{"as_of":"2026-08-08T23:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f84c0266b14ab579229e995f296bfd358935490ab67a453c718158af31dd9d2c","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":"2026-08-07T10:31:58.359316Z","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":"2026-05-11T04:30:57.163655Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.01013","last_updated":"2024-06-18T20:53:08Z","snapshot_observed_at":"2026-07-06T18:24:13.721696Z","submitted_at":"2024-06-03T05:46:53Z","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01013","snapshot_observed_at":"2026-08-07T10:31:58.359316Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05070","last_updated":"2025-08-05T04:45:24Z","snapshot_observed_at":"2026-08-08T08:47:53.025574Z","submitted_at":"2025-06-05T14:18:21Z","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T10:31:58.359316Z"},"links":{"cited_paper":"/paper/2406.01013","citing_paper":"/paper/2506.05070"},"observation_digest":"sha256:af61a7f5216cfafdd95c3104720d244a2d9f493378264badd7342f0a43105b32","observation_id":"814d1cc0-7757-44a5-8247-f66e06bdb408","resolution":{"observed_at":"2026-08-07T10:31:58.359316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01013","last_updated":"2024-06-18T20:53:08Z","snapshot_observed_at":"2026-07-06T18:24:13.721696Z","submitted_at":"2024-06-03T05:46:53Z","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01013","snapshot_observed_at":"2026-08-06T16:34:24.932860Z","title":"Scalable ensembling for mitigating reward overoptimisation.arXiv preprint arXiv:2406.01013,","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":2023,"source":"pdf_text","source_observed_at":"2026-08-06T16:34:24.932860Z"},"links":{"cited_paper":"/paper/2406.01013","citing_paper":"/paper/2507.13158"},"observation_digest":"sha256:ced24e8dfcf2a93e4604ccdb5039dce705e26f3e392b5d89018d3e3bb078ef85","observation_id":"171b2e5f-38fb-4164-ae47-cb09d54e0173","resolution":{"observed_at":"2026-08-06T16:34:24.932860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01013","last_updated":"2024-06-18T20:53:08Z","snapshot_observed_at":"2026-07-06T18:24:13.721696Z","submitted_at":"2024-06-03T05:46:53Z","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","version":2},"cited_work":{"arxiv_id":"2406.01013","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.01013","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ahmed, Rafael Rafailov, Stepan Sharkov, Xuechen Li, and Sanmi Koyejo","venue":null,"work_id":"167aba19-1fb9-4285-a42f-8324ad965cf7","year":2024},"citing_paper":{"arxiv_id":"2605.07105","last_updated":"2026-05-08T01:32:22Z","snapshot_observed_at":"2026-07-06T23:19:30.387067Z","submitted_at":"2026-05-08T01:32:22Z","title":"Theoretical Limits of Language Model Alignment","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-11T01:18:37.614335Z"},"links":{"cited_paper":"/paper/2406.01013","citing_paper":"/paper/2605.07105"},"observation_digest":"sha256:8db0b8e55deed58ce617749c054fe8196859027488114b3f1a2dbe1c92b7b250","observation_id":"5dc3a6bc-db45-493c-bf91-0b1bac56b1e0","resolution":{"observed_at":"2026-05-11T04:30:57.181994Z","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/2406.01013/citation-record","integrity":"/paper/2406.01013/integrity","json":"/paper/2406.01013/citation-record.json","paper":"/paper/2406.01013"},"outbound":[],"paper":{"arxiv_id":"2406.01013","last_updated":"2024-06-18T20:53:08Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:24:13.721696Z","submitted_at":"2024-06-03T05:46:53Z","title":"Scalable Ensembling For Mitigating Reward Overoptimisation"},"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 3 inbound Pith citation observations for arXiv:2406.01013."}