{"as_of":"2026-08-13T17:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cdc7bca3d1f00328d36f003df0eca1fda294cdf93da180c9c0d330ca77b03d04","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T10:52:51.116862Z","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":"2026-05-17T05:48:07.012721Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1805.03359","last_updated":"2018-11-07T20:36:53Z","snapshot_observed_at":"2026-08-04T20:32:26.661813Z","submitted_at":"2018-05-09T03:11:29Z","title":"Reward Estimation for Variance Reduction in Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"1805.03359","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.03359","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reward Estimation for Variance Reduction in Deep Reinforcement Learning","venue":"cs.LG","work_id":"08d76bb6-41d0-415f-bd64-2cb1e5f8b6f0","year":2018},"citing_paper":{"arxiv_id":"2008.02217","last_updated":"2021-04-28T07:24:49Z","snapshot_observed_at":"2026-08-13T03:08:20.485293Z","submitted_at":"2020-07-16T17:52:37Z","title":"Hopfield Networks is All You Need","version":3},"reference_index":249,"source":"arxiv_source","source_observed_at":"2026-05-17T05:48:06.868758Z"},"links":{"cited_paper":"/paper/1805.03359","citing_paper":"/paper/2008.02217"},"observation_digest":"sha256:35431069594f5b08cbdaea9a995574b036bf090f2178e7b1d43f063702eaf379","observation_id":"d1930cf0-e051-4e36-8bb8-051aa726aa41","resolution":{"observed_at":"2026-05-17T05:48:07.015051Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.03359","last_updated":"2018-11-07T20:36:53Z","snapshot_observed_at":"2026-08-04T20:32:26.661813Z","submitted_at":"2018-05-09T03:11:29Z","title":"Reward Estimation for Variance Reduction in Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.03359","snapshot_observed_at":"2026-08-12T10:52:51.116862Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.10381","last_updated":"2025-05-26T03:49:37Z","snapshot_observed_at":"2026-08-13T07:21:07.679051Z","submitted_at":"2024-11-28T04:06:02Z","title":"Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed","version":6},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T10:52:51.116862Z"},"links":{"cited_paper":"/paper/1805.03359","citing_paper":"/paper/2412.10381"},"observation_digest":"sha256:e3601b60f58d00585f6e40f6bc5f898ff36f2336b1459a26351916948af52418","observation_id":"93686276-b083-4f0c-9aeb-d98005ba99b9","resolution":{"observed_at":"2026-08-12T10:52:51.116862Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1805.03359/citation-record","integrity":"/paper/1805.03359/integrity","json":"/paper/1805.03359/citation-record.json","paper":"/paper/1805.03359"},"outbound":[],"paper":{"arxiv_id":"1805.03359","last_updated":"2018-11-07T20:36:53Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T20:32:26.661813Z","submitted_at":"2018-05-09T03:11:29Z","title":"Reward Estimation for Variance Reduction in Deep 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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1805.03359."}