{"as_of":"2026-08-10T16:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:075189d2ed6c868f6c3262530b79e8ea1e30258afe1c2bd378e4aedab1e63e1c","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T18:09:29.514148Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.00684/citation-record","integrity":"/paper/2502.00684/integrity","json":"/paper/2502.00684/citation-record.json","paper":"/paper/2502.00684"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.837161Z","title":"Network dissection: Quantifying interpretability of deep visual representations","venue":null,"work_id":"013540b8-1f08-429a-98b1-8b4d24dd5b21","year":2017},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.426349Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:0b7a6b26e8dbedfe7a95efd2e4a197029f853df026ac30aee2243881f240747c","observation_id":"2e912478-220a-4525-a3ba-5a0ea8082dcf","resolution":{"observed_at":"2026-08-09T18:09:29.840655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.05821","last_updated":"2024-10-28T18:38:00Z","snapshot_observed_at":"2026-07-06T17:14:15.453464Z","submitted_at":"2024-01-11T10:38:22Z","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.05821","snapshot_observed_at":"2026-08-09T18:09:29.439326Z","title":"Interpretable concept bottlenecks to align reinforcement learning agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.439326Z"},"links":{"cited_paper":"/paper/2401.05821","citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:607521b752898886f02e45af68c269da13c346d8173618a7b410c25ce7ca306b","observation_id":"d9ba15d5-14e3-47ea-9856-c832db47230e","resolution":{"observed_at":"2026-08-09T18:09:29.439326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.799371Z","title":"Visualization of deep reinforcement learning using grad- cam: how ai plays atari games? In 2019 IEEE conference on games (CoG), pages 1–2","venue":null,"work_id":"1b28f2c0-b84d-42dd-80ae-84c3a0d28074","year":2019},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.451685Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:a5581eb3269eedf1a78d18fb392b84c2da5c79703a58f1b5f4666ba3f8602077","observation_id":"1b5ebd5d-af44-4712-bacc-46c8828ce1f6","resolution":{"observed_at":"2026-08-09T18:09:29.804614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.784330Z","title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)","venue":null,"work_id":"db7873ff-c435-42f0-ac3a-4eabe677c3bc","year":2018},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.454847Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:dd8894726e62583b3824a9940b0d29d0313a38390b2352211e76d461785e90b2","observation_id":"299782a1-a905-4c44-9194-a09fbd534d25","resolution":{"observed_at":"2026-08-09T18:09:29.790301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.748376Z","title":"Com- positional explanations of neurons","venue":null,"work_id":"c4ed6018-566c-46b2-8b17-fa4a1b026a1d","year":2020},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.465154Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:23f73b362a226a1e36827ee2a259d3b188e978f5cb708346ae79050926d34106","observation_id":"fd7ec567-ac05-4719-b8fd-70e0c63b71e5","resolution":{"observed_at":"2026-08-09T18:09:29.752289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.10386","last_updated":"2020-03-23T16:56:11Z","snapshot_observed_at":"2026-08-10T06:45:32.000190Z","submitted_at":"2020-03-23T16:56:11Z","title":"Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.10386","snapshot_observed_at":"2026-08-09T18:09:29.472194Z","title":"In- corporating relational background knowledge into rein- forcement learning via differentiable inductive logic pro- gramming","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.472194Z"},"links":{"cited_paper":"/paper/2003.10386","citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:6e1adde57634cda37e3769c21c70850a03c784239842d78ca5d5ffc3551a2ce0","observation_id":"64888dc2-8f8d-4525-8c0b-430ed983e364","resolution":{"observed_at":"2026-08-09T18:09:29.472194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.721479Z","title":"A survey on explain- able reinforcement learning: Concepts, algorithms, chal- lenges,","venue":null,"work_id":"3e4de0fc-6ff7-41a3-8380-25658fc338c6","year":2023},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.475814Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:4c4891109dbfa980e3b0b5fe4a959164a8612ed0eafdcc9a4c4e9be5c47a8b29","observation_id":"4f4cdfe7-84c0-4da7-934f-d11f8ab040c0","resolution":{"observed_at":"2026-08-09T18:09:29.726579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.705573Z","title":"Reinforcement learning with ex- plainability for traffic signal control","venue":null,"work_id":"d81e676a-d957-4d8a-a94c-16d64525c312","year":2019},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.479402Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:a0ba637dc7aadb5c27e1ebafa6c402c2c543f4531b58e91dcd46eb3212e5c7dd","observation_id":"c734c426-0125-4085-8901-ff54ffe26cb6","resolution":{"observed_at":"2026-08-09T18:09:29.710307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.693809Z","title":"Self- supervised discovering of interpretable features for rein- forcement learning","venue":null,"work_id":"85a53141-cfcb-48f7-91a9-facf61393f71","year":2020},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.483964Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:3cf561289f03de5b9452feab88226b18dd066fb1067bae00dd54f31f0e5a7a35","observation_id":"d4958fc2-78e0-400f-bed6-a699cace4475","resolution":{"observed_at":"2026-08-09T18:09:29.697781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17032","last_updated":"2025-11-02T13:42:19Z","snapshot_observed_at":"2026-07-06T18:51:06.750136Z","submitted_at":"2024-07-24T06:35:05Z","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17032","snapshot_observed_at":"2026-08-09T18:09:29.487977Z","title":"Gymnasium: A standard interface for reinforcement learning environments","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.487977Z"},"links":{"cited_paper":"/paper/2407.17032","citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:b0921e8558569068ac40e64a4f375402a2d8e6a9abfec1ca1ac85b8a45538d0e","observation_id":"3897560e-ee61-4d65-918d-13079e81726f","resolution":{"observed_at":"2026-08-09T18:09:29.487977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.679664Z","title":"Programmatically interpretable reinforcement learn- ing","venue":null,"work_id":"2c9bc935-46f9-4068-81c0-a3102b48cbd1","year":2018},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.492305Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:63f650b8dcf165e922a6cc690885dccb61a6d25fb5a62c44fcf25b5e7ff30294","observation_id":"5f58c138-b720-44d9-a119-46a855931863","resolution":{"observed_at":"2026-08-09T18:09:29.684334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.667824Z","title":"Explainable deep rein- forcement learning: state of the art and challenges","venue":null,"work_id":"4431eb41-8e29-4f68-8ca6-ba39fceb912e","year":2022},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.496572Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:ea154bfcfeac812ce7f9e210398c84d7dfc0d35ca1fb0054415af794ef70f42a","observation_id":"1929bfed-0387-45c6-a190-bc48edf0745c","resolution":{"observed_at":"2026-08-09T18:09:29.671459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.642444Z","title":"Concept-based interpretable rein- forcement learning with limited to no human labels","venue":null,"work_id":"461f1961-ff82-415c-b8a6-9ac6a777fe29","year":2024},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.506188Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:e94a1f5572bd8faa57bc078e68466bc5641afca26c6b0d753cb9e480dd84be97","observation_id":"b7c0c426-b3e4-4d6f-ae40-48e2e807955e","resolution":{"observed_at":"2026-08-09T18:09:29.646869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.628931Z","title":"Explainable reinforcement learning via a causal world model","venue":null,"work_id":"8b397a15-9a56-4d61-8bbf-9d66e4a41666","year":2023},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.510623Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:40b30a35dd9eb1f08acb813ced05f4b397e6c9d83ee008df64a5ce026f8ffde0","observation_id":"38099ba5-1f6c-44af-8230-63bbab97024d","resolution":{"observed_at":"2026-08-09T18:09:29.633160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.615555Z","title":"Concept learning for interpretable multi-agent reinforce- ment learning","venue":null,"work_id":"d6ed40cb-9aa4-44a3-8cb7-9e4bea880657","year":2023},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.514148Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:9b9ba0eeaf5e3f10470d8f426fa5bce67aba0ac04ecce6e620ed9c84e04ceb75","observation_id":"654c5761-6f02-435b-823b-a4928a094782","resolution":{"observed_at":"2026-08-09T18:09:29.619837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10378","last_updated":"2023-05-17T17:04:29Z","snapshot_observed_at":"2026-08-09T11:56:09.385326Z","submitted_at":"2023-05-17T17:04:29Z","title":"Explainable Multi-Agent Reinforcement Learning for Temporal Queries","version":1},"cited_work":{"arxiv_id":"2305.10378","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.10378","snapshot_observed_at":"2026-08-09T18:09:29.599039Z","title":"Explainable Multi-Agent Reinforcement Learning for Temporal Queries","venue":"cs.AI","work_id":"0a230967-d41b-47e1-aff9-575d5d50e692","year":2023},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.431027Z"},"links":{"cited_paper":"/paper/2305.10378","citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:bb636996389a1e3f40bde2e5bb250992ce0a11ea8f014e4855b76daf8467c079","observation_id":"9cd20e46-64af-494b-9e82-c4b2d803e11d","resolution":{"observed_at":"2026-08-09T18:09:29.605797Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.770239Z","title":"Dis- covering symbolic policies with deep reinforcement learn- ing","venue":null,"work_id":"bacfc71f-49dd-4f7a-b968-895985352cb3","year":2021},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.457875Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:1786b60d689ce64de0b359ec8de416d91c19c342e5c1bde13c17eb17eca09180","observation_id":"66b467b0-aad9-4870-a876-08c51e78e187","resolution":{"observed_at":"2026-08-09T18:09:29.774218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.812942Z","title":"Improving robot controller transparency through au- tonomous policy explanation","venue":null,"work_id":"4a0032eb-16b1-4f69-9143-549819149bf7","year":2017},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.447543Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:319e1178487e5ea3c45795726a6ff5bbfbde46aa4affa22353c1ae4c7cb91679","observation_id":"543f8471-a5dd-4932-946b-fe0a3b37027c","resolution":{"observed_at":"2026-08-09T18:09:29.817180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.735976Z","title":"Free-lunch saliency via attention in atari agents","venue":null,"work_id":"9a9462fa-b61d-4241-907b-b5d698e44b50","year":2019},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.468429Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:6f508fe4f1c29cd13b435939d77436b6b75afd372f37da683f7d6702ca59d105","observation_id":"694f9622-f2b4-4e97-921b-bbd5e39a7d5d","resolution":{"observed_at":"2026-08-09T18:09:29.740829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.759388Z","title":"Toward interpretable deep reinforcement learning with linear model u-trees","venue":null,"work_id":"e0e9a305-2468-44d1-b2f7-53367818d41e","year":2019},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.461143Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:665ea03918894686b4697085296cc18e507a8b7516861aa2f6e2c56c005c8854","observation_id":"babc21eb-3e2b-426d-ad85-ceb29d36d7c4","resolution":{"observed_at":"2026-08-09T18:09:29.763021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.656314Z","title":"Global concept-based interpretability for graph neu- ral networks via neuron analysis","venue":null,"work_id":"7cd70631-a479-4543-b6a4-602b78b4d48a","year":2023},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.501739Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:14cba0076bd46d610b5dcdd1cc7fbd9ebf52b708a9a0c7c393dbec6009fd9ad7","observation_id":"c25d9d24-1a1e-4f9a-bd1c-ff998fd2a93f","resolution":{"observed_at":"2026-08-09T18:09:29.660123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08600","last_updated":"2023-10-04T13:17:38Z","snapshot_observed_at":"2026-07-06T16:19:05.495349Z","submitted_at":"2023-09-15T17:56:55Z","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08600","snapshot_observed_at":"2026-08-09T18:09:29.435085Z","title":"Sparse autoencoders find highly interpretable features in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.435085Z"},"links":{"cited_paper":"/paper/2309.08600","citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:2067fdcc2d3cb84832340ee49ffef02211fb24127eb585ec70c564a1c74d58eb","observation_id":"46745edf-6bb0-44fa-9f88-a14ee0ff2ebc","resolution":{"observed_at":"2026-08-09T18:09:29.435085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:09:29.825617Z","title":"Towards automatic concept- based explanations","venue":null,"work_id":"7c2829e3-4949-4ef4-8e55-840bbef3cf74","year":2019},"citing_paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T18:09:29.443689Z"},"links":{"citing_paper":"/paper/2502.00684"},"observation_digest":"sha256:e131ba67980b05d842a6853359e9326157bb78a99ebeaf7c0d98a222b24d626f","observation_id":"49a29883-380d-4235-9fa0-fbbed0776981","resolution":{"observed_at":"2026-08-09T18:09:29.829729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.00684","last_updated":"2026-06-30T15:42:38Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T18:04:24.094921Z","submitted_at":"2025-02-02T06:05:49Z","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":1,"verified_fuzzy":18},"total_outbound_references":23},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"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."}