{"as_of":"2026-08-10T14:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2983bff214259cead12c9b8995772ddbd937a1f086db85c8f30b3c6188948c23","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":"2026-08-10T06:31:04.303077+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":"2026-08-09T05:02:13.337362Z","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":"2026-05-15T04:42:52.833456Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2202.01741","last_updated":"2022-07-08T16:22:28Z","snapshot_observed_at":"2026-08-10T10:12:43.722437Z","submitted_at":"2022-02-03T18:04:54Z","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","version":4},"cited_work":{"arxiv_id":"2202.01741","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.01741","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"How to leverage unlabeled data in offline reinforcement learning","venue":null,"work_id":"22b1c76b-44d5-4843-ac2e-ff277c3327d7","year":null},"citing_paper":{"arxiv_id":"2210.00030","last_updated":"2023-03-07T02:29:59Z","snapshot_observed_at":"2026-08-02T00:17:16.761436Z","submitted_at":"2022-09-30T18:14:07Z","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-15T04:42:52.627166Z"},"links":{"cited_paper":"/paper/2202.01741","citing_paper":"/paper/2210.00030"},"observation_digest":"sha256:6b79da9e559d84815618b90bc5ebbfd793aecb63509be5f439abe1a9d297e4fa","observation_id":"c68e7379-2819-4c1f-84e0-90d1c502ce2b","resolution":{"observed_at":"2026-05-15T04:42:52.836495Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2202.01741","last_updated":"2022-07-08T16:22:28Z","snapshot_observed_at":"2026-08-10T10:12:43.722437Z","submitted_at":"2022-02-03T18:04:54Z","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01741","snapshot_observed_at":"2026-08-09T05:02:13.337362Z","title":"How to leverage unlabeled data in offline reinforcement learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03369","last_updated":"2025-02-05T17:07:37Z","snapshot_observed_at":"2026-08-09T12:36:37.004381Z","submitted_at":"2025-02-05T17:07:37Z","title":"Learning from Active Human Involvement through Proxy Value Propagation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T05:02:13.337362Z"},"links":{"cited_paper":"/paper/2202.01741","citing_paper":"/paper/2502.03369"},"observation_digest":"sha256:43a736b1319e367ee44faf970999ee4a37eb374b7402d7065da3f691b54c73e6","observation_id":"4a6b2247-a7b6-4c53-8a33-62eec05ac09a","resolution":{"observed_at":"2026-08-09T05:02:13.337362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.01741","last_updated":"2022-07-08T16:22:28Z","snapshot_observed_at":"2026-08-10T10:12:43.722437Z","submitted_at":"2022-02-03T18:04:54Z","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01741","snapshot_observed_at":"2026-08-01T17:45:17.708685Z","title":"arXiv preprint arXiv:2202.01741 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17560","last_updated":"2026-07-20T05:09:36Z","snapshot_observed_at":"2026-08-05T13:38:45.921055Z","submitted_at":"2026-07-20T05:09:36Z","title":"Reinforcement Learning: From Algorithms To Foundation Models","version":1},"reference_index":217,"source":"arxiv_source","source_observed_at":"2026-08-01T17:45:17.708685Z"},"links":{"cited_paper":"/paper/2202.01741","citing_paper":"/paper/2607.17560"},"observation_digest":"sha256:13f8f0289aaeab15359143094f7a594e043a34c54c3bccf8b09cd96267dee777","observation_id":"a434c5ef-29ce-4767-afae-38d6881c0c75","resolution":{"observed_at":"2026-08-01T17:45:17.708685Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2202.01741/citation-record","integrity":"/paper/2202.01741/integrity","json":"/paper/2202.01741/citation-record.json","paper":"/paper/2202.01741"},"outbound":[],"paper":{"arxiv_id":"2202.01741","last_updated":"2022-07-08T16:22:28Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T10:12:43.722437Z","submitted_at":"2022-02-03T18:04:54Z","title":"How to Leverage Unlabeled Data in Offline 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":"2026-08-10T06:31:04.303077+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 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2202.01741."}