{"as_of":"2026-08-09T09:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b87b7f687b735aa9640d61635197b36df041d9b83aa4c3b663c722f283148d3d","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":"2026-08-08T22:48:32.829460Z","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":"2026-05-10T23:30:49.569007Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1710.06100","last_updated":"2017-10-17T05:03:19Z","snapshot_observed_at":"2026-08-07T11:28:35.203683Z","submitted_at":"2017-10-17T05:03:19Z","title":"Primal-Dual $\\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06100","snapshot_observed_at":"2026-08-08T22:48:32.829460Z","title":"Primal-dual learning: Sample complexity and sublinear run time for ergodic M arkov decision problems","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.04477","last_updated":"2025-06-13T13:25:59Z","snapshot_observed_at":"2026-08-09T02:39:25.758694Z","submitted_at":"2025-02-06T20:01:59Z","title":"Near-Optimal Sample Complexity for MDPs via Anchoring","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-08T22:48:32.829460Z"},"links":{"cited_paper":"/paper/1710.06100","citing_paper":"/paper/2502.04477"},"observation_digest":"sha256:a048d834046a9a3144b59e10df018fcee3a2650b80115288cd049fcb59c4b0f1","observation_id":"c5337e60-d0f6-445d-9e53-ee7c5761380f","resolution":{"observed_at":"2026-08-08T22:48:32.829460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06100","last_updated":"2017-10-17T05:03:19Z","snapshot_observed_at":"2026-08-07T11:28:35.203683Z","submitted_at":"2017-10-17T05:03:19Z","title":"Primal-Dual $\\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06100","snapshot_observed_at":"2026-08-06T22:16:41.136263Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22401","last_updated":"2025-06-27T17:18:43Z","snapshot_observed_at":"2026-08-08T12:23:49.475923Z","submitted_at":"2025-06-27T17:18:43Z","title":"Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:16:41.136263Z"},"links":{"cited_paper":"/paper/1710.06100","citing_paper":"/paper/2506.22401"},"observation_digest":"sha256:77f81184d27f9880dc0d44bd5dc224c1774fab9c8a74d613eac8d11e24a328ec","observation_id":"6e8bf332-c7ab-4cc7-80f6-30b07b7d1439","resolution":{"observed_at":"2026-08-06T22:16:41.136263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06100","last_updated":"2017-10-17T05:03:19Z","snapshot_observed_at":"2026-08-07T11:28:35.203683Z","submitted_at":"2017-10-17T05:03:19Z","title":"Primal-Dual $\\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems","version":1},"cited_work":{"arxiv_id":"1710.06100","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1710.06100","snapshot_observed_at":"2026-07-04T22:16:54.694076Z","title":"Primal-dualπlearning: Sample complexity and sublinear run time for ergodic markov decision problems","venue":null,"work_id":"86d2fe5e-acb7-465c-98f7-0d76166b5109","year":2017},"citing_paper":{"arxiv_id":"2604.06039","last_updated":"2026-04-07T16:34:16Z","snapshot_observed_at":"2026-07-06T22:54:34.877944Z","submitted_at":"2026-04-07T16:34:16Z","title":"Value Mirror Descent for Reinforcement Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T19:07:41.863349Z"},"links":{"cited_paper":"/paper/1710.06100","citing_paper":"/paper/2604.06039"},"observation_digest":"sha256:99e91e8d5da91265446c97bd09c06bd1b3666c51cb9cb5961262537136707fd3","observation_id":"4f84cbce-69ac-48af-97a3-efc9fb8fc1e6","resolution":{"observed_at":"2026-07-04T22:16:54.694076Z","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":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1710.06100/citation-record","integrity":"/paper/1710.06100/integrity","json":"/paper/1710.06100/citation-record.json","paper":"/paper/1710.06100"},"outbound":[],"paper":{"arxiv_id":"1710.06100","last_updated":"2017-10-17T05:03:19Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T11:28:35.203683Z","submitted_at":"2017-10-17T05:03:19Z","title":"Primal-Dual $\\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems"},"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:1710.06100."}