{"as_of":"2026-08-08T17:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2d4ca081a9b9f889c4b083219ede5f02b5cdc99d7ba294080ec390c177e7f1a8","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T12:05:26.062222Z","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":"2026-05-11T04:30:58.548818Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2302.08865","last_updated":"2023-02-17T13:22:40Z","snapshot_observed_at":"2026-07-06T14:52:56.806494Z","submitted_at":"2023-02-17T13:22:40Z","title":"Swapped goal-conditioned offline reinforcement learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.08865","snapshot_observed_at":"2026-08-07T12:05:26.062222Z","title":"a m \\\"a r \\","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00795","last_updated":"2025-09-11T03:42:40Z","snapshot_observed_at":"2026-08-07T11:55:27.735310Z","submitted_at":"2025-06-01T02:49:26Z","title":"Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization","version":3},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-07T12:05:26.062222Z"},"links":{"cited_paper":"/paper/2302.08865","citing_paper":"/paper/2506.00795"},"observation_digest":"sha256:67403e0e27f183b457fd6448c0bf553b4fd86ecceca9d853c42f23663b30caeb","observation_id":"77db9b91-9fca-46a6-9296-56fca0933486","resolution":{"observed_at":"2026-08-07T12:05:26.062222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.08865","last_updated":"2023-02-17T13:22:40Z","snapshot_observed_at":"2026-07-06T14:52:56.806494Z","submitted_at":"2023-02-17T13:22:40Z","title":"Swapped goal-conditioned offline reinforcement learning","version":1},"cited_work":{"arxiv_id":"2302.08865","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.08865","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2302.08865 , year=","venue":null,"work_id":"03d241d5-720c-4d20-a68d-526088ee045a","year":null},"citing_paper":{"arxiv_id":"2605.01862","last_updated":"2026-05-08T03:23:44Z","snapshot_observed_at":"2026-07-06T23:15:01.968194Z","submitted_at":"2026-05-03T13:11:28Z","title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","version":2},"reference_index":218,"source":"arxiv_source","source_observed_at":"2026-05-11T01:17:48.643521Z"},"links":{"cited_paper":"/paper/2302.08865","citing_paper":"/paper/2605.01862"},"observation_digest":"sha256:75e2305c78056cef4587369e02eca266ece1ee16866d88b482e04b88f736a944","observation_id":"2617e147-8ff9-4110-a2b6-02dee8b52e4c","resolution":{"observed_at":"2026-05-11T04:30:58.561372Z","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/2302.08865/citation-record","integrity":"/paper/2302.08865/integrity","json":"/paper/2302.08865/citation-record.json","paper":"/paper/2302.08865"},"outbound":[],"paper":{"arxiv_id":"2302.08865","last_updated":"2023-02-17T13:22:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T14:52:56.806494Z","submitted_at":"2023-02-17T13:22:40Z","title":"Swapped goal-conditioned 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":"2026-08-08T06:32:00.761636+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 2 inbound Pith citation observations for arXiv:2302.08865."}