{"as_of":"2026-08-23T08:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:83beb1ff76f7aad0000376054bc43a8ca9215cbe7575d86ada0a23faa8537f3f","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":"2026-08-23T06:30:58.430688+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":"2026-08-16T11:13:53.668079Z","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":"2026-08-07T22:50:34.719612Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.06886","last_updated":"2024-06-01T02:41:07Z","snapshot_observed_at":"2026-08-16T14:19:42.615195Z","submitted_at":"2024-02-10T04:54:15Z","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06886","snapshot_observed_at":"2026-08-11T19:10:52.564782Z","title":"Principled penalty-based methods for bilevel reinforcement learning and rlhf","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07138","last_updated":"2024-12-10T02:57:35Z","snapshot_observed_at":"2026-08-19T08:26:08.904117Z","submitted_at":"2024-12-10T02:57:35Z","title":"Unlocking TriLevel Learning with Level-Wise Zeroth Order Constraints: Distributed Algorithms and Provable Non-Asymptotic Convergence","version":1},"reference_index":114,"source":"pdf_text","source_observed_at":"2026-08-11T19:10:52.564782Z"},"links":{"cited_paper":"/paper/2402.06886","citing_paper":"/paper/2412.07138"},"observation_digest":"sha256:7ec0ae136ce42b2987590957dc497a7fbe85385cdcf8e90e8720fc085fd6051d","observation_id":"3376c172-6c35-4ba7-a8b8-fc4ce14d89f9","resolution":{"observed_at":"2026-08-11T19:10:52.564782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06886","last_updated":"2024-06-01T02:41:07Z","snapshot_observed_at":"2026-08-16T14:19:42.615195Z","submitted_at":"2024-02-10T04:54:15Z","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","version":3},"cited_work":{"arxiv_id":"2402.06886","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.06886","snapshot_observed_at":"2026-08-07T22:50:34.719612Z","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","venue":"cs.LG","work_id":"833e3760-36e1-4c3c-a787-784c7542bda1","year":2024},"citing_paper":{"arxiv_id":"2502.09053","last_updated":"2025-08-05T02:23:31Z","snapshot_observed_at":"2026-08-15T19:20:27.516820Z","submitted_at":"2025-02-13T08:08:27Z","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","version":2},"reference_index":178,"source":"pdf_text","source_observed_at":"2026-08-07T22:50:33.299199Z"},"links":{"cited_paper":"/paper/2402.06886","citing_paper":"/paper/2502.09053"},"observation_digest":"sha256:cf8484a3c1812cc5fd2a7120d74978ef6daadc1a988443e29aca1bb2a5ad30b5","observation_id":"e128d9c3-b751-4468-8d5a-812b368640e4","resolution":{"observed_at":"2026-08-07T22:50:34.722851Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06886","last_updated":"2024-06-01T02:41:07Z","snapshot_observed_at":"2026-08-16T14:19:42.615195Z","submitted_at":"2024-02-10T04:54:15Z","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06886","snapshot_observed_at":"2026-08-16T11:13:53.668079Z","title":"Principled penalty-based methods for bilevel reinforcement learning and rlhf, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.16272","last_updated":"2025-04-22T21:09:33Z","snapshot_observed_at":"2026-08-18T06:47:57.031246Z","submitted_at":"2025-04-22T21:09:33Z","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T11:13:53.668079Z"},"links":{"cited_paper":"/paper/2402.06886","citing_paper":"/paper/2504.16272"},"observation_digest":"sha256:bc0805a77cef1249f6329be67bb3d9c7bc7bc25ea3b3f92c2b94bb57b1581a57","observation_id":"893e5ac8-0439-4968-98f4-9431b38b94b5","resolution":{"observed_at":"2026-08-16T11:13:53.668079Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06886","last_updated":"2024-06-01T02:41:07Z","snapshot_observed_at":"2026-08-16T14:19:42.615195Z","submitted_at":"2024-02-10T04:54:15Z","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06886","snapshot_observed_at":"2026-08-04T16:23:21.764973Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.15543","last_updated":"2026-05-25T16:32:52Z","snapshot_observed_at":"2026-08-15T13:49:23.485775Z","submitted_at":"2025-09-19T02:51:19Z","title":"Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T16:23:21.764973Z"},"links":{"cited_paper":"/paper/2402.06886","citing_paper":"/paper/2509.15543"},"observation_digest":"sha256:dfcf6463952064a1d2cadd723a6a208d785ed06d7e8fba074f3143732a095a74","observation_id":"8c3a598a-c9c9-4410-97d1-b629bb03001e","resolution":{"observed_at":"2026-08-04T16:23:21.764973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.06886/citation-record","integrity":"/paper/2402.06886/integrity","json":"/paper/2402.06886/citation-record.json","paper":"/paper/2402.06886"},"outbound":[],"paper":{"arxiv_id":"2402.06886","last_updated":"2024-06-01T02:41:07Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:19:42.615195Z","submitted_at":"2024-02-10T04:54:15Z","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.06886."}