{"as_of":"2026-08-06T06:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9fefc307527aa22a92f68b92eb83c00f925af4a6236cda7d146b39c6e058c613","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":"2026-08-05T06:32:48.257954+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":"2026-05-17T12:04:10.210508Z","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":"2026-05-17T12:04:10.853240Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1611.09321","last_updated":"2017-03-15T22:55:17Z","snapshot_observed_at":"2026-07-06T05:20:25.405556Z","submitted_at":"2016-11-28T20:15:55Z","title":"Improving Policy Gradient by Exploring Under-appreciated Rewards","version":3},"cited_work":{"arxiv_id":"1611.09321","doi":null,"metadata_source":"pith","pith_arxiv_id":"1611.09321","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving Policy Gradient by Exploring Under-appreciated Rewards","venue":"cs.LG","work_id":"31c0e586-6368-4860-a526-965fccf80957","year":2016},"citing_paper":{"arxiv_id":"2409.12917","last_updated":"2024-10-04T17:28:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-19T17:16:21Z","title":"Training Language Models to Self-Correct via Reinforcement Learning","version":2},"reference_index":224,"source":"arxiv_source","source_observed_at":"2026-05-17T12:04:10.210508Z"},"links":{"cited_paper":"/paper/1611.09321","citing_paper":"/paper/2409.12917"},"observation_digest":"sha256:4bbb4e1bccfe623eaf7b6c86ee2706134c856889015ad1659f566864c7a0334b","observation_id":"b1d4b1dd-1805-41ae-8243-6baae72081ec","resolution":{"observed_at":"2026-05-17T12:04:10.855601Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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/1611.09321/citation-record","integrity":"/paper/1611.09321/integrity","json":"/paper/1611.09321/citation-record.json","paper":"/paper/1611.09321"},"outbound":[],"paper":{"arxiv_id":"1611.09321","last_updated":"2017-03-15T22:55:17Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T05:20:25.405556Z","submitted_at":"2016-11-28T20:15:55Z","title":"Improving Policy Gradient by Exploring Under-appreciated Rewards"},"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 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1611.09321."}