{"as_of":"2026-08-18T15:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4eed70d0ffb582285c742716ee2fcd95ca297f07130e149eb47bd999e40c58f2","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:14:54.333775Z","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":"2026-05-19T05:12:05.204790Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2107.00591","last_updated":"2021-10-30T04:21:12Z","snapshot_observed_at":"2026-08-18T07:30:05.382768Z","submitted_at":"2021-07-01T16:26:54Z","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.00591","snapshot_observed_at":"2026-08-16T10:14:54.333775Z","title":"Offline-to- online reinforcement learning via balanced replay and pessimistic q-ensemble, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.18766","last_updated":"2025-04-26T02:12:02Z","snapshot_observed_at":"2026-08-17T14:40:59.739803Z","submitted_at":"2025-04-26T02:12:02Z","title":"Dynamic Action Interpolation: A Universal Approach for Accelerating Reinforcement Learning with Expert Guidance","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T10:14:54.333775Z"},"links":{"cited_paper":"/paper/2107.00591","citing_paper":"/paper/2504.18766"},"observation_digest":"sha256:775fc6a8bdc7fcffa91ee4cc3e986bb18f00ed426e2e1201bfb38bb4136e068e","observation_id":"6025f4a1-3a8e-473c-82c0-c882325869c0","resolution":{"observed_at":"2026-08-16T10:14:54.333775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.00591","last_updated":"2021-10-30T04:21:12Z","snapshot_observed_at":"2026-08-18T07:30:05.382768Z","submitted_at":"2021-07-01T16:26:54Z","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","version":2},"cited_work":{"arxiv_id":"2107.00591","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.00591","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Qiyang Li, Jason Zhang, Dibya Ghosh, Amy Zhang, and Sergey Levine","venue":null,"work_id":"070c928a-0a34-45b6-a457-473000a3825f","year":null},"citing_paper":{"arxiv_id":"2507.07986","last_updated":"2026-04-30T00:00:17Z","snapshot_observed_at":"2026-08-08T11:51:09.954364Z","submitted_at":"2025-07-10T17:57:46Z","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-19T05:09:02.111308Z"},"links":{"cited_paper":"/paper/2107.00591","citing_paper":"/paper/2507.07986"},"observation_digest":"sha256:155c9b8ca0d5922db97526bacef76f254ce94fb11fbbaf20372f94bad66b8b49","observation_id":"a8a6229e-434f-4494-9d03-c227d8269702","resolution":{"observed_at":"2026-05-19T05:12:05.207294Z","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/2107.00591/citation-record","integrity":"/paper/2107.00591/integrity","json":"/paper/2107.00591/citation-record.json","paper":"/paper/2107.00591"},"outbound":[],"paper":{"arxiv_id":"2107.00591","last_updated":"2021-10-30T04:21:12Z","latest_version":2,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-18T07:30:05.382768Z","submitted_at":"2021-07-01T16:26:54Z","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble"},"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 2 inbound Pith citation observations for arXiv:2107.00591."}