{"as_of":"2026-08-05T06:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9d3bf7e6382b51634ec5cb7ae05c7a532be37a642e02c654981c79cb0c500cae","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":"2026-08-04T06:34:03.388597+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":"2026-08-04T23:17:52.975477Z","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":"2026-07-01T18:55:58.803104Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.02966","last_updated":"2021-05-04T20:27:33Z","snapshot_observed_at":"2026-07-06T10:02:05.435985Z","submitted_at":"2020-10-06T18:39:23Z","title":"Reinforcement Learning with Random Delays","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02966","snapshot_observed_at":"2026-08-04T23:17:52.975477Z","title":"Rein- forcement learning with random delays,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.06714","last_updated":"2025-09-08T14:09:33Z","snapshot_observed_at":"2026-08-04T23:17:52.616344Z","submitted_at":"2025-09-08T14:09:33Z","title":"RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T23:17:52.975477Z"},"links":{"cited_paper":"/paper/2010.02966","citing_paper":"/paper/2509.06714"},"observation_digest":"sha256:36d11d0dac286dafe4b1ed56065767617cfd6385332e4130568f6e0b5073ab1c","observation_id":"737389b3-d76b-49b6-bdfd-91c40f7c0d0d","resolution":{"observed_at":"2026-08-04T23:17:52.975477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02966","last_updated":"2021-05-04T20:27:33Z","snapshot_observed_at":"2026-07-06T10:02:05.435985Z","submitted_at":"2020-10-06T18:39:23Z","title":"Reinforcement Learning with Random Delays","version":3},"cited_work":{"arxiv_id":"2010.02966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.02966","snapshot_observed_at":"2026-07-01T18:55:58.803104Z","title":"Schulman, J., Moritz, P., Levine, S., Jordan, M., and Abbeel, P","venue":null,"work_id":"f8898f86-c667-4cde-9df9-0241bbbc37e6","year":2010},"citing_paper":{"arxiv_id":"2606.27580","last_updated":"2026-06-25T22:12:22Z","snapshot_observed_at":"2026-08-02T08:38:09.113444Z","submitted_at":"2026-06-25T22:12:22Z","title":"Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T01:23:07.441218Z"},"links":{"cited_paper":"/paper/2010.02966","citing_paper":"/paper/2606.27580"},"observation_digest":"sha256:ec01e9869938dedc54a72222a8fe6d92b5a64419afe4b00cf474fdaeb4a4c621","observation_id":"f019b2b1-739c-47a1-840b-113550646792","resolution":{"observed_at":"2026-07-01T18:55:58.804410Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2010.02966/citation-record","integrity":"/paper/2010.02966/integrity","json":"/paper/2010.02966/citation-record.json","paper":"/paper/2010.02966"},"outbound":[],"paper":{"arxiv_id":"2010.02966","last_updated":"2021-05-04T20:27:33Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:02:05.435985Z","submitted_at":"2020-10-06T18:39:23Z","title":"Reinforcement Learning with Random Delays"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2010.02966."}