{"as_of":"2026-08-18T08:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ac136ef8645d9df7ebbe08d2c2555254da320c062ed01ff363adf3a9216822e9","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T00:51:43.986018Z","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":"2026-08-12T00:51:44.040745Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2008.06036","last_updated":"2021-03-04T20:04:50Z","snapshot_observed_at":"2026-08-17T19:54:46.448667Z","submitted_at":"2020-08-13T17:49:18Z","title":"Reinforcement Learning with Trajectory Feedback","version":2},"cited_work":{"arxiv_id":"2008.06036","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.06036","snapshot_observed_at":"2026-08-12T00:51:44.040745Z","title":"Reinforcement Learning with Trajectory Feedback","venue":"cs.LG","work_id":"efb6bbb6-27de-475f-8372-e37d55726e84","year":2020},"citing_paper":{"arxiv_id":"2608.10386","last_updated":"2026-08-11T02:27:26Z","snapshot_observed_at":"2026-08-17T15:57:41.498169Z","submitted_at":"2026-08-11T02:27:26Z","title":"Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T00:51:43.986018Z"},"links":{"cited_paper":"/paper/2008.06036","citing_paper":"/paper/2608.10386"},"observation_digest":"sha256:0b92f074b1b98bda19353d484f0a71da21b21ef53b114d002630fdb6efce0788","observation_id":"eef7fdc5-3f66-4db4-b463-695e85b0756c","resolution":{"observed_at":"2026-08-12T00:51:44.049063Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2008.06036/citation-record","integrity":"/paper/2008.06036/integrity","json":"/paper/2008.06036/citation-record.json","paper":"/paper/2008.06036"},"outbound":[],"paper":{"arxiv_id":"2008.06036","last_updated":"2021-03-04T20:04:50Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T19:54:46.448667Z","submitted_at":"2020-08-13T17:49:18Z","title":"Reinforcement Learning with Trajectory Feedback"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2008.06036."}