{"as_of":"2026-08-08T16:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2efe929350940aecd227c793e0b94d3b3e24b6941d3df94f2ac63aec67ba8ed2","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:19:09.300383Z","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":"2026-05-22T13:01:34.159151Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.06734","last_updated":"2026-06-29T20:55:26Z","snapshot_observed_at":"2026-07-06T17:28:14.770675Z","submitted_at":"2024-02-09T19:09:48Z","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06734","snapshot_observed_at":"2026-08-07T15:19:09.300383Z","title":"Corruption robust offline reinforce- ment learning with human feedback","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15694","last_updated":"2025-05-21T16:07:47Z","snapshot_observed_at":"2026-08-08T05:51:01.468645Z","submitted_at":"2025-05-21T16:07:47Z","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:19:09.300383Z"},"links":{"cited_paper":"/paper/2402.06734","citing_paper":"/paper/2505.15694"},"observation_digest":"sha256:32c8fb23ca79779deaa63b0f9e31e0eba37c7baf05e4e4ed9f3895e7f7b1a18b","observation_id":"f79755dd-1d76-499c-877f-e45cedcb5d0d","resolution":{"observed_at":"2026-08-07T15:19:09.300383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06734","last_updated":"2026-06-29T20:55:26Z","snapshot_observed_at":"2026-07-06T17:28:14.770675Z","submitted_at":"2024-02-09T19:09:48Z","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06734","snapshot_observed_at":"2026-08-07T13:44:58.018188Z","title":"Corruption robust offline reinforcement learning with human feedback","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21395","last_updated":"2025-05-27T16:23:24Z","snapshot_observed_at":"2026-08-07T13:26:21.678395Z","submitted_at":"2025-05-27T16:23:24Z","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T13:44:58.018188Z"},"links":{"cited_paper":"/paper/2402.06734","citing_paper":"/paper/2505.21395"},"observation_digest":"sha256:97db1cdd3d939784affae731f7cbf07f69fb107815de94948d93f3dee4bcb269","observation_id":"b7b5f535-eca7-4929-b022-dd2a8c11a880","resolution":{"observed_at":"2026-08-07T13:44:58.018188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06734","last_updated":"2026-06-29T20:55:26Z","snapshot_observed_at":"2026-07-06T17:28:14.770675Z","submitted_at":"2024-02-09T19:09:48Z","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","version":2},"cited_work":{"arxiv_id":"2402.06734","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.06734","snapshot_observed_at":"2026-07-01T01:17:08.556002Z","title":"Corruption robust offline reinforcement learning with human feedback","venue":null,"work_id":"c1d7a727-dc19-4c2e-aab8-ba176b2799ee","year":2024},"citing_paper":{"arxiv_id":"2509.08933","last_updated":"2026-05-21T17:37:36Z","snapshot_observed_at":"2026-07-06T22:28:28.274132Z","submitted_at":"2025-09-10T18:56:39Z","title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-22T12:58:26.626172Z"},"links":{"cited_paper":"/paper/2402.06734","citing_paper":"/paper/2509.08933"},"observation_digest":"sha256:608395a66a115584e2495bdff328b63ca9101a73a54b0d66fcb9d3a58f9a6553","observation_id":"76f56e68-29ad-4828-ab29-3288d02efbae","resolution":{"observed_at":"2026-07-01T01:17:08.556002Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06734","last_updated":"2026-06-29T20:55:26Z","snapshot_observed_at":"2026-07-06T17:28:14.770675Z","submitted_at":"2024-02-09T19:09:48Z","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback","version":2},"cited_work":{"arxiv_id":"2402.06734","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.06734","snapshot_observed_at":"2026-07-01T01:17:08.556002Z","title":"Corruption robust offline reinforcement learning with human feedback","venue":null,"work_id":"c1d7a727-dc19-4c2e-aab8-ba176b2799ee","year":2024},"citing_paper":{"arxiv_id":"2605.02495","last_updated":"2026-05-25T07:21:41Z","snapshot_observed_at":"2026-07-06T23:15:32.349713Z","submitted_at":"2026-05-04T11:45:38Z","title":"Efficient Preference Poisoning Attack on Offline RLHF","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-05-08T19:29:25.000361Z"},"links":{"cited_paper":"/paper/2402.06734","citing_paper":"/paper/2605.02495"},"observation_digest":"sha256:96dc03c78be9b1b2503c17df2b8f6176fbacfd3e802ad1f552a534544e1d57af","observation_id":"253c2365-ab32-4e32-b8b6-87cb0fb7feb2","resolution":{"observed_at":"2026-07-01T01:17:08.556002Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2402.06734/citation-record","integrity":"/paper/2402.06734/integrity","json":"/paper/2402.06734/citation-record.json","paper":"/paper/2402.06734"},"outbound":[],"paper":{"arxiv_id":"2402.06734","last_updated":"2026-06-29T20:55:26Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:28:14.770675Z","submitted_at":"2024-02-09T19:09:48Z","title":"Corruption Robust Offline Reinforcement Learning with Human Feedback"},"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 4 inbound Pith citation observations for arXiv:2402.06734."}