{"as_of":"2026-08-13T01:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:46fb39098c116fc25ee50f22ad6a9f8c68d85c7553350950d39d05d9a5f16092","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":"2026-08-12T06:34:41.77262+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":"2026-05-09T16:23:20.699645Z","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":"2026-05-11T16:31:09.900873Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.06709","last_updated":"2020-11-24T21:47:29Z","snapshot_observed_at":"2026-07-06T10:14:13.767423Z","submitted_at":"2020-11-13T01:01:13Z","title":"Active Reinforcement Learning: Observing Rewards at a Cost","version":2},"cited_work":{"arxiv_id":"2011.06709","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.06709","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Active reinforcement learning: Observing rewards at a cost.arXiv:2011.06709 [cs.LG]","venue":null,"work_id":"c18a7bba-36f3-4ba2-8b37-55aecf42fe14","year":2011},"citing_paper":{"arxiv_id":"2605.01833","last_updated":"2026-05-03T12:00:25Z","snapshot_observed_at":"2026-07-31T08:29:03.173781Z","submitted_at":"2026-05-03T12:00:25Z","title":"Remote Action Generation: Remote Control with Minimal Communication","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-09T16:23:20.699645Z"},"links":{"cited_paper":"/paper/2011.06709","citing_paper":"/paper/2605.01833"},"observation_digest":"sha256:57efc7d51482b5f8ea8a514cd20dba2fdfb1da407e4a26f748288245a24b1e6f","observation_id":"4d2601aa-ba44-475d-a3d1-7b97e1983455","resolution":{"observed_at":"2026-05-11T16:31:09.904889Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2011.06709/citation-record","integrity":"/paper/2011.06709/integrity","json":"/paper/2011.06709/citation-record.json","paper":"/paper/2011.06709"},"outbound":[],"paper":{"arxiv_id":"2011.06709","last_updated":"2020-11-24T21:47:29Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:14:13.767423Z","submitted_at":"2020-11-13T01:01:13Z","title":"Active Reinforcement Learning: Observing Rewards at a Cost"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2011.06709."}