{"as_of":"2026-08-09T07:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8cea173473984f5a1e76942f84f26a52de3a8529fbcdf3e6e29cb1697cdbe394","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T10:35:58.559435Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":2,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.07536","last_updated":"2022-12-14T22:43:56Z","snapshot_observed_at":"2026-08-08T07:01:25.137948Z","submitted_at":"2022-12-14T22:43:56Z","title":"Robust Policy Optimization in Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.07536","snapshot_observed_at":"2026-08-07T10:35:58.559435Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.05445","last_updated":"2025-06-05T13:52:38Z","snapshot_observed_at":"2026-08-07T10:24:36.469912Z","submitted_at":"2025-06-05T13:52:38Z","title":"Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T10:35:58.559435Z"},"links":{"cited_paper":"/paper/2212.07536","citing_paper":"/paper/2506.05445"},"observation_digest":"sha256:c341fbefd579a101620a7c9bf1f8995fb17b8eb4665b892627523c705497ff01","observation_id":"217fafc5-d441-4cde-a5b1-50b4c0ab6376","resolution":{"observed_at":"2026-08-07T10:35:58.559435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.07536","last_updated":"2022-12-14T22:43:56Z","snapshot_observed_at":"2026-08-08T07:01:25.137948Z","submitted_at":"2022-12-14T22:43:56Z","title":"Robust Policy Optimization in Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2212.07536","doi":"10.48550/arxiv.2212.07536","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.07536","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Rahman, Y","venue":"arXiv (Cornell University)","work_id":"2f2a0394-ed10-48ff-b225-37f3cf59b064","year":2022},"citing_paper":{"arxiv_id":"2506.07339","last_updated":"2025-12-05T07:35:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-09T01:01:59Z","title":"Real-Time Execution of Action Chunking Flow Policies","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-15T14:18:51.613045Z"},"links":{"cited_paper":"/paper/2212.07536","citing_paper":"/paper/2506.07339"},"observation_digest":"sha256:c0074f84c7c87006b3c0da8f91d9f2c0303eca8971e0f86d19d04af65422a9f2","observation_id":"d7f800f9-1ab3-4467-a583-d9b4a07965cd","resolution":{"observed_at":"2026-05-15T14:18:51.659871Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-21T15:23:00.473561+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T15:23:00.473561+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.07536","last_updated":"2022-12-14T22:43:56Z","snapshot_observed_at":"2026-08-08T07:01:25.137948Z","submitted_at":"2022-12-14T22:43:56Z","title":"Robust Policy Optimization in Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2212.07536","doi":"10.48550/arxiv.2212.07536","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.07536","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Rahman, Y","venue":"arXiv (Cornell University)","work_id":"2f2a0394-ed10-48ff-b225-37f3cf59b064","year":2022},"citing_paper":{"arxiv_id":"2605.20644","last_updated":"2026-05-20T03:07:00Z","snapshot_observed_at":"2026-07-06T23:31:13.042581Z","submitted_at":"2026-05-20T03:07:00Z","title":"Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-21T06:20:25.205139Z"},"links":{"cited_paper":"/paper/2212.07536","citing_paper":"/paper/2605.20644"},"observation_digest":"sha256:505a57095856a6605a7117936b3fd71b9ec2f00a15e55f87df9113e59e42bc03","observation_id":"9224248e-99b7-44a1-9f02-2b490040456b","resolution":{"observed_at":"2026-05-21T06:24:00.404680Z","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":"2026-05-21T15:23:00.473561+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T15:23:00.473561+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2212.07536/citation-record","integrity":"/paper/2212.07536/integrity","json":"/paper/2212.07536/citation-record.json","paper":"/paper/2212.07536"},"outbound":[],"paper":{"arxiv_id":"2212.07536","last_updated":"2022-12-14T22:43:56Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T07:01:25.137948Z","submitted_at":"2022-12-14T22:43:56Z","title":"Robust Policy Optimization in Deep 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 3 inbound Pith citation observations for arXiv:2212.07536."}