{"as_of":"2026-08-17T20:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8dfae9c55638ef8d8a232d212e07cb783a8156c9a9f977899cfcbe8f9e846fb9","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":"2026-08-17T06:30:58.91139+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":"2026-08-06T16:44:48.223183Z","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":"2026-05-13T07:59:55.881558Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.08199","last_updated":"2023-08-01T12:02:58Z","snapshot_observed_at":"2026-08-16T18:16:59.351231Z","submitted_at":"2021-06-15T14:59:14Z","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","version":2},"cited_work":{"arxiv_id":"2106.08199","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.08199","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Abdolmaleki, S","venue":null,"work_id":"5c221c2f-3097-4840-b11a-99d337009c0e","year":null},"citing_paper":{"arxiv_id":"2308.08998","last_updated":"2023-08-21T10:23:42Z","snapshot_observed_at":"2026-08-13T14:38:32.919809Z","submitted_at":"2023-08-17T14:12:48Z","title":"Reinforced Self-Training (ReST) for Language Modeling","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-13T07:59:55.849296Z"},"links":{"cited_paper":"/paper/2106.08199","citing_paper":"/paper/2308.08998"},"observation_digest":"sha256:2011acfad81936ffe3e733984d44fb341917b9fa1d0fcc6fdcd32be9a43d2a85","observation_id":"ce78034a-9e93-45c2-91e8-fc6a4d23db04","resolution":{"observed_at":"2026-05-13T07:59:55.885760Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08199","last_updated":"2023-08-01T12:02:58Z","snapshot_observed_at":"2026-08-16T18:16:59.351231Z","submitted_at":"2021-06-15T14:59:14Z","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08199","snapshot_observed_at":"2026-08-06T16:44:48.223183Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.12856","last_updated":"2025-09-06T23:54:03Z","snapshot_observed_at":"2026-08-15T17:21:36.441374Z","submitted_at":"2025-07-17T07:26:54Z","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T16:44:48.223183Z"},"links":{"cited_paper":"/paper/2106.08199","citing_paper":"/paper/2507.12856"},"observation_digest":"sha256:450813219c1331a5488f0dd684ab7844395c569cf6ab985928e902892244025a","observation_id":"45f416fc-0333-48e9-97be-f7b45475e876","resolution":{"observed_at":"2026-08-06T16:44:48.223183Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08199","last_updated":"2023-08-01T12:02:58Z","snapshot_observed_at":"2026-08-16T18:16:59.351231Z","submitted_at":"2021-06-15T14:59:14Z","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08199","snapshot_observed_at":"2026-08-05T11:44:01.546632Z","title":"On Multi-objective Policy Opti mization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.02395","last_updated":"2025-09-02T15:02:44Z","snapshot_observed_at":"2026-08-11T15:34:39.925754Z","submitted_at":"2025-09-02T15:02:44Z","title":"Next-Generation Sustainable Wireless Systems: Energy Efficiency Meets Environmental Impact","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T11:44:01.546632Z"},"links":{"cited_paper":"/paper/2106.08199","citing_paper":"/paper/2509.02395"},"observation_digest":"sha256:1f9265fcaf1aa5be56bf21f9ebc4e39c09ebdf5cd4a4c1fcf890840ae62f06d4","observation_id":"c342de01-9414-467b-87f3-1897be13fe44","resolution":{"observed_at":"2026-08-05T11:44:01.546632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2106.08199/citation-record","integrity":"/paper/2106.08199/integrity","json":"/paper/2106.08199/citation-record.json","paper":"/paper/2106.08199"},"outbound":[],"paper":{"arxiv_id":"2106.08199","last_updated":"2023-08-01T12:02:58Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T18:16:59.351231Z","submitted_at":"2021-06-15T14:59:14Z","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2106.08199."}