{"as_of":"2026-08-13T23:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b987dfaec02e7830ca64d13d32e929e44939fc563318fe20833c1f6b5ccf164","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":"2026-08-13T06:32:02.005865+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":"2026-05-21T06:42:15.135148Z","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":"2026-05-21T06:44:00.911741Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.02244","last_updated":"2024-01-04T12:54:10Z","snapshot_observed_at":"2026-08-13T04:49:02.136744Z","submitted_at":"2024-01-04T12:54:10Z","title":"Policy-regularized Offline Multi-objective Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2401.02244","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.02244","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Policy-regularized offline multi-objective reinforcement learning","venue":null,"work_id":"26d11fc0-3ea3-4321-97d5-31dd9ed3fd3b","year":2024},"citing_paper":{"arxiv_id":"2605.20619","last_updated":"2026-05-20T02:09:32Z","snapshot_observed_at":"2026-08-12T16:38:42.494963Z","submitted_at":"2026-05-20T02:09:32Z","title":"SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-21T06:42:15.135148Z"},"links":{"cited_paper":"/paper/2401.02244","citing_paper":"/paper/2605.20619"},"observation_digest":"sha256:232e1172290e2dafd19ed9250f4673f88a0e39414cda26c3696c750a1a6e7009","observation_id":"d4954148-ce32-4968-b9ff-02a2a2773fea","resolution":{"observed_at":"2026-05-21T06:44:00.913186Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.02244/citation-record","integrity":"/paper/2401.02244/integrity","json":"/paper/2401.02244/citation-record.json","paper":"/paper/2401.02244"},"outbound":[],"paper":{"arxiv_id":"2401.02244","last_updated":"2024-01-04T12:54:10Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T04:49:02.136744Z","submitted_at":"2024-01-04T12:54:10Z","title":"Policy-regularized Offline Multi-objective Reinforcement Learning"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2401.02244."}