{"as_of":"2026-08-14T23:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8c0534e178e38bda9b69e125ad927832303653969b5f772885ea905064e726b0","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":"2026-08-10T18:11:48.442208Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":3,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1912.01557","last_updated":"2020-10-16T05:51:08Z","snapshot_observed_at":"2026-08-09T22:46:14.160461Z","submitted_at":"2019-12-02T11:01:32Z","title":"Policy Optimization Reinforcement Learning with Entropy Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01557","snapshot_observed_at":"2026-08-10T18:11:48.442208Z","title":"arXiv preprint arXiv:1912.01557 (2019)","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.11533","last_updated":"2025-01-20T15:17:24Z","snapshot_observed_at":"2026-08-14T12:39:10.034760Z","submitted_at":"2025-01-20T15:17:24Z","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T18:11:48.442208Z"},"links":{"cited_paper":"/paper/1912.01557","citing_paper":"/paper/2501.11533"},"observation_digest":"sha256:f0a2956da37a2f1907b6922192d191625fe95dab1233f536050b72b26ba1cba5","observation_id":"8f3dc071-12e3-4616-a261-56c905370b96","resolution":{"observed_at":"2026-08-10T18:11:48.442208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01557","last_updated":"2020-10-16T05:51:08Z","snapshot_observed_at":"2026-08-09T22:46:14.160461Z","submitted_at":"2019-12-02T11:01:32Z","title":"Policy Optimization Reinforcement Learning with Entropy Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01557","snapshot_observed_at":"2026-08-06T14:10:34.101630Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.19725","last_updated":"2025-07-26T00:49:25Z","snapshot_observed_at":"2026-08-12T11:50:11.165558Z","submitted_at":"2025-07-26T00:49:25Z","title":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T14:10:34.101630Z"},"links":{"cited_paper":"/paper/1912.01557","citing_paper":"/paper/2507.19725"},"observation_digest":"sha256:a50a51cd8c933b8b5e1af93706250347a467badd03a08c88b0c78254bdafc698","observation_id":"1e0d9857-252e-48d9-93b9-9a3135961f9c","resolution":{"observed_at":"2026-08-06T14:10:34.101630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01557","last_updated":"2020-10-16T05:51:08Z","snapshot_observed_at":"2026-08-09T22:46:14.160461Z","submitted_at":"2019-12-02T11:01:32Z","title":"Policy Optimization Reinforcement Learning with Entropy Regularization","version":3},"cited_work":{"arxiv_id":"1912.01557","doi":"10.48550/arxiv.1912.01557","metadata_source":"pith","pith_arxiv_id":"1912.01557","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Policy Optimization Reinforcement Learning with Entropy Regularization","venue":"cs.LG","work_id":"ce28d688-be18-4b3f-8320-2433aae49eb5","year":2019},"citing_paper":{"arxiv_id":"2607.23854","last_updated":"2026-07-26T21:44:08Z","snapshot_observed_at":"2026-08-13T22:39:58.754345Z","submitted_at":"2026-07-26T21:44:08Z","title":"Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-30T10:33:03.092752Z"},"links":{"cited_paper":"/paper/1912.01557","citing_paper":"/paper/2607.23854"},"observation_digest":"sha256:6aab4543c9bfde174b1f8d74f3a5d0fb91a4bbcea2f9350b4fe43d4adf5c6971","observation_id":"31a1e293-b602-4bfc-9527-9c6520f73f05","resolution":{"observed_at":"2026-07-30T10:36:10.054118Z","resolver_source":"local_arxiv","status":"verified_exact"},"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"}}],"links":{"evidence":"/evidence","html":"/paper/1912.01557/citation-record","integrity":"/paper/1912.01557/integrity","json":"/paper/1912.01557/citation-record.json","paper":"/paper/1912.01557"},"outbound":[],"paper":{"arxiv_id":"1912.01557","last_updated":"2020-10-16T05:51:08Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T22:46:14.160461Z","submitted_at":"2019-12-02T11:01:32Z","title":"Policy Optimization Reinforcement Learning with Entropy Regularization"},"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 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1912.01557."}