{"as_of":"2026-08-19T07:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7004588e5c60bef66ef03f8ba6927bb824523f4b5b13a738139ea0f2ec7396fe","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":"2026-08-19T06:32:44.657259+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":"2026-08-16T00:06:35.818578Z","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":"2026-08-07T10:43:38.288421Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.01386","last_updated":"2025-04-22T19:08:27Z","snapshot_observed_at":"2026-08-19T02:12:31.387756Z","submitted_at":"2024-06-03T14:48:53Z","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01386","snapshot_observed_at":"2026-08-07T12:59:39.839337Z","title":"Combinatorial multivariant multi- armed bandits with applications to episodic reinforcement learning and beyond.arXiv preprint arXiv:2406.01386, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23131","last_updated":"2026-06-04T20:53:20Z","snapshot_observed_at":"2026-08-14T22:00:11.264091Z","submitted_at":"2025-05-29T06:04:32Z","title":"DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:59:39.839337Z"},"links":{"cited_paper":"/paper/2406.01386","citing_paper":"/paper/2505.23131"},"observation_digest":"sha256:a0ddb27de69a5079967676d755004f38c35cae42af26178fd6adab0fec3c8794","observation_id":"e00cfcb2-3e10-42d9-8dc5-1d4b51ca682b","resolution":{"observed_at":"2026-08-07T12:59:39.839337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01386","last_updated":"2025-04-22T19:08:27Z","snapshot_observed_at":"2026-08-19T02:12:31.387756Z","submitted_at":"2024-06-03T14:48:53Z","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","version":3},"cited_work":{"arxiv_id":"2406.01386","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.01386","snapshot_observed_at":"2026-08-07T10:43:38.288421Z","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","venue":"cs.LG","work_id":"31b9a83b-b863-4f9a-86eb-87b7977f8ecf","year":2024},"citing_paper":{"arxiv_id":"2506.04594","last_updated":"2025-06-05T03:19:57Z","snapshot_observed_at":"2026-08-18T08:50:38.486079Z","submitted_at":"2025-06-05T03:19:57Z","title":"Intelligent Channel Allocation for IEEE 802.11be Multi-Link Operation: When MAB Meets LLM","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:36.981857Z"},"links":{"cited_paper":"/paper/2406.01386","citing_paper":"/paper/2506.04594"},"observation_digest":"sha256:52b345382c34c1d2f1240193238931c7135cd716f1f32d927c755afd43967310","observation_id":"7314a9b9-dacc-4c4e-a0e2-2113353fd139","resolution":{"observed_at":"2026-08-07T10:43:38.371550Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01386","last_updated":"2025-04-22T19:08:27Z","snapshot_observed_at":"2026-08-19T02:12:31.387756Z","submitted_at":"2024-06-03T14:48:53Z","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01386","snapshot_observed_at":"2026-08-16T00:06:35.818578Z","title":"arXiv preprint arXiv:2406.01386 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.12753","last_updated":"2026-08-13T03:06:11Z","snapshot_observed_at":"2026-08-19T06:14:46.131568Z","submitted_at":"2026-08-13T03:06:11Z","title":"Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry","version":1},"reference_index":132,"source":"arxiv_source","source_observed_at":"2026-08-16T00:06:35.818578Z"},"links":{"cited_paper":"/paper/2406.01386","citing_paper":"/paper/2608.12753"},"observation_digest":"sha256:21ddbdd7d0d1275c0b0c830b2289500795a19ec2d1a45e5359bce225b740627b","observation_id":"afe966b3-8ce7-48ca-b19b-c9db2f3e3f98","resolution":{"observed_at":"2026-08-16T00:06:35.818578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.01386/citation-record","integrity":"/paper/2406.01386/integrity","json":"/paper/2406.01386/citation-record.json","paper":"/paper/2406.01386"},"outbound":[],"paper":{"arxiv_id":"2406.01386","last_updated":"2025-04-22T19:08:27Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T02:12:31.387756Z","submitted_at":"2024-06-03T14:48:53Z","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.01386."}