{"as_of":"2026-08-05T14:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2599bf78246d09df232b5e0f6bc3a8c74752fe77e1d82e3c5db18bb9a39f838","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T16:43:54.214636Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2107.08285","last_updated":"2022-04-18T22:03:40Z","snapshot_observed_at":"2026-08-04T10:23:26.860467Z","submitted_at":"2021-07-17T17:09:18Z","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.08285","snapshot_observed_at":"2026-08-03T16:43:54.214636Z","title":"Chen, C., Liu, Z., Du, C., Pang, T., Liu, Q., Sinha, A., Varakantham, P., and Lin, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.12576","last_updated":"2026-05-23T02:48:11Z","snapshot_observed_at":"2026-08-03T16:43:53.189781Z","submitted_at":"2025-12-14T07:03:51Z","title":"Coupled Variational Reinforcement Learning for Language Model General Reasoning","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-03T16:43:54.214636Z"},"links":{"cited_paper":"/paper/2107.08285","citing_paper":"/paper/2512.12576"},"observation_digest":"sha256:4411c79e56a729e0dd92d5ba781acf8205e3c64e9627a80db995fd059f8f3bc6","observation_id":"7cb0e51f-c2a5-4a38-9c2a-988bb9120003","resolution":{"observed_at":"2026-08-03T16:43:54.214636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2107.08285/citation-record","integrity":"/paper/2107.08285/integrity","json":"/paper/2107.08285/citation-record.json","paper":"/paper/2107.08285"},"outbound":[],"paper":{"arxiv_id":"2107.08285","last_updated":"2022-04-18T22:03:40Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T10:23:26.860467Z","submitted_at":"2021-07-17T17:09:18Z","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2107.08285."}