{"as_of":"2026-08-08T02:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a6c2b1e1dc40948c550554c648078c36a7b4e8bdcaa774737a48d72b9a0aa77f","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T13:35:47.885604Z","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":"2026-08-07T13:35:53.447482Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.00885","last_updated":"2022-10-18T01:23:03Z","snapshot_observed_at":"2026-07-06T12:14:24.842188Z","submitted_at":"2021-12-01T23:21:48Z","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2112.00885","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.00885","snapshot_observed_at":"2026-08-07T13:35:53.447482Z","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","venue":"cs.LG","work_id":"504fd8cf-6f48-430b-a480-02276df3e5b9","year":2021},"citing_paper":{"arxiv_id":"2505.21841","last_updated":"2025-05-28T00:16:34Z","snapshot_observed_at":"2026-08-07T13:19:25.695756Z","submitted_at":"2025-05-28T00:16:34Z","title":"An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T13:35:47.885604Z"},"links":{"cited_paper":"/paper/2112.00885","citing_paper":"/paper/2505.21841"},"observation_digest":"sha256:ab2ab8e731ff46a6817bc07bb58808317ce5055fc1cecb5854364f9f3eb3d8a7","observation_id":"eff5fcfe-0b06-4347-bcf2-9688eb8b64b2","resolution":{"observed_at":"2026-08-07T13:35:53.527372Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.00885","last_updated":"2022-10-18T01:23:03Z","snapshot_observed_at":"2026-07-06T12:14:24.842188Z","submitted_at":"2021-12-01T23:21:48Z","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.00885","snapshot_observed_at":"2026-07-13T10:33:19.825936Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2604.04247","last_updated":"2026-04-05T20:07:48Z","snapshot_observed_at":"2026-07-13T10:33:16.289426Z","submitted_at":"2026-04-05T20:07:48Z","title":"Combee: Scaling Prompt Learning for Self-Improving Language Model Agents","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-13T10:33:19.825936Z"},"links":{"cited_paper":"/paper/2112.00885","citing_paper":"/paper/2604.04247"},"observation_digest":"sha256:5f3fb4464d6fa8d91b502447f42e8543d0f83aaeadb8b8d3f883bc1d06807247","observation_id":"4c8a3749-18fd-421a-82cc-c787a6c54e92","resolution":{"observed_at":"2026-07-13T10:33:19.825936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2112.00885/citation-record","integrity":"/paper/2112.00885/integrity","json":"/paper/2112.00885/citation-record.json","paper":"/paper/2112.00885"},"outbound":[],"paper":{"arxiv_id":"2112.00885","last_updated":"2022-10-18T01:23:03Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T12:14:24.842188Z","submitted_at":"2021-12-01T23:21:48Z","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:2112.00885."}