{"as_of":"2026-08-12T06:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a9ac2e132ff49cdbb2ff47adf8a5f4fa7361c696449aa277aa6169da239b12f4","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T12:38:32.184591Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T22:16:42.211692Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1705.07041","last_updated":"2020-03-30T23:58:02Z","snapshot_observed_at":"2026-07-06T05:43:24.039769Z","submitted_at":"2017-05-19T15:10:21Z","title":"Posterior sampling for reinforcement learning: worst-case regret bounds","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07041","snapshot_observed_at":"2026-08-11T12:38:32.184591Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.14075","last_updated":"2024-12-19T14:41:03Z","snapshot_observed_at":"2026-08-11T12:28:52.703238Z","submitted_at":"2024-12-18T17:19:55Z","title":"Online MDP with Transition Prototypes: A Robust Adaptive Approach","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T12:38:32.184591Z"},"links":{"cited_paper":"/paper/1705.07041","citing_paper":"/paper/2412.14075"},"observation_digest":"sha256:e3afe856bca2d6b688953ccd2e859b6e6ee0ec782dd039f14d2c9aec1fd8ae6b","observation_id":"677c2e43-bf96-461f-a037-dca6b1b2a0a3","resolution":{"observed_at":"2026-08-11T12:38:32.184591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07041","last_updated":"2020-03-30T23:58:02Z","snapshot_observed_at":"2026-07-06T05:43:24.039769Z","submitted_at":"2017-05-19T15:10:21Z","title":"Posterior sampling for reinforcement learning: worst-case regret bounds","version":3},"cited_work":{"arxiv_id":"1705.07041","doi":null,"metadata_source":"pith","pith_arxiv_id":"1705.07041","snapshot_observed_at":"2026-08-06T22:16:42.211692Z","title":"Posterior sampling for reinforcement learning: worst-case regret bounds","venue":"cs.LG","work_id":"ddc9dc43-1c98-4f6c-85ed-8c13131dd78e","year":2017},"citing_paper":{"arxiv_id":"2506.22401","last_updated":"2025-06-27T17:18:43Z","snapshot_observed_at":"2026-08-12T04:33:28.346732Z","submitted_at":"2025-06-27T17:18:43Z","title":"Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T22:16:40.034564Z"},"links":{"cited_paper":"/paper/1705.07041","citing_paper":"/paper/2506.22401"},"observation_digest":"sha256:4eead2e7c2165c9a0cb3442b3e83c3d814fb722471d64abbf32240f19de34bde","observation_id":"349dbb18-227f-4524-b75a-bd9eba90e993","resolution":{"observed_at":"2026-08-06T22:16:42.253497Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1705.07041/citation-record","integrity":"/paper/1705.07041/integrity","json":"/paper/1705.07041/citation-record.json","paper":"/paper/1705.07041"},"outbound":[],"paper":{"arxiv_id":"1705.07041","last_updated":"2020-03-30T23:58:02Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T05:43:24.039769Z","submitted_at":"2017-05-19T15:10:21Z","title":"Posterior sampling for reinforcement learning: worst-case regret bounds"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1705.07041."}