{"as_of":"2026-08-16T16:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7400b8f4ccaa4bf600a8e28c263190954f26cee9a5601918a5fad3876c4694d8","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":"2026-08-16T06:30:59.297886+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":"2026-08-14T12:58:10.434294Z","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":"2026-05-11T12:26:08.922944Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1805.05071","last_updated":"2022-07-01T10:12:30Z","snapshot_observed_at":"2026-08-16T14:47:24.419240Z","submitted_at":"2018-05-14T09:05:10Z","title":"KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.05071","snapshot_observed_at":"2026-08-14T12:58:10.434294Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.06158","last_updated":"2019-08-16T20:44:01Z","snapshot_observed_at":"2026-08-16T11:26:00.431548Z","submitted_at":"2019-08-16T20:44:01Z","title":"Accelerated learning from recommender systems using multi-armed bandit","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:58:10.434294Z"},"links":{"cited_paper":"/paper/1805.05071","citing_paper":"/paper/1908.06158"},"observation_digest":"sha256:2511cfc29e94a59114800caa8da51287c63c39e6145c1da68072fd912604b749","observation_id":"35c38755-4f24-43ff-8b16-d53c0997f5dc","resolution":{"observed_at":"2026-08-14T12:58:10.434294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.05071","last_updated":"2022-07-01T10:12:30Z","snapshot_observed_at":"2026-08-16T14:47:24.419240Z","submitted_at":"2018-05-14T09:05:10Z","title":"KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints","version":3},"cited_work":{"arxiv_id":"1805.05071","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1805.05071","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv , arxivId =:1805.05071 , month =","venue":null,"work_id":"b093a95c-5940-4d72-89d4-8d08919ca077","year":null},"citing_paper":{"arxiv_id":"2604.19672","last_updated":"2026-04-21T16:51:57Z","snapshot_observed_at":"2026-08-15T10:37:42.834332Z","submitted_at":"2026-04-21T16:51:57Z","title":"Budgeted Online Influence Maximization","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-05-10T03:39:32.852934Z"},"links":{"cited_paper":"/paper/1805.05071","citing_paper":"/paper/2604.19672"},"observation_digest":"sha256:a18a3413229fa79392a1261b4c49a71c3c8150f187870fb25e21ed05dc421e82","observation_id":"a60d3712-b311-4d9c-96db-63692e172048","resolution":{"observed_at":"2026-05-11T12:26:08.926507Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.05071","last_updated":"2022-07-01T10:12:30Z","snapshot_observed_at":"2026-08-16T14:47:24.419240Z","submitted_at":"2018-05-14T09:05:10Z","title":"KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.05071","snapshot_observed_at":"2026-08-03T09:55:52.708972Z","title":"arXiv preprint arXiv:1805.05071 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.29294","last_updated":"2026-07-31T11:12:31Z","snapshot_observed_at":"2026-08-13T20:34:15.935730Z","submitted_at":"2026-07-31T11:12:31Z","title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-03T09:55:52.708972Z"},"links":{"cited_paper":"/paper/1805.05071","citing_paper":"/paper/2607.29294"},"observation_digest":"sha256:8e2ec20115830f2faaad7ec79f19f38f31cdc03e63ed760778afe53ff11742a7","observation_id":"bcdc0c60-f423-4af0-9e75-bb72101a73fc","resolution":{"observed_at":"2026-08-03T09:55:52.708972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1805.05071/citation-record","integrity":"/paper/1805.05071/integrity","json":"/paper/1805.05071/citation-record.json","paper":"/paper/1805.05071"},"outbound":[],"paper":{"arxiv_id":"1805.05071","last_updated":"2022-07-01T10:12:30Z","latest_version":3,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-16T14:47:24.419240Z","submitted_at":"2018-05-14T09:05:10Z","title":"KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1805.05071."}