{"as_of":"2026-08-19T21:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:21460862b7d7b56bf6325fc052e4fa4c7d0b540824f9ff014848025a4f945ef4","coverage":[{"denominator":4,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T06:28:01.767455Z","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":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":[],"links":{"evidence":"/evidence","html":"/paper/2601.22823/citation-record","integrity":"/paper/2601.22823/integrity","json":"/paper/2601.22823/citation-record.json","paper":"/paper/2601.22823"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T06:28:01.282100Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.22823","last_updated":"2026-06-28T20:39:55Z","snapshot_observed_at":"2026-08-13T06:18:06.099607Z","submitted_at":"2026-01-30T10:49:22Z","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-03T06:28:01.282100Z"},"links":{"citing_paper":"/paper/2601.22823"},"observation_digest":"sha256:b92ed09bb5385014ed475dfe41e23ecb081c19d20664fa5f880e67f5706d2173","observation_id":"239c8204-ed52-42f1-ab81-856ad4e8e32f","resolution":{"observed_at":"2026-08-03T06:28:01.282100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T06:28:01.441524Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.22823","last_updated":"2026-06-28T20:39:55Z","snapshot_observed_at":"2026-08-13T06:18:06.099607Z","submitted_at":"2026-01-30T10:49:22Z","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-03T06:28:01.441524Z"},"links":{"citing_paper":"/paper/2601.22823"},"observation_digest":"sha256:c501514715f6db8b6c3e9d22190e542008526a227a90fd94d58e8f3e0cdb71b2","observation_id":"839e90d2-cfda-4823-b129-32bac2686205","resolution":{"observed_at":"2026-08-03T06:28:01.441524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T06:28:01.589621Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.22823","last_updated":"2026-06-28T20:39:55Z","snapshot_observed_at":"2026-08-13T06:18:06.099607Z","submitted_at":"2026-01-30T10:49:22Z","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-03T06:28:01.589621Z"},"links":{"citing_paper":"/paper/2601.22823"},"observation_digest":"sha256:b7e0fdbec9a8a88bd8bf6f89974b2948b466efa264ba242a941f0687c6186012","observation_id":"97231f5c-9352-4909-b580-905d07dbb7a1","resolution":{"observed_at":"2026-08-03T06:28:01.589621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T06:28:01.767455Z","title":"the vector of an unsupervised learned trajectory encoder","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2601.22823","last_updated":"2026-06-28T20:39:55Z","snapshot_observed_at":"2026-08-13T06:18:06.099607Z","submitted_at":"2026-01-30T10:49:22Z","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-03T06:28:01.767455Z"},"links":{"citing_paper":"/paper/2601.22823"},"observation_digest":"sha256:ead94e0de6ace1f1d22b8a40b0b74aed6522a99f45d57e3b503fdd6d7ce14df3","observation_id":"3664f6e3-c1a3-49a5-8e6b-83c0ec46a218","resolution":{"observed_at":"2026-08-03T06:28:01.767455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.22823","last_updated":"2026-06-28T20:39:55Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T06:18:06.099607Z","submitted_at":"2026-01-30T10:49:22Z","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment"},"reference_resolution":{"displayed":4,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":4},"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 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2601.22823."}