{"as_of":"2026-08-08T03:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ecb76a0ba7a71446a6fbf83ab4748089220d24ee5701c35dbcc2114f9a0a0ae4","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T01:06:18.561088Z","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":"2026-05-22T07:51:16.548910Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.11091","last_updated":"2021-01-13T19:11:34Z","snapshot_observed_at":"2026-08-07T22:59:21.871787Z","submitted_at":"2020-07-21T21:13:02Z","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL","version":2},"cited_work":{"arxiv_id":"2007.11091","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.11091","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emaq: Expected-max q-learning operator for simple yet effective offline and online RL.CoRR, abs/2007.11091","venue":null,"work_id":"f807fb43-9817-49e5-9399-fe5c0fc4a0ed","year":2007},"citing_paper":{"arxiv_id":"2108.03298","last_updated":"2021-09-25T00:37:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-08-06T20:48:30Z","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-13T08:51:55.826747Z"},"links":{"cited_paper":"/paper/2007.11091","citing_paper":"/paper/2108.03298"},"observation_digest":"sha256:dbcd170b64120d18575e84332a53a821200658ad5aaf64ad2f1bb9ad72c0e5a8","observation_id":"079e9831-c32d-4426-8fd2-17a6e83aecf6","resolution":{"observed_at":"2026-05-13T08:51:55.950585Z","resolver_source":"arxiv_id","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":"2007.11091","last_updated":"2021-01-13T19:11:34Z","snapshot_observed_at":"2026-08-07T22:59:21.871787Z","submitted_at":"2020-07-21T21:13:02Z","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.11091","snapshot_observed_at":"2026-08-07T01:06:18.561088Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.11967","last_updated":"2025-06-13T17:25:27Z","snapshot_observed_at":"2026-08-07T00:57:22.861281Z","submitted_at":"2025-06-13T17:25:27Z","title":"Visual Pre-Training on Unlabeled Images using Reinforcement Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T01:06:18.561088Z"},"links":{"cited_paper":"/paper/2007.11091","citing_paper":"/paper/2506.11967"},"observation_digest":"sha256:fe162a23034f88025477fd88495da55d014431c5796bedc24bbb2fd1f851a5da","observation_id":"9a706c9c-1b13-42de-8294-31444d9fff6a","resolution":{"observed_at":"2026-08-07T01:06:18.561088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.11091","last_updated":"2021-01-13T19:11:34Z","snapshot_observed_at":"2026-08-07T22:59:21.871787Z","submitted_at":"2020-07-21T21:13:02Z","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL","version":2},"cited_work":{"arxiv_id":"2007.11091","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.11091","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emaq: Expected-max q-learning operator for simple yet effective offline and online RL.CoRR, abs/2007.11091","venue":null,"work_id":"f807fb43-9817-49e5-9399-fe5c0fc4a0ed","year":2007},"citing_paper":{"arxiv_id":"2605.22711","last_updated":"2026-05-21T16:50:26Z","snapshot_observed_at":"2026-07-06T23:32:59.663926Z","submitted_at":"2026-05-21T16:50:26Z","title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-22T07:46:20.289421Z"},"links":{"cited_paper":"/paper/2007.11091","citing_paper":"/paper/2605.22711"},"observation_digest":"sha256:6b28111e8ea1c26b51708a384d9b44c9ea6371eba644a49849c7b974f5ba7ccd","observation_id":"42acfa00-10cb-44a1-9353-437dd73ac8d8","resolution":{"observed_at":"2026-05-22T07:51:16.552201Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2007.11091/citation-record","integrity":"/paper/2007.11091/integrity","json":"/paper/2007.11091/citation-record.json","paper":"/paper/2007.11091"},"outbound":[],"paper":{"arxiv_id":"2007.11091","last_updated":"2021-01-13T19:11:34Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T22:59:21.871787Z","submitted_at":"2020-07-21T21:13:02Z","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2007.11091."}