{"as_of":"2026-08-16T09:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:de8d599d3da1c9383dbce65bb72acb23fde13e0e2f939c78d883f9c7d1688c9d","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":"2026-08-16T06:30:59.297886+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":"2026-08-10T20:56:51.074552Z","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":"2026-08-10T20:13:58.440169Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.01972","last_updated":"2024-08-04T09:26:00Z","snapshot_observed_at":"2026-08-15T18:53:59.860697Z","submitted_at":"2024-08-04T09:26:00Z","title":"RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.01972","snapshot_observed_at":"2026-08-10T20:56:51.074552Z","title":"and Ono, I","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06937","last_updated":"2025-01-12T21:24:27Z","snapshot_observed_at":"2026-08-15T14:32:10.018340Z","submitted_at":"2025-01-12T21:24:27Z","title":"An Empirical Study of Deep Reinforcement Learning in Continuing Tasks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T20:56:51.074552Z"},"links":{"cited_paper":"/paper/2408.01972","citing_paper":"/paper/2501.06937"},"observation_digest":"sha256:11a23a54a16be3e48f82ca4c292a9485e81b6525d1cecf24102edab443f0b5b3","observation_id":"3577ed12-96a2-4ede-afe8-fbe2a3f4b295","resolution":{"observed_at":"2026-08-10T20:56:51.074552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.01972","last_updated":"2024-08-04T09:26:00Z","snapshot_observed_at":"2026-08-15T18:53:59.860697Z","submitted_at":"2024-08-04T09:26:00Z","title":"RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2408.01972","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.01972","snapshot_observed_at":"2026-08-10T20:13:58.440169Z","title":"RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning","venue":"cs.LG","work_id":"9391718e-9fb0-4071-bada-83a355b08d95","year":2024},"citing_paper":{"arxiv_id":"2501.09080","last_updated":"2025-08-05T14:35:10Z","snapshot_observed_at":"2026-08-13T04:32:34.139354Z","submitted_at":"2025-01-15T19:00:46Z","title":"Average-Reward Soft Actor-Critic","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-10T20:13:57.513390Z"},"links":{"cited_paper":"/paper/2408.01972","citing_paper":"/paper/2501.09080"},"observation_digest":"sha256:a634b3d8cbb43145abb0be7821bbb8d234617f2b62603987d4c02a1b11dce75f","observation_id":"b7e82671-4a27-4b1f-b938-ed127239bce1","resolution":{"observed_at":"2026-08-10T20:13:58.447879Z","resolver_source":"local_arxiv","status":"verified_exact"},"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/2408.01972/citation-record","integrity":"/paper/2408.01972/integrity","json":"/paper/2408.01972/citation-record.json","paper":"/paper/2408.01972"},"outbound":[],"paper":{"arxiv_id":"2408.01972","last_updated":"2024-08-04T09:26:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T18:53:59.860697Z","submitted_at":"2024-08-04T09:26:00Z","title":"RVI-SAC: Average Reward Off-Policy Deep 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 2 inbound Pith citation observations for arXiv:2408.01972."}