{"as_of":"2026-08-09T22:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:808f8b399b27c9ff606eba40460bac61588b8d8f31ae9182240d176e5187a44b","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T12:55:52.250621Z","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":"2026-05-12T07:41:48.588346Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.19909","last_updated":"2024-07-15T10:55:57Z","snapshot_observed_at":"2026-08-01T17:37:51.295130Z","submitted_at":"2024-05-30T10:20:55Z","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.19909","snapshot_observed_at":"2026-08-07T12:55:52.250621Z","title":"Adaptive advantage-guided policy regularization for offline reinforcement learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23871","last_updated":"2025-06-05T03:54:42Z","snapshot_observed_at":"2026-08-09T10:58:34.700826Z","submitted_at":"2025-05-29T11:36:41Z","title":"ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:55:52.250621Z"},"links":{"cited_paper":"/paper/2405.19909","citing_paper":"/paper/2505.23871"},"observation_digest":"sha256:e19a521d3bcda2876fd31f1084db39ed6cbe70cc900ee514418f43019dc9d668","observation_id":"81d71945-2dc4-486e-8ea6-8491f145900c","resolution":{"observed_at":"2026-08-07T12:55:52.250621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.19909","last_updated":"2024-07-15T10:55:57Z","snapshot_observed_at":"2026-08-01T17:37:51.295130Z","submitted_at":"2024-05-30T10:20:55Z","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2405.19909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.19909","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2405.19909 , year=","venue":null,"work_id":"b87c51a7-5a1c-44f6-af48-6545783c758f","year":null},"citing_paper":{"arxiv_id":"2605.08202","last_updated":"2026-05-06T01:21:53Z","snapshot_observed_at":"2026-07-06T23:20:28.875586Z","submitted_at":"2026-05-06T01:21:53Z","title":"Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-05-12T02:17:25.783688Z"},"links":{"cited_paper":"/paper/2405.19909","citing_paper":"/paper/2605.08202"},"observation_digest":"sha256:67c4db174bfd9d1245d34263f5d33a3f64c357227e7d3d0d1ba4ee563d9c2a6a","observation_id":"43d3317f-e2e1-49e9-8711-659a08b4c71a","resolution":{"observed_at":"2026-05-12T07:41:48.596590Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.19909/citation-record","integrity":"/paper/2405.19909/integrity","json":"/paper/2405.19909/citation-record.json","paper":"/paper/2405.19909"},"outbound":[],"paper":{"arxiv_id":"2405.19909","last_updated":"2024-07-15T10:55:57Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-01T17:37:51.295130Z","submitted_at":"2024-05-30T10:20:55Z","title":"Adaptive Advantage-Guided Policy Regularization for Offline 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.19909."}