{"as_of":"2026-08-16T10:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f60f1d429052c49a842a5d57e114ea1061b1bb4b8035e4bb9e0c67357fa11b9b","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":"2026-08-15T15:43:00.040269Z","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":"2026-08-15T14:55:08.844282Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2210.00991","last_updated":"2023-08-29T09:23:24Z","snapshot_observed_at":"2026-08-13T14:14:03.595022Z","submitted_at":"2022-10-03T14:57:46Z","title":"Policy Gradient for Reinforcement Learning with General Utilities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.00991","snapshot_observed_at":"2026-08-15T15:43:00.040269Z","title":"Policy gradient for reinforcement learning with general utilities","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17823","last_updated":"2026-07-20T11:11:55Z","snapshot_observed_at":"2026-08-16T05:07:56.523272Z","submitted_at":"2026-07-20T11:11:55Z","title":"Theoretical Foundations of $\\max$@$k$ Reinforcement Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T15:43:00.040269Z"},"links":{"cited_paper":"/paper/2210.00991","citing_paper":"/paper/2607.17823"},"observation_digest":"sha256:1d02bdb685d9f41b32e7dfa5235ef2a592ae855bba4683d5ed7d5c1bfbcd22ed","observation_id":"22699b3b-7ddc-46f0-811d-a0fbd40a406e","resolution":{"observed_at":"2026-08-15T15:43:00.040269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.00991","last_updated":"2023-08-29T09:23:24Z","snapshot_observed_at":"2026-08-13T14:14:03.595022Z","submitted_at":"2022-10-03T14:57:46Z","title":"Policy Gradient for Reinforcement Learning with General Utilities","version":2},"cited_work":{"arxiv_id":"2210.00991","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.00991","snapshot_observed_at":"2026-08-15T14:55:08.844282Z","title":"Policy Gradient for Reinforcement Learning with General Utilities","venue":"cs.LG","work_id":"560a74e9-fb9a-42df-9630-7ec6fd4ebd19","year":2022},"citing_paper":{"arxiv_id":"2608.03562","last_updated":"2026-08-04T12:28:39Z","snapshot_observed_at":"2026-08-15T14:46:44.692808Z","submitted_at":"2026-08-04T12:28:39Z","title":"Robust General Utility for Reinforcement Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T14:55:08.124826Z"},"links":{"cited_paper":"/paper/2210.00991","citing_paper":"/paper/2608.03562"},"observation_digest":"sha256:80f153c3a6746f8f33a2ca19e4d0656c96c12831a730b7e85ca02506427d3607","observation_id":"60ff3331-aebe-468e-9113-7fd653844445","resolution":{"observed_at":"2026-08-15T14:55:08.848775Z","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/2210.00991/citation-record","integrity":"/paper/2210.00991/integrity","json":"/paper/2210.00991/citation-record.json","paper":"/paper/2210.00991"},"outbound":[],"paper":{"arxiv_id":"2210.00991","last_updated":"2023-08-29T09:23:24Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T14:14:03.595022Z","submitted_at":"2022-10-03T14:57:46Z","title":"Policy Gradient for Reinforcement Learning with General Utilities"},"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:2210.00991."}