{"as_of":"2026-08-15T16:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4dddcc18f951e88a87a681277dfc445ffc65f5e315105f7a113a7ee36d5da673","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T11:13:43.723740Z","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":"2026-08-10T11:13:43.777774Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.16383","last_updated":"2024-05-26T00:01:29Z","snapshot_observed_at":"2026-08-12T23:57:58.236909Z","submitted_at":"2024-05-26T00:01:29Z","title":"Rewarded Region Replay (R3) for Policy Learning with Discrete Action Space","version":1},"cited_work":{"arxiv_id":"2405.16383","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.16383","snapshot_observed_at":"2026-08-10T11:13:43.777774Z","title":"Rewarded Region Replay (R3) for Policy Learning with Discrete Action Space","venue":"cs.LG","work_id":"b092d159-820c-4745-a8eb-50814339da1b","year":2024},"citing_paper":{"arxiv_id":"2608.07280","last_updated":"2026-08-07T14:39:10Z","snapshot_observed_at":"2026-08-15T15:09:22.453192Z","submitted_at":"2026-08-07T14:39:10Z","title":"Why Study Emergent Behavior When You Can Regulate It? Aligning Multi-Agent Systems with Reward Prediction","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T11:13:43.723740Z"},"links":{"cited_paper":"/paper/2405.16383","citing_paper":"/paper/2608.07280"},"observation_digest":"sha256:b814157eedf58e76aa25edaecb188e959c1bcdb3a4578f00be1ca414d7160ccc","observation_id":"af4e319c-b131-4fb0-9454-55da045c73ca","resolution":{"observed_at":"2026-08-10T11:13:43.783942Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.16383/citation-record","integrity":"/paper/2405.16383/integrity","json":"/paper/2405.16383/citation-record.json","paper":"/paper/2405.16383"},"outbound":[],"paper":{"arxiv_id":"2405.16383","last_updated":"2024-05-26T00:01:29Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T23:57:58.236909Z","submitted_at":"2024-05-26T00:01:29Z","title":"Rewarded Region Replay (R3) for Policy Learning with Discrete Action Space"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2405.16383."}