{"as_of":"2026-08-06T10:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:424c9c5e31fc42a974f50b73047d9755849f14d2bb6befd8ad965a53b0957991","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":"2026-05-21T13:10:10.452691Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.18246","last_updated":"2024-03-18T00:37:12Z","snapshot_observed_at":"2026-07-06T15:34:51.593721Z","submitted_at":"2023-05-29T17:11:28Z","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","version":2},"cited_work":{"arxiv_id":"2305.18246","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.18246","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Provable and practical: Efficient exploration in reinforcement learning via langevin monte carlo.arXiv preprint arXiv:2305.18246","venue":null,"work_id":"2c040ec6-9ad9-4651-9b81-57ee97656c2a","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":14,"source":"pdf_text","source_observed_at":"2026-05-16T06:35:30.479542Z"},"links":{"cited_paper":"/paper/2305.18246","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:9e4fd17f646be160154446879a4142ab350f6c06c93fe178cdbd00cfe820e7c7","observation_id":"bca89287-66a4-4e47-aedb-4b090b1bce2c","resolution":{"observed_at":"2026-05-16T06:37:28.546455Z","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":"2305.18246","last_updated":"2024-03-18T00:37:12Z","snapshot_observed_at":"2026-07-06T15:34:51.593721Z","submitted_at":"2023-05-29T17:11:28Z","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","version":2},"cited_work":{"arxiv_id":"2305.18246","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.18246","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Provable and practical: Efficient exploration in reinforcement learning via langevin monte carlo.arXiv preprint arXiv:2305.18246","venue":null,"work_id":"2c040ec6-9ad9-4651-9b81-57ee97656c2a","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":14,"source":"pdf_text","source_observed_at":"2026-05-21T13:06:54.002248Z"},"links":{"cited_paper":"/paper/2305.18246","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:c0ba457a193e86d69d94a46730a9435d7c8f0adc3e6e4fcd125c9babe998c79d","observation_id":"9ad30eac-c650-4799-99bd-1da34f9cfd97","resolution":{"observed_at":"2026-05-21T13:10:10.454778Z","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/2305.18246/citation-record","integrity":"/paper/2305.18246/integrity","json":"/paper/2305.18246/citation-record.json","paper":"/paper/2305.18246"},"outbound":[],"paper":{"arxiv_id":"2305.18246","last_updated":"2024-03-18T00:37:12Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T15:34:51.593721Z","submitted_at":"2023-05-29T17:11:28Z","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo"},"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:2305.18246."}