{"as_of":"2026-08-23T23:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:375ceef5101b38d0137bfae9cc9a1b4b9972129ab7adec9d0eff2e9dd1ee9f5e","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":"2026-08-23T06:30:58.430688+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":"2026-08-15T14:39:15.516180Z","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":"2026-05-16T08:17:36.497807Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2005.06392","last_updated":"2022-06-02T06:16:17Z","snapshot_observed_at":"2026-08-15T19:04:43.031317Z","submitted_at":"2020-05-13T16:01:39Z","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","version":3},"cited_work":{"arxiv_id":"2005.06392","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.06392","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"375a6221-4b78-443a-bd26-90d3a3257db6","year":2022},"citing_paper":{"arxiv_id":"2602.01505","last_updated":"2026-05-06T16:04:38Z","snapshot_observed_at":"2026-08-11T14:55:55.889399Z","submitted_at":"2026-02-02T00:35:42Z","title":"Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-16T08:12:57.430291Z"},"links":{"cited_paper":"/paper/2005.06392","citing_paper":"/paper/2602.01505"},"observation_digest":"sha256:99b06addcf7e6c1f3c41477c95051c46696204f444d9f14e3f704b88e843fd40","observation_id":"c216de61-5a8b-45e0-a88a-3a378f821381","resolution":{"observed_at":"2026-05-16T08:17:36.499390Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.06392","last_updated":"2022-06-02T06:16:17Z","snapshot_observed_at":"2026-08-15T19:04:43.031317Z","submitted_at":"2020-05-13T16:01:39Z","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.06392","snapshot_observed_at":"2026-08-04T00:53:27.440871Z","title":"2020 , title =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.00301","last_updated":"2026-07-31T21:31:07Z","snapshot_observed_at":"2026-08-14T19:42:48.000510Z","submitted_at":"2026-07-31T21:31:07Z","title":"Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T00:53:27.440871Z"},"links":{"cited_paper":"/paper/2005.06392","citing_paper":"/paper/2608.00301"},"observation_digest":"sha256:c50e2a7ce009b14f853f03a39830e291ea38ee6030a5d74d033c331946ab3b76","observation_id":"48d7edbf-492b-4f17-ad60-91b93f9125f3","resolution":{"observed_at":"2026-08-04T00:53:27.440871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.06392","last_updated":"2022-06-02T06:16:17Z","snapshot_observed_at":"2026-08-15T19:04:43.031317Z","submitted_at":"2020-05-13T16:01:39Z","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.06392","snapshot_observed_at":"2026-08-15T14:39:15.516180Z","title":"arXiv preprint arXiv:2005.06392 , year=","venue":null,"work_id":null,"year":2005},"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":60,"source":"arxiv_source","source_observed_at":"2026-08-15T14:39:15.516180Z"},"links":{"cited_paper":"/paper/2005.06392","citing_paper":"/paper/2608.06545"},"observation_digest":"sha256:deb0d6c4771565519398d10832e914a586bfa4d76b37ed0880b87f239c8ab455","observation_id":"a2746f34-f148-4e9d-b074-5d3f586fae8e","resolution":{"observed_at":"2026-08-15T14:39:15.516180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2005.06392/citation-record","integrity":"/paper/2005.06392/integrity","json":"/paper/2005.06392/citation-record.json","paper":"/paper/2005.06392"},"outbound":[],"paper":{"arxiv_id":"2005.06392","last_updated":"2022-06-02T06:16:17Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T19:04:43.031317Z","submitted_at":"2020-05-13T16:01:39Z","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2005.06392."}