{"as_of":"2026-08-09T00:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cfd782eee4af0ebde9c9ba87cdab420a7a76109d6c50f3738b5a191b530e79a0","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T18:51:28.518998Z","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":"2026-07-01T21:06:13.284428Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.05171","last_updated":"2024-07-09T13:17:36Z","snapshot_observed_at":"2026-08-03T16:32:31.666416Z","submitted_at":"2024-03-08T09:20:12Z","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05171","snapshot_observed_at":"2026-08-06T18:51:28.518998Z","title":"Overcom- ing reward overoptimization via adversarial policy optimization with lightweight uncertainty estimation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07375","last_updated":"2025-07-10T01:56:56Z","snapshot_observed_at":"2026-08-08T11:06:36.428118Z","submitted_at":"2025-07-10T01:56:56Z","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:51:28.518998Z"},"links":{"cited_paper":"/paper/2403.05171","citing_paper":"/paper/2507.07375"},"observation_digest":"sha256:0408ae9be069e229445019350551b4c8848c4cf4e2e2aa3513985a46278af6b0","observation_id":"0c6ff2cd-dc93-4461-8ad5-5cef5b5228ba","resolution":{"observed_at":"2026-08-06T18:51:28.518998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05171","last_updated":"2024-07-09T13:17:36Z","snapshot_observed_at":"2026-08-03T16:32:31.666416Z","submitted_at":"2024-03-08T09:20:12Z","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05171","snapshot_observed_at":"2026-08-06T16:34:25.291921Z","title":"Xiaoying Zhang, Jean-Francois Ton, Wei Shen, Hongning Wang, and Yang Liu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13158","last_updated":"2025-07-17T14:22:24Z","snapshot_observed_at":"2026-08-07T07:16:46.127762Z","submitted_at":"2025-07-17T14:22:24Z","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","version":1},"reference_index":114,"source":"pdf_text","source_observed_at":"2026-08-06T16:34:25.291921Z"},"links":{"cited_paper":"/paper/2403.05171","citing_paper":"/paper/2507.13158"},"observation_digest":"sha256:512647a29ea6363a41ee0e258c758ffe9c15640438401de9c4b64572e2f57593","observation_id":"d3396fdf-285c-4f06-9ab9-8ce1b7348ab2","resolution":{"observed_at":"2026-08-06T16:34:25.291921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05171","last_updated":"2024-07-09T13:17:36Z","snapshot_observed_at":"2026-08-03T16:32:31.666416Z","submitted_at":"2024-03-08T09:20:12Z","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","version":2},"cited_work":{"arxiv_id":"2403.05171","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.05171","snapshot_observed_at":"2026-07-01T21:06:13.284428Z","title":"ArXiv Preprint: 2403.05171 , Year =","venue":null,"work_id":"65fb2d7e-8400-4d9e-915e-1fd5a7437a8a","year":null},"citing_paper":{"arxiv_id":"2606.01382","last_updated":"2026-05-31T18:11:26Z","snapshot_observed_at":"2026-08-06T07:55:08.019280Z","submitted_at":"2026-05-31T18:11:26Z","title":"Efficient Exploration for Iterative Nash Preference Optimization","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-06-28T17:33:36.210383Z"},"links":{"cited_paper":"/paper/2403.05171","citing_paper":"/paper/2606.01382"},"observation_digest":"sha256:15a2580e04f905d64ae571ebcec995d573917ed39732d91fe7ff12fb6a7c68de","observation_id":"b7a53fee-808b-4f5c-ac37-e2dea604045c","resolution":{"observed_at":"2026-07-01T21:06:13.286270Z","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/2403.05171/citation-record","integrity":"/paper/2403.05171/integrity","json":"/paper/2403.05171/citation-record.json","paper":"/paper/2403.05171"},"outbound":[],"paper":{"arxiv_id":"2403.05171","last_updated":"2024-07-09T13:17:36Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T16:32:31.666416Z","submitted_at":"2024-03-08T09:20:12Z","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2403.05171."}