{"as_of":"2026-08-23T23:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a5860a86cc37dc569a13129595fe58220ba1f14825a4a130d491df117cb15ddb","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":"2026-07-01T05:28:28.298787Z","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":"2026-07-01T10:25:42.279123Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.04792","last_updated":"2024-12-11T09:40:27Z","snapshot_observed_at":"2026-08-16T13:20:33.280823Z","submitted_at":"2024-09-07T11:08:20Z","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","version":2},"cited_work":{"arxiv_id":"2409.04792","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.04792","snapshot_observed_at":"2026-07-01T10:25:42.279123Z","title":"Kenny Young and Tian Tian","venue":null,"work_id":"891b5821-3053-4c80-93dc-a0d0afa2601f","year":2024},"citing_paper":{"arxiv_id":"2605.05481","last_updated":"2026-06-17T20:11:22Z","snapshot_observed_at":"2026-08-12T13:28:54.823431Z","submitted_at":"2026-05-06T22:02:35Z","title":"Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-08T16:58:39.520620Z"},"links":{"cited_paper":"/paper/2409.04792","citing_paper":"/paper/2605.05481"},"observation_digest":"sha256:d33c522fb32fd05845e39db5806d5190c21dd104c4e0bba67519a25f6b3e0ff7","observation_id":"5d69c715-bb0a-45be-bed2-a36db91dc881","resolution":{"observed_at":"2026-05-11T17:56:05.358455Z","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":"2409.04792","last_updated":"2024-12-11T09:40:27Z","snapshot_observed_at":"2026-08-16T13:20:33.280823Z","submitted_at":"2024-09-07T11:08:20Z","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","version":2},"cited_work":{"arxiv_id":"2409.04792","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.04792","snapshot_observed_at":"2026-07-01T10:25:42.279123Z","title":"Kenny Young and Tian Tian","venue":null,"work_id":"891b5821-3053-4c80-93dc-a0d0afa2601f","year":2024},"citing_paper":{"arxiv_id":"2605.05481","last_updated":"2026-06-17T20:11:22Z","snapshot_observed_at":"2026-08-12T13:28:54.823431Z","submitted_at":"2026-05-06T22:02:35Z","title":"Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-30T23:41:30.860309Z"},"links":{"cited_paper":"/paper/2409.04792","citing_paper":"/paper/2605.05481"},"observation_digest":"sha256:9823da18a39719f9a3494a62e13b6c8a024618dbdebd41d24426ca3a702d191d","observation_id":"ac0ef233-a1f2-4cba-84c8-9a2b3b4ae1c8","resolution":{"observed_at":"2026-06-30T23:45:08.144479Z","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":"2409.04792","last_updated":"2024-12-11T09:40:27Z","snapshot_observed_at":"2026-08-16T13:20:33.280823Z","submitted_at":"2024-09-07T11:08:20Z","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","version":2},"cited_work":{"arxiv_id":"2409.04792","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.04792","snapshot_observed_at":"2026-07-01T10:25:42.279123Z","title":"Kenny Young and Tian Tian","venue":null,"work_id":"891b5821-3053-4c80-93dc-a0d0afa2601f","year":2024},"citing_paper":{"arxiv_id":"2606.31691","last_updated":"2026-06-30T14:04:26Z","snapshot_observed_at":"2026-08-13T05:18:37.585754Z","submitted_at":"2026-06-30T14:04:26Z","title":"FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-01T05:28:28.298787Z"},"links":{"cited_paper":"/paper/2409.04792","citing_paper":"/paper/2606.31691"},"observation_digest":"sha256:f4a8543352474b2e1992d2e178e93a0a525d5a6a3bbb798a78183e8f69e5e3c8","observation_id":"885ddcd0-b9ed-4882-9a81-0af74ef93f18","resolution":{"observed_at":"2026-07-01T10:25:42.280503Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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"}}],"links":{"evidence":"/evidence","html":"/paper/2409.04792/citation-record","integrity":"/paper/2409.04792/integrity","json":"/paper/2409.04792/citation-record.json","paper":"/paper/2409.04792"},"outbound":[],"paper":{"arxiv_id":"2409.04792","last_updated":"2024-12-11T09:40:27Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T13:20:33.280823Z","submitted_at":"2024-09-07T11:08:20Z","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn"},"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:2409.04792."}