{"as_of":"2026-08-15T09:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:50788630a6b9fa7958bbc929f4fa748645e4a0e393562b2129a9e893f296e3a8","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":"2026-08-15T06:32:42.880941+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":"2026-08-11T19:28:38.396922Z","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":"2026-08-06T04:39:11.650771Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1903.10605","last_updated":"2019-07-01T21:03:09Z","snapshot_observed_at":"2026-08-14T16:56:57.508089Z","submitted_at":"2019-03-25T21:46:58Z","title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10605","snapshot_observed_at":"2026-08-11T19:28:38.396922Z","title":"Q-learning for continuous actions with cross-entropy guided policies.arXiv preprint arXiv:1903.10605, 2019","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.06685","last_updated":"2024-12-09T17:28:03Z","snapshot_observed_at":"2026-08-13T05:32:21.574534Z","submitted_at":"2024-12-09T17:28:03Z","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T19:28:38.396922Z"},"links":{"cited_paper":"/paper/1903.10605","citing_paper":"/paper/2412.06685"},"observation_digest":"sha256:0b16dd92a81b4a6025e45bfe60acc89c79a39518c08618234430bfd2c37d1326","observation_id":"d14fd665-77f4-409e-8587-75aaf4caee95","resolution":{"observed_at":"2026-08-11T19:28:38.396922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10605","last_updated":"2019-07-01T21:03:09Z","snapshot_observed_at":"2026-08-14T16:56:57.508089Z","submitted_at":"2019-03-25T21:46:58Z","title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies","version":3},"cited_work":{"arxiv_id":"1903.10605","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.10605","snapshot_observed_at":"2026-08-06T04:39:11.650771Z","title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies","venue":"cs.AI","work_id":"8325e832-1263-4ae0-8adc-3289c83da9d9","year":2019},"citing_paper":{"arxiv_id":"2508.03194","last_updated":"2025-08-05T08:03:12Z","snapshot_observed_at":"2026-08-11T12:45:17.685609Z","submitted_at":"2025-08-05T08:03:12Z","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T04:39:07.677891Z"},"links":{"cited_paper":"/paper/1903.10605","citing_paper":"/paper/2508.03194"},"observation_digest":"sha256:153d2e8a4a8c557b909452c2782c8cf42c908bbae3e03eac4a4a1c7a42dfb6d7","observation_id":"04bfc398-424b-4cec-927b-236058396c63","resolution":{"observed_at":"2026-08-06T04:39:11.817965Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1903.10605/citation-record","integrity":"/paper/1903.10605/integrity","json":"/paper/1903.10605/citation-record.json","paper":"/paper/1903.10605"},"outbound":[],"paper":{"arxiv_id":"1903.10605","last_updated":"2019-07-01T21:03:09Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-14T16:56:57.508089Z","submitted_at":"2019-03-25T21:46:58Z","title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1903.10605."}