{"as_of":"2026-08-16T22:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e9372bfc65ec1a9c060cdb42a1f7ef172e14856791b2b50a8ff799ba14765c0","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":"2026-08-16T06:30:59.297886+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":"2026-08-16T11:47:06.619644Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-05-22T10:06:21.834699Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1608.02732","last_updated":"2016-08-09T09:02:01Z","snapshot_observed_at":"2026-08-14T21:44:53.101212Z","submitted_at":"2016-08-09T09:02:01Z","title":"On Lower Bounds for Regret in Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.02732","snapshot_observed_at":"2026-08-16T11:47:06.619644Z","title":"On lower bounds for regret in reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.14732","last_updated":"2025-04-25T21:54:56Z","snapshot_observed_at":"2026-08-16T11:39:45.416168Z","submitted_at":"2025-04-20T20:09:19Z","title":"Reinforcement Learning from Multi-level and Episodic Human Feedback","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-16T11:47:06.619644Z"},"links":{"cited_paper":"/paper/1608.02732","citing_paper":"/paper/2504.14732"},"observation_digest":"sha256:fafd66d0c42eec11dd7d77bd81d01eb96075b2695adb9c57b68f7f001a714b59","observation_id":"e4d25f93-6eda-42bf-9b74-568c7980d848","resolution":{"observed_at":"2026-08-16T11:47:06.619644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.02732","last_updated":"2016-08-09T09:02:01Z","snapshot_observed_at":"2026-08-14T21:44:53.101212Z","submitted_at":"2016-08-09T09:02:01Z","title":"On Lower Bounds for Regret in Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"1608.02732","doi":null,"metadata_source":"pith","pith_arxiv_id":"1608.02732","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On Lower Bounds for Regret in Reinforcement Learning","venue":"stat.ML","work_id":"28c1a129-d8b9-41fc-acdc-4ba26ff59e2d","year":2016},"citing_paper":{"arxiv_id":"2605.21214","last_updated":"2026-05-21T13:30:53Z","snapshot_observed_at":"2026-08-13T03:04:15.922231Z","submitted_at":"2026-05-20T14:08:33Z","title":"Behavior-Consistent Deep Reinforcement Learning","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-05-21T05:37:29.919862Z"},"links":{"cited_paper":"/paper/1608.02732","citing_paper":"/paper/2605.21214"},"observation_digest":"sha256:b5852e3950a9c303dfb6b687b4ae9578cdc9aa3b51fbaa1859f93ca2041a8f01","observation_id":"e75e0cff-0570-41a0-bb15-4f2498a1d214","resolution":{"observed_at":"2026-05-21T05:39:40.727776Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.02732","last_updated":"2016-08-09T09:02:01Z","snapshot_observed_at":"2026-08-14T21:44:53.101212Z","submitted_at":"2016-08-09T09:02:01Z","title":"On Lower Bounds for Regret in Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"1608.02732","doi":null,"metadata_source":"pith","pith_arxiv_id":"1608.02732","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On Lower Bounds for Regret in Reinforcement Learning","venue":"stat.ML","work_id":"28c1a129-d8b9-41fc-acdc-4ba26ff59e2d","year":2016},"citing_paper":{"arxiv_id":"2605.21214","last_updated":"2026-05-21T13:30:53Z","snapshot_observed_at":"2026-08-13T03:04:15.922231Z","submitted_at":"2026-05-20T14:08:33Z","title":"Behavior-Consistent Deep Reinforcement Learning","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-05-22T10:06:04.478006Z"},"links":{"cited_paper":"/paper/1608.02732","citing_paper":"/paper/2605.21214"},"observation_digest":"sha256:a05d01be0f99e06423589a0dcff7db555b7c17a8f7ddcb7033fb33a450a246bb","observation_id":"c2783902-abc4-4c9b-bd6d-8c5bd19b588c","resolution":{"observed_at":"2026-05-22T10:06:21.837414Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1608.02732/citation-record","integrity":"/paper/1608.02732/integrity","json":"/paper/1608.02732/citation-record.json","paper":"/paper/1608.02732"},"outbound":[],"paper":{"arxiv_id":"1608.02732","last_updated":"2016-08-09T09:02:01Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-14T21:44:53.101212Z","submitted_at":"2016-08-09T09:02:01Z","title":"On Lower Bounds for Regret in 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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1608.02732."}