{"as_of":"2026-08-03T22:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0f4cdd232ff9661e78d8cc2e5acff20743dda5bf00c9971bd553dd6b3918f4dc","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":"2026-08-03T06:30:56.289259+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":"2026-06-25T21:17:28.832301Z","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":"2026-07-04T19:30:07.606033Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.13799","last_updated":"2022-09-01T03:43:25Z","snapshot_observed_at":"2026-07-06T12:02:01.569473Z","submitted_at":"2021-10-26T15:56:57Z","title":"Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective","version":4},"cited_work":{"arxiv_id":"2110.13799","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.13799","snapshot_observed_at":"2026-07-04T19:30:07.606033Z","title":"arXiv preprint arXiv:2110.13799 , year=","venue":null,"work_id":"7b5599df-da32-4cc8-b157-db011273f56a","year":2021},"citing_paper":{"arxiv_id":"2605.18591","last_updated":"2026-05-18T16:05:36Z","snapshot_observed_at":"2026-07-06T23:29:29.105126Z","submitted_at":"2026-05-18T16:05:36Z","title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","version":1},"reference_index":135,"source":"arxiv_source","source_observed_at":"2026-05-20T12:44:29.147095Z"},"links":{"cited_paper":"/paper/2110.13799","citing_paper":"/paper/2605.18591"},"observation_digest":"sha256:b41341f8868ba001347cd5a3417dc4fa2ffe471ff27b6c61f108e3963930defa","observation_id":"5500c30a-bf41-446d-8bfe-a68afde016f7","resolution":{"observed_at":"2026-05-20T12:48:17.561580Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.13799","last_updated":"2022-09-01T03:43:25Z","snapshot_observed_at":"2026-07-06T12:02:01.569473Z","submitted_at":"2021-10-26T15:56:57Z","title":"Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective","version":4},"cited_work":{"arxiv_id":"2110.13799","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.13799","snapshot_observed_at":"2026-07-04T19:30:07.606033Z","title":"arXiv preprint arXiv:2110.13799 , year=","venue":null,"work_id":"7b5599df-da32-4cc8-b157-db011273f56a","year":2021},"citing_paper":{"arxiv_id":"2606.25526","last_updated":"2026-06-24T08:05:11Z","snapshot_observed_at":"2026-08-02T01:57:59.936036Z","submitted_at":"2026-06-24T08:05:11Z","title":"Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-25T21:17:28.832301Z"},"links":{"cited_paper":"/paper/2110.13799","citing_paper":"/paper/2606.25526"},"observation_digest":"sha256:b788e2e20fa91dff7e25f9849d8856d005d75fad4da16389d5303a85bfb11a62","observation_id":"fb52bd12-3557-4508-8120-10976269fba7","resolution":{"observed_at":"2026-07-04T19:30:07.607563Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.13799/citation-record","integrity":"/paper/2110.13799/integrity","json":"/paper/2110.13799/citation-record.json","paper":"/paper/2110.13799"},"outbound":[],"paper":{"arxiv_id":"2110.13799","last_updated":"2022-09-01T03:43:25Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T12:02:01.569473Z","submitted_at":"2021-10-26T15:56:57Z","title":"Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective"},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 3 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2110.13799."}