{"as_of":"2026-08-21T09:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2191f59a5548d08a7e77f670420e4bf0f1edece28c7a983b000d84a34e04e4fc","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T20:58:02.992888Z","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":"2026-07-04T08:49:42.750271Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.03442","last_updated":"2021-11-01T03:53:25Z","snapshot_observed_at":"2026-08-17T12:32:53.813629Z","submitted_at":"2021-06-07T09:19:42Z","title":"Average-Reward Reinforcement Learning with Trust Region Methods","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03442","snapshot_observed_at":"2026-08-10T20:58:02.992888Z","title":"Average-reward reinforcement learning with trust region methods,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06700","last_updated":"2025-01-12T03:45:14Z","snapshot_observed_at":"2026-08-16T18:57:05.934580Z","submitted_at":"2025-01-12T03:45:14Z","title":"Average Reward Reinforcement Learning for Wireless Radio Resource Management","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T20:58:02.992888Z"},"links":{"cited_paper":"/paper/2106.03442","citing_paper":"/paper/2501.06700"},"observation_digest":"sha256:fd38808ac273586f22a001cd52a5163870ce5dc37993003189addf800af86178","observation_id":"38faea7d-0567-4d26-9138-308f0ede6ca3","resolution":{"observed_at":"2026-08-10T20:58:02.992888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03442","last_updated":"2021-11-01T03:53:25Z","snapshot_observed_at":"2026-08-17T12:32:53.813629Z","submitted_at":"2021-06-07T09:19:42Z","title":"Average-Reward Reinforcement Learning with Trust Region Methods","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03442","snapshot_observed_at":"2026-08-10T20:56:51.082564Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06937","last_updated":"2025-01-12T21:24:27Z","snapshot_observed_at":"2026-08-19T12:44:49.581077Z","submitted_at":"2025-01-12T21:24:27Z","title":"An Empirical Study of Deep Reinforcement Learning in Continuing Tasks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T20:56:51.082564Z"},"links":{"cited_paper":"/paper/2106.03442","citing_paper":"/paper/2501.06937"},"observation_digest":"sha256:2c4e02eebc6deb585a73d51fd902ac7642fb66fb44ac862f0e6d5ffd5c9bed02","observation_id":"0bc6b9d6-5972-481e-acdd-4019b2ad8d9a","resolution":{"observed_at":"2026-08-10T20:56:51.082564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03442","last_updated":"2021-11-01T03:53:25Z","snapshot_observed_at":"2026-08-17T12:32:53.813629Z","submitted_at":"2021-06-07T09:19:42Z","title":"Average-Reward Reinforcement Learning with Trust Region Methods","version":2},"cited_work":{"arxiv_id":"2106.03442","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.03442","snapshot_observed_at":"2026-07-04T08:49:42.750271Z","title":"arXiv:2106.03442 [cs.LG] https://arxiv.org/abs/2106.03442","venue":null,"work_id":"2d1662a7-3cb5-4cb9-9b60-c8e75a8bde5c","year":null},"citing_paper":{"arxiv_id":"2605.04880","last_updated":"2026-05-06T13:16:42Z","snapshot_observed_at":"2026-08-11T06:48:28.195530Z","submitted_at":"2026-05-06T13:16:42Z","title":"A Harmonic Mean Formulation of Average Reward Reinforcement Learning in SMDPs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-08T16:55:51.365605Z"},"links":{"cited_paper":"/paper/2106.03442","citing_paper":"/paper/2605.04880"},"observation_digest":"sha256:c680fe4f6e0dad73794b1a90061791bf0c83be0593396dff205b149dd11b3f6d","observation_id":"d6ac368f-d7fd-4462-929c-a4574422354e","resolution":{"observed_at":"2026-05-11T17:56:06.647823Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03442","last_updated":"2021-11-01T03:53:25Z","snapshot_observed_at":"2026-08-17T12:32:53.813629Z","submitted_at":"2021-06-07T09:19:42Z","title":"Average-Reward Reinforcement Learning with Trust Region Methods","version":2},"cited_work":{"arxiv_id":"2106.03442","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.03442","snapshot_observed_at":"2026-07-04T08:49:42.750271Z","title":"arXiv:2106.03442 [cs.LG] https://arxiv.org/abs/2106.03442","venue":null,"work_id":"2d1662a7-3cb5-4cb9-9b60-c8e75a8bde5c","year":null},"citing_paper":{"arxiv_id":"2606.22579","last_updated":"2026-06-21T16:29:25Z","snapshot_observed_at":"2026-08-02T07:11:59.062207Z","submitted_at":"2026-06-21T16:29:25Z","title":"Stationary Robust Mean-Field Games under Model Mismatches","version":1},"reference_index":205,"source":"arxiv_source","source_observed_at":"2026-06-26T10:50:40.841967Z"},"links":{"cited_paper":"/paper/2106.03442","citing_paper":"/paper/2606.22579"},"observation_digest":"sha256:8fb00896917d041400b4b2fd50a43f4d908de844af0d507494fb4d47005a1851","observation_id":"6121a5e4-ecbb-43f3-bc81-6c0a7aa6cc13","resolution":{"observed_at":"2026-07-04T08:49:42.752068Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.03442/citation-record","integrity":"/paper/2106.03442/integrity","json":"/paper/2106.03442/citation-record.json","paper":"/paper/2106.03442"},"outbound":[],"paper":{"arxiv_id":"2106.03442","last_updated":"2021-11-01T03:53:25Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T12:32:53.813629Z","submitted_at":"2021-06-07T09:19:42Z","title":"Average-Reward Reinforcement Learning with Trust Region Methods"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2106.03442."}