{"as_of":"2026-08-09T01:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ea1a40547ffbb0fb7f5a4714691669935619260021412e70f8cda8c043a60afd","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T11:32:29.571593Z","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":"2026-08-07T11:32:32.239050Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.08302","last_updated":"2025-09-11T10:17:06Z","snapshot_observed_at":"2026-08-05T19:19:51.785740Z","submitted_at":"2024-11-13T02:45:21Z","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","version":2},"cited_work":{"arxiv_id":"2411.08302","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.08302","snapshot_observed_at":"2026-08-07T11:32:32.239050Z","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","venue":"cs.CL","work_id":"b790476c-97f6-4051-8e20-05fa884acb61","year":2024},"citing_paper":{"arxiv_id":"2506.02553","last_updated":"2025-06-03T07:44:31Z","snapshot_observed_at":"2026-08-09T00:47:31.746531Z","submitted_at":"2025-06-03T07:44:31Z","title":"Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:32:29.571593Z"},"links":{"cited_paper":"/paper/2411.08302","citing_paper":"/paper/2506.02553"},"observation_digest":"sha256:38873ae1102af5000c53d4c18e4ec1382f06f484129224767c5558ca296c6fc7","observation_id":"d1e21099-45e5-456f-9a22-a89f33de763d","resolution":{"observed_at":"2026-08-07T11:32:32.289654Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.08302","last_updated":"2025-09-11T10:17:06Z","snapshot_observed_at":"2026-08-05T19:19:51.785740Z","submitted_at":"2024-11-13T02:45:21Z","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.08302","snapshot_observed_at":"2026-08-02T13:58:43.513582Z","title":"R3hf: Reward re- distribution for enhancing reinforcement learning from human feedback.arXiv preprint arXiv:2411.08302, 2024","venue":null,"work_id":null,"year":2024},"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":33,"source":"pdf_text","source_observed_at":"2026-08-02T13:58:43.513582Z"},"links":{"cited_paper":"/paper/2411.08302","citing_paper":"/paper/2607.18258"},"observation_digest":"sha256:a6086047759a7d6d4d0d471a6c00cc4f79cdafbf5f757877af982395c6536fbc","observation_id":"b6b31347-93a8-45a4-91e0-514061b8e5b6","resolution":{"observed_at":"2026-08-02T13:58:43.513582Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2411.08302/citation-record","integrity":"/paper/2411.08302/integrity","json":"/paper/2411.08302/citation-record.json","paper":"/paper/2411.08302"},"outbound":[],"paper":{"arxiv_id":"2411.08302","last_updated":"2025-09-11T10:17:06Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T19:19:51.785740Z","submitted_at":"2024-11-13T02:45:21Z","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution"},"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 2 inbound Pith citation observations for arXiv:2411.08302."}