{"as_of":"2026-08-13T05:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:35215d9b681dda0c223710d420713b2ae97f1fb3e066de4069d3222207c87430","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T22:15:08.194750Z","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":"2026-05-19T17:12:41.371382Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2006.01782","last_updated":"2020-06-02T17:02:55Z","snapshot_observed_at":"2026-08-13T00:43:46.311162Z","submitted_at":"2020-06-02T17:02:55Z","title":"Temporally-Extended {\\epsilon}-Greedy Exploration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.01782","snapshot_observed_at":"2026-08-11T22:15:08.194750Z","title":"Temporally-extended {\\epsilon}-greedy exploration","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.03767","last_updated":"2024-12-04T23:12:41Z","snapshot_observed_at":"2026-08-12T09:34:12.100457Z","submitted_at":"2024-12-04T23:12:41Z","title":"Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T22:15:08.194750Z"},"links":{"cited_paper":"/paper/2006.01782","citing_paper":"/paper/2412.03767"},"observation_digest":"sha256:92adca2845919939498e5dc13b0d8d36d61944c756e19baaa50b5b7d1bb1fff4","observation_id":"f4aaee55-e2ac-4197-9a3c-a0591c7617a7","resolution":{"observed_at":"2026-08-11T22:15:08.194750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.01782","last_updated":"2020-06-02T17:02:55Z","snapshot_observed_at":"2026-08-13T00:43:46.311162Z","submitted_at":"2020-06-02T17:02:55Z","title":"Temporally-Extended {\\epsilon}-Greedy Exploration","version":1},"cited_work":{"arxiv_id":"2006.01782","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2006.01782","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Temporally-extended{\\epsilon}-greedy exploration","venue":null,"work_id":"23fa4203-f98d-498b-94a6-78f2a746293c","year":2006},"citing_paper":{"arxiv_id":"2604.04539","last_updated":"2026-05-15T07:15:36Z","snapshot_observed_at":"2026-08-02T17:13:51.910717Z","submitted_at":"2026-04-06T09:03:41Z","title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T20:04:56.512544Z"},"links":{"cited_paper":"/paper/2006.01782","citing_paper":"/paper/2604.04539"},"observation_digest":"sha256:644563c8036ba049b6511f7e0569b7baab729db5653c85d0fe4630e11beb4775","observation_id":"7d511b0c-05ab-40bf-9e29-b38c6b784a58","resolution":{"observed_at":"2026-05-10T22:15:49.929412Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2006.01782","last_updated":"2020-06-02T17:02:55Z","snapshot_observed_at":"2026-08-13T00:43:46.311162Z","submitted_at":"2020-06-02T17:02:55Z","title":"Temporally-Extended {\\epsilon}-Greedy Exploration","version":1},"cited_work":{"arxiv_id":"2006.01782","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2006.01782","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Temporally-extended{\\epsilon}-greedy exploration","venue":null,"work_id":"23fa4203-f98d-498b-94a6-78f2a746293c","year":2006},"citing_paper":{"arxiv_id":"2604.04539","last_updated":"2026-05-15T07:15:36Z","snapshot_observed_at":"2026-08-02T17:13:51.910717Z","submitted_at":"2026-04-06T09:03:41Z","title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-19T17:08:31.770889Z"},"links":{"cited_paper":"/paper/2006.01782","citing_paper":"/paper/2604.04539"},"observation_digest":"sha256:50c8dd9130eed566832411362c923778e9003f69c0e3e679bb7396c61678ba8e","observation_id":"6b13ce23-a4ea-4721-bcdd-3f73351f4adc","resolution":{"observed_at":"2026-05-19T17:12:41.372969Z","resolver_source":"arxiv_id","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/2006.01782/citation-record","integrity":"/paper/2006.01782/integrity","json":"/paper/2006.01782/citation-record.json","paper":"/paper/2006.01782"},"outbound":[],"paper":{"arxiv_id":"2006.01782","last_updated":"2020-06-02T17:02:55Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T00:43:46.311162Z","submitted_at":"2020-06-02T17:02:55Z","title":"Temporally-Extended {\\epsilon}-Greedy Exploration"},"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 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2006.01782."}