{"as_of":"2026-08-09T15:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:03d15793f2b721c6c425393f06d651a3bce8fc452f4ffc70aebf1de93478bd9b","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":"2026-08-08T13:45:15.683374Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T16:29:06.947483Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.11364","last_updated":"2020-12-24T18:22:03Z","snapshot_observed_at":"2026-08-05T20:18:33.953605Z","submitted_at":"2020-10-22T01:02:55Z","title":"Sample Efficient Reinforcement Learning with REINFORCE","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11364","snapshot_observed_at":"2026-08-08T13:45:15.683374Z","title":"Sample efficient reinforcement learning with reinforce","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.07141","last_updated":"2025-02-11T00:12:04Z","snapshot_observed_at":"2026-08-08T13:38:36.265872Z","submitted_at":"2025-02-11T00:12:04Z","title":"Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T13:45:15.683374Z"},"links":{"cited_paper":"/paper/2010.11364","citing_paper":"/paper/2502.07141"},"observation_digest":"sha256:d0ce8aafde1d282059b7612e50dde2b56d058e3a74a98949630b3973b8ad89af","observation_id":"2e928c6a-be97-47d0-84aa-78389f100064","resolution":{"observed_at":"2026-08-08T13:45:15.683374Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11364","last_updated":"2020-12-24T18:22:03Z","snapshot_observed_at":"2026-08-05T20:18:33.953605Z","submitted_at":"2020-10-22T01:02:55Z","title":"Sample Efficient Reinforcement Learning with REINFORCE","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11364","snapshot_observed_at":"2026-08-07T15:20:10.646973Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15514","last_updated":"2025-05-21T13:38:45Z","snapshot_observed_at":"2026-08-07T15:13:59.589795Z","submitted_at":"2025-05-21T13:38:45Z","title":"AM-PPO: (Advantage) Alpha-Modulation with Proximal Policy Optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:20:10.646973Z"},"links":{"cited_paper":"/paper/2010.11364","citing_paper":"/paper/2505.15514"},"observation_digest":"sha256:2cda56d01a24ffa083eda14a44d6a9a768cae582337df983b8c23e63c685f750","observation_id":"3649ef8e-7d34-47fa-97f8-e11134e226e0","resolution":{"observed_at":"2026-08-07T15:20:10.646973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11364","last_updated":"2020-12-24T18:22:03Z","snapshot_observed_at":"2026-08-05T20:18:33.953605Z","submitted_at":"2020-10-22T01:02:55Z","title":"Sample Efficient Reinforcement Learning with REINFORCE","version":2},"cited_work":{"arxiv_id":"2010.11364","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.11364","snapshot_observed_at":"2026-08-06T16:29:06.947483Z","title":"Sample Efficient Reinforcement Learning with REINFORCE","venue":"cs.LG","work_id":"204855c2-3897-4226-b873-163a77915c66","year":2020},"citing_paper":{"arxiv_id":"2507.13491","last_updated":"2025-07-17T18:59:54Z","snapshot_observed_at":"2026-08-09T13:11:06.973683Z","submitted_at":"2025-07-17T18:59:54Z","title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","version":1},"reference_index":196,"source":"pdf_text","source_observed_at":"2026-08-06T16:29:06.690547Z"},"links":{"cited_paper":"/paper/2010.11364","citing_paper":"/paper/2507.13491"},"observation_digest":"sha256:002ed64cb24e3f287eeef41f1245b3eb63d2da12781ce6c8977c1cbc3c3bedb7","observation_id":"ff40f90d-3b2b-4515-8e28-adeb753550ff","resolution":{"observed_at":"2026-08-06T16:29:07.046798Z","resolver_source":"local_arxiv","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/2010.11364/citation-record","integrity":"/paper/2010.11364/integrity","json":"/paper/2010.11364/citation-record.json","paper":"/paper/2010.11364"},"outbound":[],"paper":{"arxiv_id":"2010.11364","last_updated":"2020-12-24T18:22:03Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T20:18:33.953605Z","submitted_at":"2020-10-22T01:02:55Z","title":"Sample Efficient Reinforcement Learning with REINFORCE"},"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:2010.11364."}