{"as_of":"2026-08-19T17:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f6b67b9784822d4a96f24d0d4fdec13858770444b2c8566ee1938ffb82b66b2a","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":"2026-08-19T06:32:44.657259+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":"2026-08-10T20:18:54.476829Z","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":"2026-05-22T17:35:00.853668Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1910.02140","last_updated":"2019-11-27T07:28:55Z","snapshot_observed_at":"2026-08-19T13:37:21.288323Z","submitted_at":"2019-10-04T20:52:39Z","title":"Discounted Reinforcement Learning Is Not an Optimization Problem","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.02140","snapshot_observed_at":"2026-08-10T20:13:57.580973Z","title":"Discounted reinforcement learning is not an optimization problem","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2501.09080","last_updated":"2025-08-05T14:35:10Z","snapshot_observed_at":"2026-08-13T04:32:34.139354Z","submitted_at":"2025-01-15T19:00:46Z","title":"Average-Reward Soft Actor-Critic","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T20:13:57.580973Z"},"links":{"cited_paper":"/paper/1910.02140","citing_paper":"/paper/2501.09080"},"observation_digest":"sha256:cb2fdfc95f809e9912ebdcda320a3d5594d4a0dbb75475925a0dfd336ab3343e","observation_id":"1b6fd44b-c44c-4368-894a-37436948a5c3","resolution":{"observed_at":"2026-08-10T20:13:57.580973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.02140","last_updated":"2019-11-27T07:28:55Z","snapshot_observed_at":"2026-08-19T13:37:21.288323Z","submitted_at":"2019-10-04T20:52:39Z","title":"Discounted Reinforcement Learning Is Not an Optimization Problem","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.02140","snapshot_observed_at":"2026-08-10T20:18:54.476829Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.09770","last_updated":"2025-01-15T19:00:45Z","snapshot_observed_at":"2026-08-15T04:08:52.360058Z","submitted_at":"2025-01-15T19:00:45Z","title":"EVAL: EigenVector-based Average-reward Learning","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T20:18:54.476829Z"},"links":{"cited_paper":"/paper/1910.02140","citing_paper":"/paper/2501.09770"},"observation_digest":"sha256:75e2eb63e34268679056ad51a47f0c47de6aa46d3bf96ee83e43c299537c2986","observation_id":"22b76259-2cec-4a0e-bbd6-fe5c3402b724","resolution":{"observed_at":"2026-08-10T20:18:54.476829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.02140","last_updated":"2019-11-27T07:28:55Z","snapshot_observed_at":"2026-08-19T13:37:21.288323Z","submitted_at":"2019-10-04T20:52:39Z","title":"Discounted Reinforcement Learning Is Not an Optimization Problem","version":3},"cited_work":{"arxiv_id":"1910.02140","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1910.02140","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Chen, Z","venue":null,"work_id":"5a201833-4c8e-446c-bdea-a2feee7b6d0b","year":2025},"citing_paper":{"arxiv_id":"2504.18743","last_updated":"2026-04-05T13:54:13Z","snapshot_observed_at":"2026-08-17T11:51:06.893835Z","submitted_at":"2025-04-25T23:41:14Z","title":"From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-22T17:34:49.191496Z"},"links":{"cited_paper":"/paper/1910.02140","citing_paper":"/paper/2504.18743"},"observation_digest":"sha256:08814ccd394427f2b025b232ebeda9b4c5cf24010da3fc81bfa841a90e3ee2d1","observation_id":"ef9f9df8-47c7-4518-9ebb-4a997b1ebe92","resolution":{"observed_at":"2026-05-22T17:35:00.856976Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.02140","last_updated":"2019-11-27T07:28:55Z","snapshot_observed_at":"2026-08-19T13:37:21.288323Z","submitted_at":"2019-10-04T20:52:39Z","title":"Discounted Reinforcement Learning Is Not an Optimization Problem","version":3},"cited_work":{"arxiv_id":"1910.02140","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1910.02140","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Chen, Z","venue":null,"work_id":"5a201833-4c8e-446c-bdea-a2feee7b6d0b","year":2025},"citing_paper":{"arxiv_id":"2605.22076","last_updated":"2026-05-21T07:15:43Z","snapshot_observed_at":"2026-08-18T01:35:54.766553Z","submitted_at":"2026-05-21T07:15:43Z","title":"Isomorphic Dynamic Programs","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-05-22T02:49:51.331717Z"},"links":{"cited_paper":"/paper/1910.02140","citing_paper":"/paper/2605.22076"},"observation_digest":"sha256:9dbc37dba693fe491ff5ecf017fb19a2e66e2c0edefec7a4257b0ac02cd919b2","observation_id":"9953429e-a13c-4914-903b-1ae69b8e7029","resolution":{"observed_at":"2026-05-22T02:50:58.395784Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1910.02140/citation-record","integrity":"/paper/1910.02140/integrity","json":"/paper/1910.02140/citation-record.json","paper":"/paper/1910.02140"},"outbound":[],"paper":{"arxiv_id":"1910.02140","last_updated":"2019-11-27T07:28:55Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-19T13:37:21.288323Z","submitted_at":"2019-10-04T20:52:39Z","title":"Discounted Reinforcement Learning Is Not an Optimization Problem"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1910.02140."}