{"as_of":"2026-08-07T07:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:19f46f64d863f93b3953ea025ca1f92e56ab7b040c8fc5b4bb5e86a253c561b9","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:21:58.724147Z","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":"2026-08-07T05:21:59.022598Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.19933","last_updated":"2025-02-27T07:28:35Z","snapshot_observed_at":"2026-07-06T19:39:59.961070Z","submitted_at":"2024-10-25T19:08:23Z","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","version":2},"cited_work":{"arxiv_id":"2410.19933","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.19933","snapshot_observed_at":"2026-08-07T05:21:59.022598Z","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","venue":"cs.LG","work_id":"3b0bc07a-a5eb-4206-b258-70a0a37531ab","year":2024},"citing_paper":{"arxiv_id":"2506.08266","last_updated":"2025-06-09T22:03:56Z","snapshot_observed_at":"2026-08-07T05:12:42.307191Z","submitted_at":"2025-06-09T22:03:56Z","title":"Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T05:21:58.724147Z"},"links":{"cited_paper":"/paper/2410.19933","citing_paper":"/paper/2506.08266"},"observation_digest":"sha256:365ee8cb842ec516a2b2db9eb60bca4216c74d33b42cbcac8e1ff712ba0c0311","observation_id":"08ef3aa0-5ad6-4b8b-a146-bd0f8c20961f","resolution":{"observed_at":"2026-08-07T05:21:59.026775Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19933","last_updated":"2025-02-27T07:28:35Z","snapshot_observed_at":"2026-07-06T19:39:59.961070Z","submitted_at":"2024-10-25T19:08:23Z","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19933","snapshot_observed_at":"2026-07-12T07:05:47.150308Z","title":"arXiv preprint arXiv:2410.19933 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.02781","last_updated":"2026-07-02T21:27:59Z","snapshot_observed_at":"2026-08-02T20:53:24.751933Z","submitted_at":"2026-07-02T21:27:59Z","title":"Safe Inference-Time Alignment via Lagrangian Reward Augmentation","version":1},"reference_index":106,"source":"arxiv_source","source_observed_at":"2026-07-12T07:05:47.150308Z"},"links":{"cited_paper":"/paper/2410.19933","citing_paper":"/paper/2607.02781"},"observation_digest":"sha256:6df33dccddacc1d899cd08c76991557fed45d3280f823bbfe0b552c31bba3abf","observation_id":"fbba9b50-535d-46a1-9911-52c57324de6d","resolution":{"observed_at":"2026-07-12T07:05:47.150308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19933","last_updated":"2025-02-27T07:28:35Z","snapshot_observed_at":"2026-07-06T19:39:59.961070Z","submitted_at":"2024-10-25T19:08:23Z","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19933","snapshot_observed_at":"2026-07-13T05:26:06.829382Z","title":"Enhancing safety in reinforcement learning with human feedback via rectified policy optimization.arXiv preprint arXiv:2410.19933, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.08968","last_updated":"2026-07-09T22:09:16Z","snapshot_observed_at":"2026-08-02T07:02:01.100420Z","submitted_at":"2026-07-09T22:09:16Z","title":"Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-13T05:26:06.829382Z"},"links":{"cited_paper":"/paper/2410.19933","citing_paper":"/paper/2607.08968"},"observation_digest":"sha256:324d4aae8b552237129ff8f5d738b2412c932c67dfc4f763e24e2ed5ad7c441f","observation_id":"2263d3e0-5401-4ce9-8ad9-97524ad245d4","resolution":{"observed_at":"2026-07-13T05:26:06.829382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.19933/citation-record","integrity":"/paper/2410.19933/integrity","json":"/paper/2410.19933/citation-record.json","paper":"/paper/2410.19933"},"outbound":[],"paper":{"arxiv_id":"2410.19933","last_updated":"2025-02-27T07:28:35Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:39:59.961070Z","submitted_at":"2024-10-25T19:08:23Z","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.19933."}