{"as_of":"2026-08-08T08:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0526e2f0e77f8cbac73805e9a426eb5cb33074fcee049610d62583ae06b5b6cd","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:05:35.083962Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T13:58:21.621045Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2105.00579","last_updated":"2021-12-12T23:22:37Z","snapshot_observed_at":"2026-07-06T11:05:38.870562Z","submitted_at":"2021-05-02T23:47:55Z","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.00579","snapshot_observed_at":"2026-08-07T13:05:35.083962Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22829","last_updated":"2026-06-18T15:45:13Z","snapshot_observed_at":"2026-08-07T12:57:10.888209Z","submitted_at":"2025-05-28T20:11:30Z","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","version":2},"reference_index":184,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:35.083962Z"},"links":{"cited_paper":"/paper/2105.00579","citing_paper":"/paper/2505.22829"},"observation_digest":"sha256:c3313db5d83dd73904705bada4648750e61e733cf68fe46d1a93dc1e74c0317a","observation_id":"91c4db19-c7b7-4a7c-b828-4184bf1993eb","resolution":{"observed_at":"2026-08-07T13:05:35.083962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.00579","last_updated":"2021-12-12T23:22:37Z","snapshot_observed_at":"2026-07-06T11:05:38.870562Z","submitted_at":"2021-05-02T23:47:55Z","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.00579","snapshot_observed_at":"2026-08-06T19:47:32.531262Z","title":"arXiv preprint arXiv:2105.00579","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04883","last_updated":"2025-07-07T11:15:54Z","snapshot_observed_at":"2026-08-06T19:34:47.468372Z","submitted_at":"2025-07-07T11:15:54Z","title":"Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:47:32.531262Z"},"links":{"cited_paper":"/paper/2105.00579","citing_paper":"/paper/2507.04883"},"observation_digest":"sha256:2987a842acb1f93f44ad58a898ed6d2847e32d34ae6c3114ab28e35692ea70ae","observation_id":"c748fc02-93b7-42d3-bc99-3714c2db734b","resolution":{"observed_at":"2026-08-06T19:47:32.531262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.00579","last_updated":"2021-12-12T23:22:37Z","snapshot_observed_at":"2026-07-06T11:05:38.870562Z","submitted_at":"2021-05-02T23:47:55Z","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.00579","snapshot_observed_at":"2026-08-03T12:18:23.824751Z","title":"Backdoorl: Backdoor attack against competitive reinforcement learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.04266","last_updated":"2026-06-08T05:08:44Z","snapshot_observed_at":"2026-08-07T08:42:06.936507Z","submitted_at":"2026-01-07T08:54:31Z","title":"State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T12:18:23.824751Z"},"links":{"cited_paper":"/paper/2105.00579","citing_paper":"/paper/2601.04266"},"observation_digest":"sha256:aee2e8dc8659d1281efe107ada3c4dbe97ab5c502b2d3788525d56dd00dbd362","observation_id":"4af959bc-14b5-41cc-93ac-cd6eeb747e52","resolution":{"observed_at":"2026-08-03T12:18:23.824751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.00579","last_updated":"2021-12-12T23:22:37Z","snapshot_observed_at":"2026-07-06T11:05:38.870562Z","submitted_at":"2021-05-02T23:47:55Z","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2105.00579","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2105.00579","snapshot_observed_at":"2026-07-03T13:58:21.621045Z","title":"Backdoorl: Backdoor attack against competitive reinforcement learn- ing.arXiv preprint arXiv:2105.00579","venue":null,"work_id":"4ca00828-4c3d-4a5c-8717-6d00dc2554ee","year":2021},"citing_paper":{"arxiv_id":"2605.05977","last_updated":"2026-05-07T10:21:14Z","snapshot_observed_at":"2026-07-06T23:18:31.432422Z","submitted_at":"2026-05-07T10:21:14Z","title":"BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-08T10:45:47.028500Z"},"links":{"cited_paper":"/paper/2105.00579","citing_paper":"/paper/2605.05977"},"observation_digest":"sha256:a949897ebb1a4f7781ce827f588b8093d88b33936f1359e506368e82f657b0f9","observation_id":"9358b655-da2a-4972-b1a2-1450f8d23b30","resolution":{"observed_at":"2026-05-11T19:56:07.110465Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.00579","last_updated":"2021-12-12T23:22:37Z","snapshot_observed_at":"2026-07-06T11:05:38.870562Z","submitted_at":"2021-05-02T23:47:55Z","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2105.00579","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2105.00579","snapshot_observed_at":"2026-07-03T13:58:21.621045Z","title":"Backdoorl: Backdoor attack against competitive reinforcement learn- ing.arXiv preprint arXiv:2105.00579","venue":null,"work_id":"4ca00828-4c3d-4a5c-8717-6d00dc2554ee","year":2021},"citing_paper":{"arxiv_id":"2606.00414","last_updated":"2026-05-29T23:09:01Z","snapshot_observed_at":"2026-08-08T01:56:46.082743Z","submitted_at":"2026-05-29T23:09:01Z","title":"Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T22:55:56.432874Z"},"links":{"cited_paper":"/paper/2105.00579","citing_paper":"/paper/2606.00414"},"observation_digest":"sha256:6c3090aa000abe9e9cd5694f75ac8c467618524c6c6259cbf2760b14b9e0e654","observation_id":"08d70c12-4a67-4180-b83b-b190e4cde2ca","resolution":{"observed_at":"2026-07-01T19:16:00.608902Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.00579","last_updated":"2021-12-12T23:22:37Z","snapshot_observed_at":"2026-07-06T11:05:38.870562Z","submitted_at":"2021-05-02T23:47:55Z","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2105.00579","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2105.00579","snapshot_observed_at":"2026-07-03T13:58:21.621045Z","title":"Backdoorl: Backdoor attack against competitive reinforcement learn- ing.arXiv preprint arXiv:2105.00579","venue":null,"work_id":"4ca00828-4c3d-4a5c-8717-6d00dc2554ee","year":2021},"citing_paper":{"arxiv_id":"2606.12896","last_updated":"2026-06-20T06:38:45Z","snapshot_observed_at":"2026-08-08T06:59:30.111406Z","submitted_at":"2026-06-11T04:54:28Z","title":"PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for Reinforcement Learning Agent","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-06-27T07:24:38.668110Z"},"links":{"cited_paper":"/paper/2105.00579","citing_paper":"/paper/2606.12896"},"observation_digest":"sha256:0461e55282dd51dcd1de24f846d0317a4a3c11b90ed8350a6a16a23dfff173cf","observation_id":"2d928352-459f-4fb4-b298-e185799caffd","resolution":{"observed_at":"2026-07-03T13:58:21.622584Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2105.00579/citation-record","integrity":"/paper/2105.00579/integrity","json":"/paper/2105.00579/citation-record.json","paper":"/paper/2105.00579"},"outbound":[],"paper":{"arxiv_id":"2105.00579","last_updated":"2021-12-12T23:22:37Z","latest_version":3,"primary_category":"cs.CR","snapshot_observed_at":"2026-07-06T11:05:38.870562Z","submitted_at":"2021-05-02T23:47:55Z","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2105.00579."}