{"as_of":"2026-08-19T21:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:db86c22099e66ab3a8028119fe39d015b92f5435c04f8cadb74442c35addc775","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":"2026-08-19T06:32:44.657259+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":"2026-08-15T19:08:14.376134Z","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":"2026-08-12T18:14:34.240235Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.06234","last_updated":"2021-02-11T19:35:33Z","snapshot_observed_at":"2026-08-19T14:36:08.853872Z","submitted_at":"2021-02-11T19:35:33Z","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","version":1},"cited_work":{"arxiv_id":"2102.06234","doi":null,"metadata_source":"pith","pith_arxiv_id":"2102.06234","snapshot_observed_at":"2026-08-12T18:14:34.240235Z","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","venue":"cs.LG","work_id":"264fe695-42bb-4c2f-b9d8-8ea798aa52ba","year":2021},"citing_paper":{"arxiv_id":"2411.12042","last_updated":"2025-05-30T01:46:35Z","snapshot_observed_at":"2026-08-19T17:48:04.568289Z","submitted_at":"2024-11-18T20:27:13Z","title":"Fast Convergence of Softmax Policy Mirror Ascent","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T18:14:33.882424Z"},"links":{"cited_paper":"/paper/2102.06234","citing_paper":"/paper/2411.12042"},"observation_digest":"sha256:75ef41afdb71d6ccf81227a61be2dd50ec99ee3039683b699c5a5c745cd62443","observation_id":"7f8938ac-71b1-42de-abd2-3a705b91283a","resolution":{"observed_at":"2026-08-12T18:14:34.247286Z","resolver_source":"local_arxiv","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":"2102.06234","last_updated":"2021-02-11T19:35:33Z","snapshot_observed_at":"2026-08-19T14:36:08.853872Z","submitted_at":"2021-02-11T19:35:33Z","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.06234","snapshot_observed_at":"2026-08-15T19:08:14.376134Z","title":"Optimization issues in kl-constrained approximate policy iteration.arXiv preprint arXiv:2102.06234, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.17828","last_updated":"2025-07-03T05:12:51Z","snapshot_observed_at":"2026-08-18T11:12:16.166349Z","submitted_at":"2025-06-21T21:49:02Z","title":"Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T19:08:14.376134Z"},"links":{"cited_paper":"/paper/2102.06234","citing_paper":"/paper/2506.17828"},"observation_digest":"sha256:42eebee18d99738a6c8dd987de7a7bd3cbc630dd5bd90011b3776db27dc37024","observation_id":"a8c9afe5-3b56-498f-9129-1c8a0280e79a","resolution":{"observed_at":"2026-08-15T19:08:14.376134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2102.06234/citation-record","integrity":"/paper/2102.06234/integrity","json":"/paper/2102.06234/citation-record.json","paper":"/paper/2102.06234"},"outbound":[],"paper":{"arxiv_id":"2102.06234","last_updated":"2021-02-11T19:35:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T14:36:08.853872Z","submitted_at":"2021-02-11T19:35:33Z","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration"},"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 2 inbound Pith citation observations for arXiv:2102.06234."}