{"as_of":"2026-08-22T22:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:970ad3e66331c2a7ecd526659702bdc94c13d74d28c846658b2d24686fd760b7","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":"2026-08-22T06:32:14.747728+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":"2026-08-15T21:45:35.140853Z","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":"2026-05-18T14:02:39.876114Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.09123","last_updated":"2022-05-18T17:58:54Z","snapshot_observed_at":"2026-08-20T17:40:47.812510Z","submitted_at":"2022-05-18T17:58:54Z","title":"A2C is a special case of PPO","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.09123","snapshot_observed_at":"2026-08-15T21:45:35.140853Z","title":"”A2C is a special case of PPO.” arXiv preprint arXiv:2205.09123 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.09029","last_updated":"2025-05-13T23:56:12Z","snapshot_observed_at":"2026-08-20T11:05:33.705067Z","submitted_at":"2025-05-13T23:56:12Z","title":"Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T21:45:35.140853Z"},"links":{"cited_paper":"/paper/2205.09123","citing_paper":"/paper/2505.09029"},"observation_digest":"sha256:80302c26009452271f58e1f1659c0d3426cf16e50620f33e08edac19a22fa1b3","observation_id":"845e944e-000f-4355-ab96-3c7494df062e","resolution":{"observed_at":"2026-08-15T21:45:35.140853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.09123","last_updated":"2022-05-18T17:58:54Z","snapshot_observed_at":"2026-08-20T17:40:47.812510Z","submitted_at":"2022-05-18T17:58:54Z","title":"A2C is a special case of PPO","version":1},"cited_work":{"arxiv_id":"2205.09123","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.09123","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A2c is a special case of ppo","venue":null,"work_id":"a15fc7b5-740b-47c1-ba97-e2f20098cdf8","year":2022},"citing_paper":{"arxiv_id":"2509.20265","last_updated":"2026-04-29T12:32:16Z","snapshot_observed_at":"2026-08-15T04:57:38.385397Z","submitted_at":"2025-09-24T15:52:36Z","title":"Failure Modes of Maximum Entropy RLHF","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-05-18T14:02:11.084514Z"},"links":{"cited_paper":"/paper/2205.09123","citing_paper":"/paper/2509.20265"},"observation_digest":"sha256:12357e4d45b6b4c5771d7ce79cfbb4330776aef985573c25e6841de0591e2e3b","observation_id":"7285566d-fcd6-4ddd-ac29-8f1ce0ab926d","resolution":{"observed_at":"2026-05-18T14:02:39.878641Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2205.09123/citation-record","integrity":"/paper/2205.09123/integrity","json":"/paper/2205.09123/citation-record.json","paper":"/paper/2205.09123"},"outbound":[],"paper":{"arxiv_id":"2205.09123","last_updated":"2022-05-18T17:58:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T17:40:47.812510Z","submitted_at":"2022-05-18T17:58:54Z","title":"A2C is a special case of PPO"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2205.09123."}