{"as_of":"2026-08-17T04:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c799e5b7fbc988635967d80bd00f87b7a68dce724e189876f102563eac8c6a57","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":"2026-08-15T22:32:45.004845Z","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":"2026-07-02T12:06:55.882039Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2005.10804","last_updated":"2020-06-19T17:49:05Z","snapshot_observed_at":"2026-07-06T09:22:23.803339Z","submitted_at":"2020-05-21T17:36:09Z","title":"Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.10804","snapshot_observed_at":"2026-08-15T22:32:45.004845Z","title":"Provably efficient reinforcement learning with general value function approximation","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.07101","last_updated":"2025-05-22T14:30:05Z","snapshot_observed_at":"2026-08-15T22:22:36.383757Z","submitted_at":"2025-05-11T19:22:04Z","title":"Constrained Online Decision-Making: A Unified Framework","version":3},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-15T22:32:45.004845Z"},"links":{"cited_paper":"/paper/2005.10804","citing_paper":"/paper/2505.07101"},"observation_digest":"sha256:94043c990205422885ee430581540afacaf1f720c43960b8a1fa2443c1512604","observation_id":"20199f8d-0569-4c55-bec8-a71a86667fb2","resolution":{"observed_at":"2026-08-15T22:32:45.004845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.10804","last_updated":"2020-06-19T17:49:05Z","snapshot_observed_at":"2026-07-06T09:22:23.803339Z","submitted_at":"2020-05-21T17:36:09Z","title":"Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension","version":3},"cited_work":{"arxiv_id":"2005.10804","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.10804","snapshot_observed_at":"2026-07-02T12:06:55.882039Z","title":"Zihan Wang, Boyi Liu, and Chi Jin","venue":null,"work_id":"ce73e6d9-5941-4525-a3f8-0c1790c0e7f5","year":2005},"citing_paper":{"arxiv_id":"2606.06053","last_updated":"2026-07-12T09:46:20Z","snapshot_observed_at":"2026-08-15T09:30:13.878235Z","submitted_at":"2026-06-04T11:54:23Z","title":"Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T02:31:11.200818Z"},"links":{"cited_paper":"/paper/2005.10804","citing_paper":"/paper/2606.06053"},"observation_digest":"sha256:517657d561d04a24fb7307bd7530c840dae91e6acb854094526f71000b61f3e0","observation_id":"ffcba04f-8c7d-4ce4-82ab-8876e7413b10","resolution":{"observed_at":"2026-07-02T12:06:55.883570Z","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":"2005.10804","last_updated":"2020-06-19T17:49:05Z","snapshot_observed_at":"2026-07-06T09:22:23.803339Z","submitted_at":"2020-05-21T17:36:09Z","title":"Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.10804","snapshot_observed_at":"2026-07-14T18:23:21.126826Z","title":"Zihan Wang, Boyi Liu, and Chi Jin","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2606.06053","last_updated":"2026-07-12T09:46:20Z","snapshot_observed_at":"2026-08-15T09:30:13.878235Z","submitted_at":"2026-06-04T11:54:23Z","title":"Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T18:23:21.126826Z"},"links":{"cited_paper":"/paper/2005.10804","citing_paper":"/paper/2606.06053"},"observation_digest":"sha256:e745fa12c3bb3b0eb6b644054f9428a2d14dda54f9bc3a8cdc71ccca5bce2a5c","observation_id":"34538777-5d01-4780-a822-09a6156e2127","resolution":{"observed_at":"2026-07-14T18:23:21.126826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2005.10804/citation-record","integrity":"/paper/2005.10804/integrity","json":"/paper/2005.10804/citation-record.json","paper":"/paper/2005.10804"},"outbound":[],"paper":{"arxiv_id":"2005.10804","last_updated":"2020-06-19T17:49:05Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T09:22:23.803339Z","submitted_at":"2020-05-21T17:36:09Z","title":"Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension"},"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 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2005.10804."}