{"as_of":"2026-08-05T16:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:840b2d0f4141b4f76dd49c82a1ce34d6a2a2a697e62b41da551165fb1811820b","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":"2026-08-05T06:32:48.257954+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":"2026-05-12T04:01:25.989133Z","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":"2026-05-12T06:41:45.960979Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1802.10031","last_updated":"2018-11-19T18:57:02Z","snapshot_observed_at":"2026-08-05T01:52:13.699581Z","submitted_at":"2018-02-27T17:16:48Z","title":"The Mirage of Action-Dependent Baselines in Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"1802.10031","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1802.10031","snapshot_observed_at":"2026-07-04T23:12:36.958783Z","title":"Turner, Zoubin Ghahramani, and Sergey Levine","venue":null,"work_id":"0bc41dd1-560f-4a4e-bde9-a8d4cfd5b4cf","year":2018},"citing_paper":{"arxiv_id":"2605.07579","last_updated":"2026-05-11T03:09:39Z","snapshot_observed_at":"2026-07-06T23:19:56.415523Z","submitted_at":"2026-05-08T10:49:36Z","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-11T02:08:28.113371Z"},"links":{"cited_paper":"/paper/1802.10031","citing_paper":"/paper/2605.07579"},"observation_digest":"sha256:d0b8f97fec5938a35809107b1ee478d751df4e2225976e995f29269b8896f14c","observation_id":"66eda886-bfb5-4fab-9e7b-6854477fcdf5","resolution":{"observed_at":"2026-07-04T23:12:36.958783Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.10031","last_updated":"2018-11-19T18:57:02Z","snapshot_observed_at":"2026-08-05T01:52:13.699581Z","submitted_at":"2018-02-27T17:16:48Z","title":"The Mirage of Action-Dependent Baselines in Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"1802.10031","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1802.10031","snapshot_observed_at":"2026-07-04T23:12:36.958783Z","title":"Turner, Zoubin Ghahramani, and Sergey Levine","venue":null,"work_id":"0bc41dd1-560f-4a4e-bde9-a8d4cfd5b4cf","year":2018},"citing_paper":{"arxiv_id":"2605.07579","last_updated":"2026-05-11T03:09:39Z","snapshot_observed_at":"2026-07-06T23:19:56.415523Z","submitted_at":"2026-05-08T10:49:36Z","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-12T04:01:25.989133Z"},"links":{"cited_paper":"/paper/1802.10031","citing_paper":"/paper/2605.07579"},"observation_digest":"sha256:19fb2997c885036635ffada8546d551833ef98bf07821e10a6a41e12b670f9c9","observation_id":"6fefd98f-3f89-4fc0-9ce5-0d448944eff0","resolution":{"observed_at":"2026-07-04T23:12:36.958783Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1802.10031/citation-record","integrity":"/paper/1802.10031/integrity","json":"/paper/1802.10031/citation-record.json","paper":"/paper/1802.10031"},"outbound":[],"paper":{"arxiv_id":"1802.10031","last_updated":"2018-11-19T18:57:02Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T01:52:13.699581Z","submitted_at":"2018-02-27T17:16:48Z","title":"The Mirage of Action-Dependent Baselines in 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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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:1802.10031."}