{"as_of":"2026-08-11T13:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b14f1a4cdc511eda55eb7277827934e30bd8641261ce22ab0ef3ba0b72284a60","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":"2026-08-11T06:34:44.6726+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":"2026-08-02T18:45:23.170247Z","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":"2026-05-10T11:35:19.044780Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.00666","last_updated":"2024-11-01T15:29:10Z","snapshot_observed_at":"2026-08-06T09:39:34.103148Z","submitted_at":"2024-11-01T15:29:10Z","title":"Beyond the Boundaries of Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00666","snapshot_observed_at":"2026-08-02T18:45:23.170247Z","title":"Beyond the boundaries of proximal policy optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06009","last_updated":"2026-07-18T00:55:49Z","snapshot_observed_at":"2026-08-06T19:01:23.378136Z","submitted_at":"2026-03-06T08:07:08Z","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-02T18:45:23.170247Z"},"links":{"cited_paper":"/paper/2411.00666","citing_paper":"/paper/2603.06009"},"observation_digest":"sha256:e676a876258fc8730ffb897b72e735d45cbc0df18bb9338f83fb64a97ebd01e5","observation_id":"058f5053-c8a0-4149-a692-54718f1bd4a8","resolution":{"observed_at":"2026-08-02T18:45:23.170247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00666","last_updated":"2024-11-01T15:29:10Z","snapshot_observed_at":"2026-08-06T09:39:34.103148Z","submitted_at":"2024-11-01T15:29:10Z","title":"Beyond the Boundaries of Proximal Policy Optimization","version":1},"cited_work":{"arxiv_id":"2411.00666","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.00666","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Beyond the boundaries of proximal policy optimization","venue":null,"work_id":"0fca00b0-4efa-4f3e-976f-26cfc4874f8d","year":2024},"citing_paper":{"arxiv_id":"2604.18578","last_updated":"2026-04-30T14:35:55Z","snapshot_observed_at":"2026-08-11T13:35:33.213975Z","submitted_at":"2026-04-20T17:59:01Z","title":"Bounded Ratio Reinforcement Learning","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-10T04:50:11.020901Z"},"links":{"cited_paper":"/paper/2411.00666","citing_paper":"/paper/2604.18578"},"observation_digest":"sha256:bf47326de3e379812ee5d339b8d7cc4e4b6c225618e720ebf56704e719f30212","observation_id":"2f0d50e0-d134-4ab1-8ad7-78cc8fffc9f6","resolution":{"observed_at":"2026-05-10T11:35:19.046157Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.00666/citation-record","integrity":"/paper/2411.00666/integrity","json":"/paper/2411.00666/citation-record.json","paper":"/paper/2411.00666"},"outbound":[],"paper":{"arxiv_id":"2411.00666","last_updated":"2024-11-01T15:29:10Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T09:39:34.103148Z","submitted_at":"2024-11-01T15:29:10Z","title":"Beyond the Boundaries of Proximal Policy Optimization"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2411.00666."}