Paper Citation Record · LEDGER

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning

As of 10 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2502.00684.

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

pith.paper-citation-record.v1
2502.00684 v2

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T18:09:29.514148Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

23 of 23 outbound references displayed

verified exact1
verified fuzzy18
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2e912478-220a-4525-a3ba-5a0ea8082dcf · outbound

This paper cites Network dissection: Quantifying interpretability of deep visual representations.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Network dissection: Quantifying interpretability of deep visual representations

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.840655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d9ba15d5-14e3-47ea-9856-c832db47230e · outbound

This paper cites Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T18:09:29.439326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b5ebd5d-af44-4712-bacc-46c8828ce1f6 · outbound

This paper cites Visualization of deep reinforcement learning using grad- cam: how ai plays atari games? In 2019 IEEE conference on games (CoG), pages 1–2.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Visualization of deep reinforcement learning using grad- cam: how ai plays atari games? In 2019 IEEE conference on games (CoG), pages 1–2

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.804614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 299782a1-a905-4c44-9194-a09fbd534d25 · outbound

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

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.790301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fd7ec567-ac05-4719-b8fd-70e0c63b71e5 · outbound

This paper cites Com- positional explanations of neurons.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Com- positional explanations of neurons

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.752289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64888dc2-8f8d-4525-8c0b-430ed983e364 · outbound

This paper cites Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T18:09:29.472194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4cdfe7-84c0-4da7-934f-d11f8ab040c0 · outbound

This paper cites A survey on explain- able reinforcement learning: Concepts, algorithms, chal- lenges,.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning A survey on explain- able reinforcement learning: Concepts, algorithms, chal- lenges,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.726579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c734c426-0125-4085-8901-ff54ffe26cb6 · outbound

This paper cites Reinforcement learning with ex- plainability for traffic signal control.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Reinforcement learning with ex- plainability for traffic signal control

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.710307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d4958fc2-78e0-400f-bed6-a699cace4475 · outbound

This paper cites Self- supervised discovering of interpretable features for rein- forcement learning.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Self- supervised discovering of interpretable features for rein- forcement learning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.697781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3897560e-ee61-4d65-918d-13079e81726f · outbound

This paper cites Gymnasium: A Standard Interface for Reinforcement Learning Environments.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Gymnasium: A Standard Interface for Reinforcement Learning Environments

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T18:09:29.487977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f58c138-b720-44d9-a119-46a855931863 · outbound

This paper cites Programmatically interpretable reinforcement learn- ing.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Programmatically interpretable reinforcement learn- ing

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.684334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1929bfed-0387-45c6-a190-bc48edf0745c · outbound

This paper cites Explainable deep rein- forcement learning: state of the art and challenges.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Explainable deep rein- forcement learning: state of the art and challenges

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.671459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b7c0c426-b3e4-4d6f-ae40-48e2e807955e · outbound

This paper cites Concept-based interpretable rein- forcement learning with limited to no human labels.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Concept-based interpretable rein- forcement learning with limited to no human labels

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.646869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 38099ba5-1f6c-44af-8230-63bbab97024d · outbound

This paper cites Explainable reinforcement learning via a causal world model.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Explainable reinforcement learning via a causal world model

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.633160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 654c5761-6f02-435b-823b-a4928a094782 · outbound

This paper cites Concept learning for interpretable multi-agent reinforce- ment learning.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Concept learning for interpretable multi-agent reinforce- ment learning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.619837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9cd20e46-64af-494b-9e82-c4b2d803e11d · outbound

This paper cites Explainable Multi-Agent Reinforcement Learning for Temporal Queries.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Explainable Multi-Agent Reinforcement Learning for Temporal Queries

Reference 2017

Resolution: verified exact; local_arxiv, observed 2026-08-09T18:09:29.605797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 66b467b0-aad9-4870-a876-08c51e78e187 · outbound

This paper cites Dis- covering symbolic policies with deep reinforcement learn- ing.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Dis- covering symbolic policies with deep reinforcement learn- ing

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.774218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 543f8471-a5dd-4932-946b-fe0a3b37027c · outbound

This paper cites Improving robot controller transparency through au- tonomous policy explanation.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Improving robot controller transparency through au- tonomous policy explanation

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.817180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 694f9622-f2b4-4e97-921b-bbd5e39a7d5d · outbound

This paper cites Free-lunch saliency via attention in atari agents.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Free-lunch saliency via attention in atari agents

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.740829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation babc21eb-3e2b-426d-ad85-ceb29d36d7c4 · outbound

This paper cites Toward interpretable deep reinforcement learning with linear model u-trees.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Toward interpretable deep reinforcement learning with linear model u-trees

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.763021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c25d9d24-1a1e-4f9a-bd1c-ff998fd2a93f · outbound

This paper cites Global concept-based interpretability for graph neu- ral networks via neuron analysis.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Global concept-based interpretability for graph neu- ral networks via neuron analysis

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.660123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 46745edf-6bb0-44fa-9f88-a14ee0ff2ebc · outbound

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

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T18:09:29.435085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a29883-380d-4235-9fa0-fbbed0776981 · outbound

This paper cites Towards automatic concept- based explanations.

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning Towards automatic concept- based explanations

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:09:29.829729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.