{"as_of":"2026-08-07T03:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6d50ef84f86eef82bd96efa9be8ce409af8f35c5e9a165c9c45e2719e815b128","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":"2026-08-06T06:34:29.942622+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":"2026-05-23T19:19:27.381408Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-23T19:23:22.088073Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.15370","last_updated":"2025-05-21T05:30:43Z","snapshot_observed_at":"2026-07-06T19:55:51.415524Z","submitted_at":"2024-11-22T22:46:21Z","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","version":2},"cited_work":{"arxiv_id":"2411.15370","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.15370","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"https://arxiv.org/abs/2411.15370","venue":null,"work_id":"3bb1a1d0-a457-4b4f-8f4e-0a2334ef8e8e","year":2024},"citing_paper":{"arxiv_id":"2410.17517","last_updated":"2026-07-21T18:31:44Z","snapshot_observed_at":"2026-08-02T20:53:10.034892Z","submitted_at":"2024-10-23T02:49:37Z","title":"The Hive Mind is a Single Reinforcement Learning Agent","version":5},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-23T19:19:27.381408Z"},"links":{"cited_paper":"/paper/2411.15370","citing_paper":"/paper/2410.17517"},"observation_digest":"sha256:9d5d4de93bd9f65a6dfc945c6f8f971e5d2b5fa0968beb4324e35fcded489508","observation_id":"5f805f2b-8114-45fc-9733-87f9dd8099b4","resolution":{"observed_at":"2026-05-23T19:23:22.090290Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.15370/citation-record","integrity":"/paper/2411.15370/integrity","json":"/paper/2411.15370/citation-record.json","paper":"/paper/2411.15370"},"outbound":[],"paper":{"arxiv_id":"2411.15370","last_updated":"2025-05-21T05:30:43Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:55:51.415524Z","submitted_at":"2024-11-22T22:46:21Z","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2411.15370."}