{"as_of":"2026-08-07T19:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d636c86068b717d01f7747c890d7f26c0dfcb6242ca52818fa51690313fe7313","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:18:49.430393Z","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":"2026-08-06T20:31:08.422311Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.06487","last_updated":"2021-08-07T18:51:37Z","snapshot_observed_at":"2026-08-06T06:51:06.607084Z","submitted_at":"2020-02-16T02:02:23Z","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06487","snapshot_observed_at":"2026-08-07T10:18:49.430393Z","title":"Maxmin q-learning: Controlling the estimation bias of q-learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.05716","last_updated":"2026-07-04T11:13:11Z","snapshot_observed_at":"2026-08-07T10:11:20.967628Z","submitted_at":"2025-06-06T03:36:19Z","title":"Ensemble Elastic DQN: A Step Dependent Ensemble Approach for Reducing Overestimation in Deep Value-Based Reinforcement Learning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T10:18:49.430393Z"},"links":{"cited_paper":"/paper/2002.06487","citing_paper":"/paper/2506.05716"},"observation_digest":"sha256:cb667a79b48c7a5a611c2217971e303c6c8222448a65d4aafe9cd09339a8aa79","observation_id":"9086a3f5-1f5e-405f-a0a9-1042649faf05","resolution":{"observed_at":"2026-08-07T10:18:49.430393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06487","last_updated":"2021-08-07T18:51:37Z","snapshot_observed_at":"2026-08-06T06:51:06.607084Z","submitted_at":"2020-02-16T02:02:23Z","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06487","snapshot_observed_at":"2026-08-07T00:34:01.965749Z","title":"Maxmin q-learning: Controlling the estimation bias of q-learning.arXiv preprint arXiv:2002.06487,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.13862","last_updated":"2025-06-16T18:00:01Z","snapshot_observed_at":"2026-08-07T00:24:19.971630Z","submitted_at":"2025-06-16T18:00:01Z","title":"StaQ it! Growing neural networks for Policy Mirror Descent","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T00:34:01.965749Z"},"links":{"cited_paper":"/paper/2002.06487","citing_paper":"/paper/2506.13862"},"observation_digest":"sha256:4243cd701d68601045cf9d25acc3863fc060b4a5903133bc0a7983b7693437d2","observation_id":"6f1bc58c-a35c-4fa4-a565-7dc90dcc5f57","resolution":{"observed_at":"2026-08-07T00:34:01.965749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06487","last_updated":"2021-08-07T18:51:37Z","snapshot_observed_at":"2026-08-06T06:51:06.607084Z","submitted_at":"2020-02-16T02:02:23Z","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","version":2},"cited_work":{"arxiv_id":"2002.06487","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.06487","snapshot_observed_at":"2026-08-06T20:31:08.422311Z","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","venue":"cs.LG","work_id":"e9a2d593-0325-43a0-92f9-5be66b9c652e","year":2020},"citing_paper":{"arxiv_id":"2507.02712","last_updated":"2025-07-03T15:26:48Z","snapshot_observed_at":"2026-08-06T20:20:16.400675Z","submitted_at":"2025-07-03T15:26:48Z","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T20:31:07.784730Z"},"links":{"cited_paper":"/paper/2002.06487","citing_paper":"/paper/2507.02712"},"observation_digest":"sha256:b0d1c40097fbaa269afaef7a9bc445360c7a584e53221e1407a128568ccecc1a","observation_id":"d088f7c7-5f19-4ea5-a0b3-35d00bd2887e","resolution":{"observed_at":"2026-08-06T20:31:08.425853Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06487","last_updated":"2021-08-07T18:51:37Z","snapshot_observed_at":"2026-08-06T06:51:06.607084Z","submitted_at":"2020-02-16T02:02:23Z","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06487","snapshot_observed_at":"2026-08-01T14:19:58.566038Z","title":null,"venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.26509","last_updated":"2026-07-29T06:18:19Z","snapshot_observed_at":"2026-08-06T07:43:12.234195Z","submitted_at":"2026-07-29T06:18:19Z","title":"Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T14:19:58.566038Z"},"links":{"cited_paper":"/paper/2002.06487","citing_paper":"/paper/2607.26509"},"observation_digest":"sha256:12fcf1002a51f58726046c9063153ba96460ce62925d4879cdbc86a8bd0669f6","observation_id":"5837f5c2-4c72-4f00-98e0-e0f509e345b8","resolution":{"observed_at":"2026-08-01T14:19:58.566038Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2002.06487/citation-record","integrity":"/paper/2002.06487/integrity","json":"/paper/2002.06487/citation-record.json","paper":"/paper/2002.06487"},"outbound":[],"paper":{"arxiv_id":"2002.06487","last_updated":"2021-08-07T18:51:37Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T06:51:06.607084Z","submitted_at":"2020-02-16T02:02:23Z","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2002.06487."}