{"as_of":"2026-08-15T06:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5445e1468c29deed67ac7930b0c77bd61334b57e448107e2ef343a8d844b9ba5","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:16:31.952713Z","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":"2026-08-14T21:28:15.397417Z","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":"2026-08-14T09:52:03.795785Z","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":"sha256:3e058d092c729071d544cb35c602e3f8cdd77a624dbcfb477419015371159822","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 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.09321","last_updated":"2017-03-15T22:55:17Z","snapshot_observed_at":"2026-08-14T21:28:15.397417Z","submitted_at":"2016-11-28T20:15:55Z","title":"Improving Policy Gradient by Exploring Under-appreciated Rewards","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.09321","snapshot_observed_at":"2026-08-11T12:16:31.952713Z","title":"Improving policy gradient by exploring under-appreciated rewards","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.14516","last_updated":"2024-12-19T04:31:56Z","snapshot_observed_at":"2026-08-13T00:53:12.423214Z","submitted_at":"2024-12-19T04:31:56Z","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T12:16:31.952713Z"},"links":{"cited_paper":"/paper/1611.09321","citing_paper":"/paper/2412.14516"},"observation_digest":"sha256:c819fe268962637b8b3095cb459a69f43032b368a7e15dc03cf13ba5aaa587fc","observation_id":"42d83879-5ccc-4995-84eb-62af187d97d4","resolution":{"observed_at":"2026-08-11T12:16:31.952713Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.09321","last_updated":"2017-03-15T22:55:17Z","snapshot_observed_at":"2026-08-14T21:28:15.397417Z","submitted_at":"2016-11-28T20:15:55Z","title":"Improving Policy Gradient by Exploring Under-appreciated Rewards","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.09321","snapshot_observed_at":"2026-08-07T11:42:34.196122Z","title":"Improving policy gradient by exploring under-appreciated rewards","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.01639","last_updated":"2025-06-02T13:15:30Z","snapshot_observed_at":"2026-08-13T09:32:52.217115Z","submitted_at":"2025-06-02T13:15:30Z","title":"Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T11:42:34.196122Z"},"links":{"cited_paper":"/paper/1611.09321","citing_paper":"/paper/2506.01639"},"observation_digest":"sha256:38387235dfe224cb6a7c04eea376347d795b5b90a2d55b25ccf58af4ff8b4ee1","observation_id":"c4b94ee6-79d0-4931-8ac2-ba475ccf4576","resolution":{"observed_at":"2026-08-07T11:42:34.196122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"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":"2026-08-14T21:28:15.397417Z","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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1611.09321."}