{"as_of":"2026-08-18T09:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f9c469d34c9754027cc7388f8f34567e9b92b8cf9817ce3592d26b1269174a2","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":"2026-08-18T06:34:40.430872+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":"2026-08-15T20:45:55.493828Z","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":"2026-05-12T01:41:19.856098Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.11721","last_updated":"2024-09-21T15:32:03Z","snapshot_observed_at":"2026-08-16T15:59:42.939512Z","submitted_at":"2023-01-27T14:08:09Z","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.11721","snapshot_observed_at":"2026-08-15T20:45:55.493828Z","title":"Single-trajectory distributionally robust reinforcement learning.arXiv preprint arXiv:2301.11721, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12462","last_updated":"2026-06-21T21:20:26Z","snapshot_observed_at":"2026-08-17T19:23:25.884434Z","submitted_at":"2025-05-18T15:34:45Z","title":"Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T20:45:55.493828Z"},"links":{"cited_paper":"/paper/2301.11721","citing_paper":"/paper/2505.12462"},"observation_digest":"sha256:3fcc94f30e923ad950806ba5f4dd6ccacd5e24b97c659de870b0c9f2412715e7","observation_id":"ae1f8c9d-162f-4da7-a650-84c95a131da9","resolution":{"observed_at":"2026-08-15T20:45:55.493828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.11721","last_updated":"2024-09-21T15:32:03Z","snapshot_observed_at":"2026-08-16T15:59:42.939512Z","submitted_at":"2023-01-27T14:08:09Z","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2301.11721","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.11721","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"24f7ae69-8c53-4f7b-9ea3-09d5ac732484","year":2023},"citing_paper":{"arxiv_id":"2605.08417","last_updated":"2026-05-08T19:24:28Z","snapshot_observed_at":"2026-07-06T23:20:38.385189Z","submitted_at":"2026-05-08T19:24:28Z","title":"Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-12T01:40:22.323345Z"},"links":{"cited_paper":"/paper/2301.11721","citing_paper":"/paper/2605.08417"},"observation_digest":"sha256:3b2fdff0fbfd0296f23bb055e1d09c8a4e7994ca7dedd56b39dbbbd6b551547f","observation_id":"de6aaa8c-cc98-487e-80f7-0300caaf1a71","resolution":{"observed_at":"2026-05-12T01:41:19.858872Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2301.11721","last_updated":"2024-09-21T15:32:03Z","snapshot_observed_at":"2026-08-16T15:59:42.939512Z","submitted_at":"2023-01-27T14:08:09Z","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.11721","snapshot_observed_at":"2026-08-15T14:39:15.788295Z","title":"arXiv preprint arXiv:2301.11721 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.06545","last_updated":"2026-08-06T19:49:48Z","snapshot_observed_at":"2026-08-16T19:41:39.037201Z","submitted_at":"2026-08-06T19:49:48Z","title":"Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions","version":1},"reference_index":147,"source":"arxiv_source","source_observed_at":"2026-08-15T14:39:15.788295Z"},"links":{"cited_paper":"/paper/2301.11721","citing_paper":"/paper/2608.06545"},"observation_digest":"sha256:001993ab362528cd2bd54627220b69bc6f5291098538fd6d144b32849487232d","observation_id":"10fad8db-5da1-432e-832b-c660d423866f","resolution":{"observed_at":"2026-08-15T14:39:15.788295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2301.11721/citation-record","integrity":"/paper/2301.11721/integrity","json":"/paper/2301.11721/citation-record.json","paper":"/paper/2301.11721"},"outbound":[],"paper":{"arxiv_id":"2301.11721","last_updated":"2024-09-21T15:32:03Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-16T15:59:42.939512Z","submitted_at":"2023-01-27T14:08:09Z","title":"Single-Trajectory Distributionally Robust 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":"2026-08-18T06:34:40.430872+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 3 inbound Pith citation observations for arXiv:2301.11721."}