{"as_of":"2026-08-15T05:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a50c42b7be6498915331d9b14bc09db07ab37c13d78d4137ddf0c06e4a0894c9","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":"2026-08-14T06:32:32.682623+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":"2026-08-08T21:27:27.637124Z","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":"2026-08-06T16:17:35.951074Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.02160","last_updated":"2024-01-04T09:17:53Z","snapshot_observed_at":"2026-08-14T10:24:03.705802Z","submitted_at":"2024-01-04T09:17:53Z","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02160","snapshot_observed_at":"2026-08-08T21:27:27.637124Z","title":"and Guo, H","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04809","last_updated":"2025-06-02T14:32:56Z","snapshot_observed_at":"2026-08-12T17:18:07.831913Z","submitted_at":"2025-02-07T10:28:39Z","title":"Humans Coexist, So Must Embodied Artificial Agents","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-08T21:27:27.637124Z"},"links":{"cited_paper":"/paper/2401.02160","citing_paper":"/paper/2502.04809"},"observation_digest":"sha256:b842d687059dcaa1837bfa7a0bce26e902208cff9c9d01736d530344ffb1d5c1","observation_id":"bcfdfcf6-d5da-493f-aa8c-a5fe1d2603c2","resolution":{"observed_at":"2026-08-08T21:27:27.637124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02160","last_updated":"2024-01-04T09:17:53Z","snapshot_observed_at":"2026-08-14T10:24:03.705802Z","submitted_at":"2024-01-04T09:17:53Z","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2401.02160","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.02160","snapshot_observed_at":"2026-08-06T16:17:35.951074Z","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","venue":"cs.NE","work_id":"16c37952-162f-45bf-8d03-5d8a518cf7b4","year":2024},"citing_paper":{"arxiv_id":"2507.14066","last_updated":"2025-07-18T16:43:04Z","snapshot_observed_at":"2026-08-06T15:59:43.105055Z","submitted_at":"2025-07-18T16:43:04Z","title":"Preference-based Multi-Objective Reinforcement Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T16:17:35.855636Z"},"links":{"cited_paper":"/paper/2401.02160","citing_paper":"/paper/2507.14066"},"observation_digest":"sha256:91fd8c3656b819b103b60f952094e932e46c58e37de9ac021305afbcc1bdf23b","observation_id":"420d363e-a9f4-47b2-bd3e-6ef4f759e91c","resolution":{"observed_at":"2026-08-06T16:17:35.956243Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.02160/citation-record","integrity":"/paper/2401.02160/integrity","json":"/paper/2401.02160/citation-record.json","paper":"/paper/2401.02160"},"outbound":[],"paper":{"arxiv_id":"2401.02160","last_updated":"2024-01-04T09:17:53Z","latest_version":1,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-14T10:24:03.705802Z","submitted_at":"2024-01-04T09:17:53Z","title":"Human-in-the-Loop Policy Optimization for Preference-Based 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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2401.02160."}