{"as_of":"2026-08-18T09:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:68f86bdd261cefc48404d1ea37b7eeaee766def61a9f55b392df4a2e19f3a40b","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:53:28.864222Z","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":"2026-05-16T23:38:00.770777Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.06668","last_updated":"2023-02-02T00:11:58Z","snapshot_observed_at":"2026-08-16T17:56:43.312126Z","submitted_at":"2021-09-14T13:16:33Z","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","version":6},"cited_work":{"arxiv_id":"2109.06668","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.06668","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Exploration in deep reinforcement learning: a comprehensive survey","venue":null,"work_id":"ef4e4410-69a7-4440-b8dc-938fa63a2f80","year":2021},"citing_paper":{"arxiv_id":"2403.09227","last_updated":"2024-03-14T09:48:36Z","snapshot_observed_at":"2026-08-16T07:36:37.508005Z","submitted_at":"2024-03-14T09:48:36Z","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-16T23:38:00.611856Z"},"links":{"cited_paper":"/paper/2109.06668","citing_paper":"/paper/2403.09227"},"observation_digest":"sha256:b0e78348a4fb170d340201f6a5982cd4dc5019752c1c4d5fac295ffcd568acd1","observation_id":"e0a9236c-cec0-4a37-8ab9-c6fac411bb07","resolution":{"observed_at":"2026-05-16T23:38:00.774525Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.06668","last_updated":"2023-02-02T00:11:58Z","snapshot_observed_at":"2026-08-16T17:56:43.312126Z","submitted_at":"2021-09-14T13:16:33Z","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.06668","snapshot_observed_at":"2026-08-16T11:53:28.864222Z","title":"arXiv preprint arXiv:2109.06668 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.14363","last_updated":"2025-07-05T09:43:33Z","snapshot_observed_at":"2026-08-17T12:22:03.663299Z","submitted_at":"2025-04-19T17:40:04Z","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T11:53:28.864222Z"},"links":{"cited_paper":"/paper/2109.06668","citing_paper":"/paper/2504.14363"},"observation_digest":"sha256:9ed63c15cd0df41857f5a0c4b73547c99db18c73b77df23c7a94d7782cf7abcc","observation_id":"a016837c-4a05-42e1-b30e-e793c6fd24c5","resolution":{"observed_at":"2026-08-16T11:53:28.864222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.06668","last_updated":"2023-02-02T00:11:58Z","snapshot_observed_at":"2026-08-16T17:56:43.312126Z","submitted_at":"2021-09-14T13:16:33Z","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","version":6},"cited_work":{"arxiv_id":"2109.06668","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.06668","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Exploration in deep reinforcement learning: a comprehensive survey","venue":null,"work_id":"ef4e4410-69a7-4440-b8dc-938fa63a2f80","year":2021},"citing_paper":{"arxiv_id":"2605.01778","last_updated":"2026-05-03T08:31:24Z","snapshot_observed_at":"2026-08-14T03:28:12.234907Z","submitted_at":"2026-05-03T08:31:24Z","title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-10T15:23:34.582807Z"},"links":{"cited_paper":"/paper/2109.06668","citing_paper":"/paper/2605.01778"},"observation_digest":"sha256:ca58da02017c598fea40b166dfada2b94056f92eec61c90f7b93069b0ce814bd","observation_id":"d61e6545-3261-4fdf-a095-c774c0f0ad0a","resolution":{"observed_at":"2026-05-11T10:41:02.779291Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2109.06668/citation-record","integrity":"/paper/2109.06668/integrity","json":"/paper/2109.06668/citation-record.json","paper":"/paper/2109.06668"},"outbound":[],"paper":{"arxiv_id":"2109.06668","last_updated":"2023-02-02T00:11:58Z","latest_version":6,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T17:56:43.312126Z","submitted_at":"2021-09-14T13:16:33Z","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2109.06668."}