{"as_of":"2026-08-09T18:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bd6cdd17104a87f66d6a4c07817fa6934e33967541cdf55a7f379d817a5e2f82","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T04:59:11.753710Z","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":"2026-05-21T13:10:10.470449Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2302.09339","last_updated":"2023-06-04T13:35:45Z","snapshot_observed_at":"2026-08-09T14:10:12.746383Z","submitted_at":"2023-02-18T14:13:25Z","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.09339","snapshot_observed_at":"2026-08-07T04:59:11.753710Z","title":"Efficient Exploration via Epistemic - Risk - Seeking Policy Optimization , June 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09270","last_updated":"2025-06-10T22:07:13Z","snapshot_observed_at":"2026-08-09T14:59:59.898677Z","submitted_at":"2025-06-10T22:07:13Z","title":"Uncertainty Prioritized Experience Replay","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T04:59:11.753710Z"},"links":{"cited_paper":"/paper/2302.09339","citing_paper":"/paper/2506.09270"},"observation_digest":"sha256:215c681e9d460d52eb271ff7461da28e79bcc8761f10bc855a5d5eaa489caba0","observation_id":"f313ebd7-a4bd-4626-988b-13528cf7511a","resolution":{"observed_at":"2026-08-07T04:59:11.753710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.09339","last_updated":"2023-06-04T13:35:45Z","snapshot_observed_at":"2026-08-09T14:10:12.746383Z","submitted_at":"2023-02-18T14:13:25Z","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","version":2},"cited_work":{"arxiv_id":"2302.09339","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.09339","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient exploration via epistemic-risk-seeking policy optimization.arXiv preprint arXiv:2302.09339","venue":null,"work_id":"f0c7c155-244a-499f-a8c1-090de3cbe8d2","year":null},"citing_paper":{"arxiv_id":"2602.06239","last_updated":"2026-05-15T16:18:46Z","snapshot_observed_at":"2026-07-06T22:44:46.690576Z","submitted_at":"2026-02-05T22:31:07Z","title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-16T06:35:30.479542Z"},"links":{"cited_paper":"/paper/2302.09339","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:b42657cc3208daeb94061c4c9fdf4eacaad6b6a1325b594b674682e27c3f71a8","observation_id":"18370318-bc2c-495c-89ff-7e0c46c30c42","resolution":{"observed_at":"2026-05-16T06:37:28.603186Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.09339","last_updated":"2023-06-04T13:35:45Z","snapshot_observed_at":"2026-08-09T14:10:12.746383Z","submitted_at":"2023-02-18T14:13:25Z","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","version":2},"cited_work":{"arxiv_id":"2302.09339","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.09339","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient exploration via epistemic-risk-seeking policy optimization.arXiv preprint arXiv:2302.09339","venue":null,"work_id":"f0c7c155-244a-499f-a8c1-090de3cbe8d2","year":null},"citing_paper":{"arxiv_id":"2602.06239","last_updated":"2026-05-15T16:18:46Z","snapshot_observed_at":"2026-07-06T22:44:46.690576Z","submitted_at":"2026-02-05T22:31:07Z","title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-21T13:06:54.002248Z"},"links":{"cited_paper":"/paper/2302.09339","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:4a9f3b79adba28d25f807ab2acf51f6520a5293af0aa2c1e4202b5e32470a482","observation_id":"2d6efd9b-139d-462c-a986-2a723501163b","resolution":{"observed_at":"2026-05-21T13:10:10.472344Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2302.09339/citation-record","integrity":"/paper/2302.09339/integrity","json":"/paper/2302.09339/citation-record.json","paper":"/paper/2302.09339"},"outbound":[],"paper":{"arxiv_id":"2302.09339","last_updated":"2023-06-04T13:35:45Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T14:10:12.746383Z","submitted_at":"2023-02-18T14:13:25Z","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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:2302.09339."}