{"as_of":"2026-08-04T18:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5bd9947f4b9e0a7ed1a866e038f035cdb6780944178c9c0982554c1a817ca4bb","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":"2026-08-04T06:34:03.388597+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":"2026-05-15T01:57:37.847553Z","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":"2026-05-15T01:58:29.015767Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.06874","last_updated":"2024-11-29T23:41:57Z","snapshot_observed_at":"2026-07-06T18:28:33.795339Z","submitted_at":"2024-06-11T01:20:53Z","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","version":3},"cited_work":{"arxiv_id":"2406.06874","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.06874","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.06874 , year=","venue":null,"work_id":"98309c9e-447c-46f0-bd10-5cb8475fa088","year":2024},"citing_paper":{"arxiv_id":"2605.08006","last_updated":"2026-05-08T16:59:29Z","snapshot_observed_at":"2026-07-06T23:20:19.821342Z","submitted_at":"2026-05-08T16:59:29Z","title":"Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-11T02:40:09.940793Z"},"links":{"cited_paper":"/paper/2406.06874","citing_paper":"/paper/2605.08006"},"observation_digest":"sha256:8efbcae4e19e62619301ed897e1111eea18e05ba57eccdbf48001b103037e1a9","observation_id":"432f54c0-3a6f-4f53-bd44-ce060d53b925","resolution":{"observed_at":"2026-05-11T02:40:56.193500Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06874","last_updated":"2024-11-29T23:41:57Z","snapshot_observed_at":"2026-07-06T18:28:33.795339Z","submitted_at":"2024-06-11T01:20:53Z","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","version":3},"cited_work":{"arxiv_id":"2406.06874","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.06874","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.06874 , year=","venue":null,"work_id":"98309c9e-447c-46f0-bd10-5cb8475fa088","year":2024},"citing_paper":{"arxiv_id":"2605.14409","last_updated":"2026-05-14T05:52:04Z","snapshot_observed_at":"2026-07-06T23:25:49.545418Z","submitted_at":"2026-05-14T05:52:04Z","title":"On the Nature of Regularity Assumptions in Bilevel Optimization with Constrained Lower-level Problem","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-15T01:57:37.847553Z"},"links":{"cited_paper":"/paper/2406.06874","citing_paper":"/paper/2605.14409"},"observation_digest":"sha256:039d64db860d7c55798c8aa63ef4fe8f2da55c1cc966f99d2f1f088c96b50890","observation_id":"79196a24-a92f-4d0e-9e12-04e5c4a047eb","resolution":{"observed_at":"2026-05-15T01:58:29.017626Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.06874/citation-record","integrity":"/paper/2406.06874/integrity","json":"/paper/2406.06874/citation-record.json","paper":"/paper/2406.06874"},"outbound":[],"paper":{"arxiv_id":"2406.06874","last_updated":"2024-11-29T23:41:57Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T18:28:33.795339Z","submitted_at":"2024-06-11T01:20:53Z","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.06874."}