers,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.156695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 179a57e9-4947-4c45-a243-73666df31a0b · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Understanding intermediate layers using linear classifier probes

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.265355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f945cdd-ae38-48a9-80a7-8c58545e1e10 · outbound

This paper cites Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav),.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav),

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.366068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4790ad6-5486-40d2-8634-4007980dab2d · outbound

This paper cites Interfacegan: Interpreting the disentangled face representation learned by gans,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Interfacegan: Interpreting the disentangled face representation learned by gans,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.532448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87c6162-45d4-4c40-8ffc-afcbee40e597 · outbound

This paper cites Prompt-to-Prompt Image Editing with Cross Attention Control.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Prompt-to-Prompt Image Editing with Cross Attention Control

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.670275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a0dd14-83c8-42b5-81f4-48beb1a547bb · outbound

This paper cites P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.834479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c6c5e23-728d-4b5f-891f-d9e6ea526a4a · outbound

This paper cites Plug and play language models: A simple approach to controlled text generation,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Plug and play language models: A simple approach to controlled text generation,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.957568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85cbbff4-52a9-4100-8bf8-8b39a2d91957 · outbound

This paper cites Locating and editing factual associations in gpt,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Locating and editing factual associations in gpt,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:05.117341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c8df2dc-ca8c-4880-a266-2371122523d4 · outbound

This paper cites Elad,Sparse and redundant representations: from theory to appli- cations in signal and image processing.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Elad,Sparse and redundant representations: from theory to appli- cations in signal and image processing

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:05.242832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68fd3e4-fcb1-4425-833e-9ee0aa8bbffc · outbound

This paper cites Toy Models of Superposition.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Toy Models of Superposition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:05.413127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c80af33-6eda-480f-992e-437d55595ca1 · outbound

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

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:05.515086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3be8570d-b6ff-461d-a176-e62b58333cd3 · outbound

This paper cites Ls3: Latent space safe sets for long-horizon visuomotor control of sparse reward iterative tasks,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Ls3: Latent space safe sets for long-horizon visuomotor control of sparse reward iterative tasks,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:05.635676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caca997a-ef10-49b1-bacd-bdfb60cce7ac · outbound

This paper cites Latent safety- constrained policy approach for safe offline reinforcement learning,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Latent safety- constrained policy approach for safe offline reinforcement learning,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:05.706735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7575a794-e980-47dd-a9c1-b402038af2d2 · outbound

This paper cites Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:05.879386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7edb8bc-9c1e-4cfd-979d-5896c4e2a2f1 · outbound

This paper cites Generalizing safety beyond collision-avoidance via latent-space reachability analysis,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Generalizing safety beyond collision-avoidance via latent-space reachability analysis,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:06.055684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4822167-1449-4fe0-8916-70b4b16e2dd7 · outbound

This paper cites A scalable dis- tributed collision avoidance scheme for multi-agent uav systems,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation A scalable dis- tributed collision avoidance scheme for multi-agent uav systems,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:06.187933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 488f96fa-21a0-4827-8c81-f976beedb9e7 · outbound

This paper cites Ego-swarm: A fully autonomous and decentralized quadrotor swarm system in cluttered environments,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Ego-swarm: A fully autonomous and decentralized quadrotor swarm system in cluttered environments,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:06.338904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33835488-daf6-4941-83b1-4f6d7e09b67b · outbound

This paper cites Safety barrier certificates for heterogeneous multi-robot systems,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Safety barrier certificates for heterogeneous multi-robot systems,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:06.491579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 684a6d17-ac29-47c1-b1a7-d1a85034cc08 · outbound

This paper cites Gcbf+: A neural graph control barrier function framework for distributed safe multi-agent control,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Gcbf+: A neural graph control barrier function framework for distributed safe multi-agent control,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:06.638356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0da3a115-c17a-4167-a98b-1a413abe30f3 · outbound

This paper cites QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:06.768072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8118872f-da45-4c38-a5c3-ddb4d7f1d958 · outbound

This paper cites Learning to Act without Actions.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Learning to Act without Actions

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:06.919976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 062a2d5b-ab07-47e2-8d8e-239bcfa231ec · outbound

This paper cites Sample factory: Egocentric 3d control from pixels at 100000 fps with asynchronous reinforcement learning,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Sample factory: Egocentric 3d control from pixels at 100000 fps with asynchronous reinforcement learning,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:07.052755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b9da0a7-2da1-44b6-9606-66d400d5d040 · outbound

This paper cites Parametric umap embeddings for representation and semisupervised learning,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Parametric umap embeddings for representation and semisupervised learning,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:07.164948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f19624-9fdc-4db3-8a99-70de7104e875 · outbound

This paper cites Barlow twins: Self-supervised learning via redundancy reduction,.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Barlow twins: Self-supervised learning via redundancy reduction,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:07.263704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ce3b6b32-e463-4680-a8a4-9fc91b679c80 · inbound

World-Task Factorization for Robot Learning cites this paper.

World-Task Factorization for Robot Learning Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-01T22:56:20.122929Z

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 b1c37c58-b0f9-4032-ae3f-9db44825504e · inbound

Inference-Time Policy Alignment for Fair Reinforcement Learning cites this paper.

Inference-Time Policy Alignment for Fair Reinforcement Learning Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T01:10:42.960233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.