{"as_of":"2026-08-12T06:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:433ddfe81f757e194abd219b34b8171af024fc732ef29787b3f5b4047856088a","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":"2026-08-11T06:34:44.6726+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":"2026-08-11T22:15:07.599131Z","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":"2026-08-10T20:18:58.690637Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.09458","last_updated":"2021-07-01T16:03:55Z","snapshot_observed_at":"2026-08-06T01:52:53.175095Z","submitted_at":"2021-01-23T08:51:04Z","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.09458","snapshot_observed_at":"2026-08-11T22:15:07.599131Z","title":"Decoupled exploration and exploitation policies for sample-efficient reinforcement learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03767","last_updated":"2024-12-04T23:12:41Z","snapshot_observed_at":"2026-08-11T22:04:28.390870Z","submitted_at":"2024-12-04T23:12:41Z","title":"Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T22:15:07.599131Z"},"links":{"cited_paper":"/paper/2101.09458","citing_paper":"/paper/2412.03767"},"observation_digest":"sha256:ef82aee7311f52ce51f2fa3b4304cbd77a7dbe3540cb9c0ffb10443744ec8b71","observation_id":"8bd19351-5d4d-4e01-8c62-7f86af3a70d8","resolution":{"observed_at":"2026-08-11T22:15:07.599131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.09458","last_updated":"2021-07-01T16:03:55Z","snapshot_observed_at":"2026-08-06T01:52:53.175095Z","submitted_at":"2021-01-23T08:51:04Z","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2101.09458","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.09458","snapshot_observed_at":"2026-08-10T20:18:58.690637Z","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning","venue":"cs.LG","work_id":"2b60e829-1c8e-4a72-8c06-413d97662faf","year":2021},"citing_paper":{"arxiv_id":"2501.08925","last_updated":"2025-08-24T16:04:08Z","snapshot_observed_at":"2026-08-12T01:12:02.186419Z","submitted_at":"2025-01-15T16:30:29Z","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T20:18:58.488803Z"},"links":{"cited_paper":"/paper/2101.09458","citing_paper":"/paper/2501.08925"},"observation_digest":"sha256:146e30474a8b0a9a33903b4f72fff2614b1e8dc0d201fd9363196334df2c29da","observation_id":"96f40b38-d6bf-4eba-a551-55f232d75e5b","resolution":{"observed_at":"2026-08-10T20:18:58.698860Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2101.09458/citation-record","integrity":"/paper/2101.09458/integrity","json":"/paper/2101.09458/citation-record.json","paper":"/paper/2101.09458"},"outbound":[],"paper":{"arxiv_id":"2101.09458","last_updated":"2021-07-01T16:03:55Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T01:52:53.175095Z","submitted_at":"2021-01-23T08:51:04Z","title":"Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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:2101.09458."}