{"as_of":"2026-08-06T08:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:520c06effe442356afccf3ab8ac8b4483faa436a75734f5018c6dc7cebe24916","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":"2026-08-06T06:34:29.942622+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":"2026-05-21T13:06:54.002248Z","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":"2026-05-21T13:10:10.486352Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.12241","last_updated":"2024-06-18T03:32:10Z","snapshot_observed_at":"2026-08-04T08:05:32.315700Z","submitted_at":"2024-06-18T03:32:10Z","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","version":1},"cited_work":{"arxiv_id":"2406.12241","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.12241","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"More efficient randomized exploration for reinforcement learning via approximate sampling.arXiv preprint arXiv:2406.12241","venue":null,"work_id":"dd1947c0-6e05-483c-9fc2-8e8ded101880","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":15,"source":"pdf_text","source_observed_at":"2026-05-16T06:35:30.479542Z"},"links":{"cited_paper":"/paper/2406.12241","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:247e442017904b53c450a5a5d3b134326aeda420d845ed658c54421463343074","observation_id":"5be92ee5-bb9a-4c30-8eee-26b2f3b9f1ca","resolution":{"observed_at":"2026-05-16T06:37:28.592535Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12241","last_updated":"2024-06-18T03:32:10Z","snapshot_observed_at":"2026-08-04T08:05:32.315700Z","submitted_at":"2024-06-18T03:32:10Z","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","version":1},"cited_work":{"arxiv_id":"2406.12241","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.12241","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"More efficient randomized exploration for reinforcement learning via approximate sampling.arXiv preprint arXiv:2406.12241","venue":null,"work_id":"dd1947c0-6e05-483c-9fc2-8e8ded101880","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":15,"source":"pdf_text","source_observed_at":"2026-05-21T13:06:54.002248Z"},"links":{"cited_paper":"/paper/2406.12241","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:edc7d0612ea16725cc04a084e2c229a3d34a7e848141d73d800d090fd363db9f","observation_id":"bf4cb7c3-cffa-45d2-b8db-2c8f1412da16","resolution":{"observed_at":"2026-05-21T13:10:10.488584Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.12241/citation-record","integrity":"/paper/2406.12241/integrity","json":"/paper/2406.12241/citation-record.json","paper":"/paper/2406.12241"},"outbound":[],"paper":{"arxiv_id":"2406.12241","last_updated":"2024-06-18T03:32:10Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T08:05:32.315700Z","submitted_at":"2024-06-18T03:32:10Z","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.12241."}