{"as_of":"2026-08-08T14:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:704acc01c375b1df378c465c1fb1e24cdce535a37a15329003b6b5a27ddd3077","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":"2026-08-07T12:12:58.048180Z","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":"2026-07-03T09:17:48.968462Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.04451","last_updated":"2024-07-05T12:05:37Z","snapshot_observed_at":"2026-07-06T18:41:57.207738Z","submitted_at":"2024-07-05T12:05:37Z","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04451","snapshot_observed_at":"2026-08-07T12:12:58.048180Z","title":"Hindsight preference learning for offline preference-based reinforcement learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00388","last_updated":"2025-06-10T13:10:39Z","snapshot_observed_at":"2026-08-07T15:00:04.313363Z","submitted_at":"2025-05-31T04:37:07Z","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T12:12:58.048180Z"},"links":{"cited_paper":"/paper/2407.04451","citing_paper":"/paper/2506.00388"},"observation_digest":"sha256:a127398540a708b058710db9eda98a105377ecbcd06153804dc28da8b174315e","observation_id":"1179e094-1d9b-4423-bdc4-75bde49d1d28","resolution":{"observed_at":"2026-08-07T12:12:58.048180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04451","last_updated":"2024-07-05T12:05:37Z","snapshot_observed_at":"2026-07-06T18:41:57.207738Z","submitted_at":"2024-07-05T12:05:37Z","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2407.04451","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.04451","snapshot_observed_at":"2026-07-03T09:17:48.968462Z","title":"arXiv preprint arXiv:2407.04451 , year =","venue":null,"work_id":"49b1e7a3-e682-44fe-bd10-5d2107c89686","year":null},"citing_paper":{"arxiv_id":"2606.11982","last_updated":"2026-06-10T12:00:17Z","snapshot_observed_at":"2026-07-06T23:50:58.297354Z","submitted_at":"2026-06-10T12:00:17Z","title":"PAWS: Preference Learning with Advantage-Weighted Segments","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-06-27T10:22:51.007376Z"},"links":{"cited_paper":"/paper/2407.04451","citing_paper":"/paper/2606.11982"},"observation_digest":"sha256:95a1853edfead2edb08d47fd349aae6e724ad235827cafe1d2cab8ad375f5117","observation_id":"6fc2c42e-d082-47cc-a619-c40609c58885","resolution":{"observed_at":"2026-07-03T09:17:48.969947Z","resolver_source":"arxiv_id","status":"verified_exact"},"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"}}],"links":{"evidence":"/evidence","html":"/paper/2407.04451/citation-record","integrity":"/paper/2407.04451/integrity","json":"/paper/2407.04451/citation-record.json","paper":"/paper/2407.04451"},"outbound":[],"paper":{"arxiv_id":"2407.04451","last_updated":"2024-07-05T12:05:37Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:41:57.207738Z","submitted_at":"2024-07-05T12:05:37Z","title":"Hindsight Preference Learning for Offline Preference-based 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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.04451."}