{"as_of":"2026-08-19T12:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c87a94ecc1f4e238491dc49f9c86fdaae4ae34650a4a5830bf5dc569c98a7f98","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":"2026-08-19T06:32:44.657259+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":"2026-08-16T11:46:01.147793Z","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":"2026-08-06T17:57:08.994560Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.12974","last_updated":"2020-04-27T17:38:53Z","snapshot_observed_at":"2026-07-06T09:15:35.314874Z","submitted_at":"2020-04-27T17:38:53Z","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.12974","snapshot_observed_at":"2026-08-16T11:46:01.147793Z","title":"Emergent real-world robotic skills via unsupervised off-policy reinforcement learning","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2504.14805","last_updated":"2025-04-21T02:11:39Z","snapshot_observed_at":"2026-08-18T22:34:58.739258Z","submitted_at":"2025-04-21T02:11:39Z","title":"Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T11:46:01.147793Z"},"links":{"cited_paper":"/paper/2004.12974","citing_paper":"/paper/2504.14805"},"observation_digest":"sha256:f2efbcddfc7875f660eadc7af7a94e13904e227b9bc12bed614b0083a62bad44","observation_id":"6d5e4303-c42a-480d-aba1-72ce395d9682","resolution":{"observed_at":"2026-08-16T11:46:01.147793Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.12974","last_updated":"2020-04-27T17:38:53Z","snapshot_observed_at":"2026-07-06T09:15:35.314874Z","submitted_at":"2020-04-27T17:38:53Z","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2004.12974","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.12974","snapshot_observed_at":"2026-08-06T17:57:08.994560Z","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","venue":"cs.RO","work_id":"9256d3f0-4ac8-42b4-8365-a8742686c9ba","year":2020},"citing_paper":{"arxiv_id":"2507.09495","last_updated":"2025-07-13T05:02:43Z","snapshot_observed_at":"2026-08-15T17:39:34.440636Z","submitted_at":"2025-07-13T05:02:43Z","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","version":1},"reference_index":136,"source":"pdf_text","source_observed_at":"2026-08-06T17:57:08.632962Z"},"links":{"cited_paper":"/paper/2004.12974","citing_paper":"/paper/2507.09495"},"observation_digest":"sha256:a8b2bf263b8395793f6b54ae2fb061edbf738e777b1953ee8f06a92c6d38e065","observation_id":"0d5d65fb-4b6d-4953-9247-6259b88b18e9","resolution":{"observed_at":"2026-08-06T17:57:08.998788Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2004.12974/citation-record","integrity":"/paper/2004.12974/integrity","json":"/paper/2004.12974/citation-record.json","paper":"/paper/2004.12974"},"outbound":[],"paper":{"arxiv_id":"2004.12974","last_updated":"2020-04-27T17:38:53Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-07-06T09:15:35.314874Z","submitted_at":"2020-04-27T17:38:53Z","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy 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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2004.12974."}