{"as_of":"2026-08-10T15:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fd93bab2f6c8ac46fa58b23c976e8989d9dc92a5d65dc2f3caa36327a6e05e6e","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T00:32:50.368740Z","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":"2026-05-24T06:44:02.486571Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2207.00986","last_updated":"2022-07-03T08:52:40Z","snapshot_observed_at":"2026-07-06T13:27:14.879012Z","submitted_at":"2022-07-03T08:52:40Z","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","version":1},"cited_work":{"arxiv_id":"2207.00986","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2207.00986","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cetin, P","venue":null,"work_id":"42c63a4f-c567-401a-badd-8fa4d01e5f85","year":2022},"citing_paper":{"arxiv_id":"2310.02635","last_updated":"2026-04-23T15:06:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-04T07:56:42Z","title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","version":5},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-24T06:40:00.328012Z"},"links":{"cited_paper":"/paper/2207.00986","citing_paper":"/paper/2310.02635"},"observation_digest":"sha256:223d1dba8e1d43957c0637528bf29dda82381a21168224b7d52228d3992242c3","observation_id":"a6a5fbe1-30ff-4c7e-960c-38dc56bd19a3","resolution":{"observed_at":"2026-05-24T06:44:02.490432Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.00986","last_updated":"2022-07-03T08:52:40Z","snapshot_observed_at":"2026-07-06T13:27:14.879012Z","submitted_at":"2022-07-03T08:52:40Z","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.00986","snapshot_observed_at":"2026-08-07T00:32:50.368740Z","title":"J., Roberts, S., and Celiktutan, O","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13672","last_updated":"2025-06-16T16:30:00Z","snapshot_observed_at":"2026-08-09T12:19:47.488554Z","submitted_at":"2025-06-16T16:30:00Z","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T00:32:50.368740Z"},"links":{"cited_paper":"/paper/2207.00986","citing_paper":"/paper/2506.13672"},"observation_digest":"sha256:1d639522df71935a4b371458d5e186a8f63130cbdcb8fcb84d112b5db6b33f61","observation_id":"ac4175c7-aa18-49a8-8509-72ac5a37170c","resolution":{"observed_at":"2026-08-07T00:32:50.368740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2207.00986/citation-record","integrity":"/paper/2207.00986/integrity","json":"/paper/2207.00986/citation-record.json","paper":"/paper/2207.00986"},"outbound":[],"paper":{"arxiv_id":"2207.00986","last_updated":"2022-07-03T08:52:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T13:27:14.879012Z","submitted_at":"2022-07-03T08:52:40Z","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2207.00986."}