{"as_of":"2026-08-13T21:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d3762d5421096716329d48756511537280d7f97793242e11b303189198494e69","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T10:52:50.950100Z","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":"2026-08-12T10:52:51.606925Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1910.03732","last_updated":"2019-10-09T00:45:53Z","snapshot_observed_at":"2026-08-13T07:21:34.908078Z","submitted_at":"2019-10-09T00:45:53Z","title":"Ctrl-Z: Recovering from Instability in Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"1910.03732","doi":null,"metadata_source":"pith","pith_arxiv_id":"1910.03732","snapshot_observed_at":"2026-08-12T10:52:51.606925Z","title":"Ctrl-Z: Recovering from Instability in Reinforcement Learning","venue":"cs.LG","work_id":"064558ea-7e6e-400b-9887-f56cb2e9d90f","year":2019},"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":8,"source":"pdf_text","source_observed_at":"2026-08-12T10:52:50.950100Z"},"links":{"cited_paper":"/paper/1910.03732","citing_paper":"/paper/2412.10381"},"observation_digest":"sha256:03e0a62b6319dcda8de8e7b99ccf25f323db5f529e639181b59d3b87f84e5bda","observation_id":"a9908d34-5b8a-4ceb-b493-7461b271111a","resolution":{"observed_at":"2026-08-12T10:52:51.616774Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/1910.03732/citation-record","integrity":"/paper/1910.03732/integrity","json":"/paper/1910.03732/citation-record.json","paper":"/paper/1910.03732"},"outbound":[],"paper":{"arxiv_id":"1910.03732","last_updated":"2019-10-09T00:45:53Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T07:21:34.908078Z","submitted_at":"2019-10-09T00:45:53Z","title":"Ctrl-Z: Recovering from Instability in 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 1 inbound Pith citation observation for arXiv:1910.03732."}