{"as_of":"2026-08-11T17:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:27145cf2eaf9fe31554c8c6909ca3ba5913305b6fba1e9cbe9e89655276cb634","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T12:06:20.410377Z","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":"2026-05-12T02:11:15.741874Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.07198","last_updated":"2024-02-11T13:25:53Z","snapshot_observed_at":"2026-08-10T13:36:52.860053Z","submitted_at":"2024-02-11T13:25:53Z","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07198","snapshot_observed_at":"2026-08-09T12:06:20.410377Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02486","last_updated":"2025-02-04T17:03:32Z","snapshot_observed_at":"2026-08-10T00:13:28.338045Z","submitted_at":"2025-02-04T17:03:32Z","title":"Catoni Contextual Bandits are Robust to Heavy-tailed Rewards","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T12:06:20.410377Z"},"links":{"cited_paper":"/paper/2402.07198","citing_paper":"/paper/2502.02486"},"observation_digest":"sha256:456f37cac87ec2d578987e4d928146a8b34e5962781f4c4af3cf369d3f4d5d31","observation_id":"e436da6d-d4cb-4263-92f1-287d22690f4f","resolution":{"observed_at":"2026-08-09T12:06:20.410377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07198","last_updated":"2024-02-11T13:25:53Z","snapshot_observed_at":"2026-08-10T13:36:52.860053Z","submitted_at":"2024-02-11T13:25:53Z","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07198","snapshot_observed_at":"2026-08-04T11:01:34.735036Z","title":"More benefits of being distributional: Second-order bounds for reinforcement learning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.07650","last_updated":"2026-05-30T05:26:12Z","snapshot_observed_at":"2026-08-04T11:01:21.243413Z","submitted_at":"2025-10-09T00:57:40Z","title":"Value Flows","version":4},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-04T11:01:34.735036Z"},"links":{"cited_paper":"/paper/2402.07198","citing_paper":"/paper/2510.07650"},"observation_digest":"sha256:b31b8c92f821f82f080b305ef2a4ac8634d4aa7287bd32ab3f01f9f215108589","observation_id":"90abeef2-eaea-45ce-a822-7ef69123956b","resolution":{"observed_at":"2026-08-04T11:01:34.735036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07198","last_updated":"2024-02-11T13:25:53Z","snapshot_observed_at":"2026-08-10T13:36:52.860053Z","submitted_at":"2024-02-11T13:25:53Z","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2402.07198","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.07198","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2402.07198 , year=","venue":null,"work_id":"1696e06b-f4c8-4c2b-ba5d-243e2faa0450","year":2024},"citing_paper":{"arxiv_id":"2605.01663","last_updated":"2026-05-28T02:21:27Z","snapshot_observed_at":"2026-08-11T13:45:14.782986Z","submitted_at":"2026-05-03T01:32:11Z","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-10T16:25:25.739019Z"},"links":{"cited_paper":"/paper/2402.07198","citing_paper":"/paper/2605.01663"},"observation_digest":"sha256:0f1da1a1cad560ee5144258683530c7d777dbf6cc31b1f3a867b1f41b61e977f","observation_id":"8df89cf0-199f-437a-9aea-bb257d1208cf","resolution":{"observed_at":"2026-05-11T08:56:00.730098Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07198","last_updated":"2024-02-11T13:25:53Z","snapshot_observed_at":"2026-08-10T13:36:52.860053Z","submitted_at":"2024-02-11T13:25:53Z","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2402.07198","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.07198","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2402.07198 , year=","venue":null,"work_id":"1696e06b-f4c8-4c2b-ba5d-243e2faa0450","year":2024},"citing_paper":{"arxiv_id":"2605.08515","last_updated":"2026-05-08T21:49:37Z","snapshot_observed_at":"2026-07-06T23:20:43.010758Z","submitted_at":"2026-05-08T21:49:37Z","title":"Quantile-Coupled Flow Matching for Distributional Reinforcement Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-12T02:09:35.261274Z"},"links":{"cited_paper":"/paper/2402.07198","citing_paper":"/paper/2605.08515"},"observation_digest":"sha256:ea006643642251c4173bb7b156e864ae708caca5cca790fb47b83dbefdf9e65f","observation_id":"0f50cbd7-13b1-47b8-a3ef-c2e34c0a4efe","resolution":{"observed_at":"2026-05-12T02:11:15.743849Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.07198/citation-record","integrity":"/paper/2402.07198/integrity","json":"/paper/2402.07198/citation-record.json","paper":"/paper/2402.07198"},"outbound":[],"paper":{"arxiv_id":"2402.07198","last_updated":"2024-02-11T13:25:53Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T13:36:52.860053Z","submitted_at":"2024-02-11T13:25:53Z","title":"More Benefits of Being Distributional: Second-Order Bounds for 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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.07198."}