{"as_of":"2026-08-09T02:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b5780f7d17784b5da8d5aaa027ac25c301af229f3a704cdff78097d063d51e3b","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":"2026-08-08T06:32:00.761636+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":"2026-08-02T13:58:44.322878Z","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":"2307.11897","last_updated":"2023-08-18T18:35:02Z","snapshot_observed_at":"2026-08-08T18:32:02.272908Z","submitted_at":"2023-07-21T20:54:52Z","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.11897","snapshot_observed_at":"2026-08-02T13:58:44.322878Z","title":"Hindsight-dice: Stable credit assignment for deep reinforcement learning.arXiv preprint arXiv:2307.11897, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18258","last_updated":"2026-05-15T09:09:57Z","snapshot_observed_at":"2026-08-07T01:09:03.575259Z","submitted_at":"2026-05-15T09:09:57Z","title":"S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T13:58:44.322878Z"},"links":{"cited_paper":"/paper/2307.11897","citing_paper":"/paper/2607.18258"},"observation_digest":"sha256:d0db6a98998f1db7e13ad7e71b53a52af6a9490753d9e6a66382089ef1c14522","observation_id":"c329ffb8-72cb-4586-a3e9-6ff234c50431","resolution":{"observed_at":"2026-08-02T13:58:44.322878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2307.11897/citation-record","integrity":"/paper/2307.11897/integrity","json":"/paper/2307.11897/citation-record.json","paper":"/paper/2307.11897"},"outbound":[],"paper":{"arxiv_id":"2307.11897","last_updated":"2023-08-18T18:35:02Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T18:32:02.272908Z","submitted_at":"2023-07-21T20:54:52Z","title":"Hindsight-DICE: Stable Credit Assignment for Deep 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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2307.11897."}