{"as_of":"2026-08-09T21:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:508fa3e437645089abc65df2d2c477c7e6a38899e1a479a305b1c95978ea71ce","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":"2026-08-09T06:31:02.800959+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":"2026-08-03T03:15:09.845886Z","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":"2026-06-29T08:43:15.331093Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1912.05663","last_updated":"2020-02-12T19:23:15Z","snapshot_observed_at":"2026-07-06T08:43:55.093635Z","submitted_at":"2019-12-10T17:50:33Z","title":"Measuring the Reliability of Reinforcement Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.05663","snapshot_observed_at":"2026-08-03T03:15:09.845886Z","title":null,"venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2602.08690","last_updated":"2026-06-22T11:24:21Z","snapshot_observed_at":"2026-08-06T10:10:44.062711Z","submitted_at":"2026-02-09T14:12:41Z","title":"SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T03:15:09.845886Z"},"links":{"cited_paper":"/paper/1912.05663","citing_paper":"/paper/2602.08690"},"observation_digest":"sha256:240e13b9f845cee816d32d49d08723f47c6b4129345be668211509d5a2fdb77c","observation_id":"339e7f89-55ec-4de5-a959-0e9b60b36113","resolution":{"observed_at":"2026-08-03T03:15:09.845886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.05663","last_updated":"2020-02-12T19:23:15Z","snapshot_observed_at":"2026-07-06T08:43:55.093635Z","submitted_at":"2019-12-10T17:50:33Z","title":"Measuring the Reliability of Reinforcement Learning Algorithms","version":2},"cited_work":{"arxiv_id":"1912.05663","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.05663","snapshot_observed_at":"2026-06-29T08:43:15.331093Z","title":"arXiv preprint arXiv:1912.05663 , year=","venue":null,"work_id":"4e8db670-3056-48e2-aeb0-d3fb80d803a3","year":1912},"citing_paper":{"arxiv_id":"2606.00135","last_updated":"2026-05-28T22:21:47Z","snapshot_observed_at":"2026-07-06T23:40:51.363776Z","submitted_at":"2026-05-28T22:21:47Z","title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-06-29T08:38:52.411671Z"},"links":{"cited_paper":"/paper/1912.05663","citing_paper":"/paper/2606.00135"},"observation_digest":"sha256:b93a8756d6eb01d17a5862e80f44dd893560c0a74e3bd0ba3bc94c5df71ad9c5","observation_id":"018240d6-bb79-4b53-a23e-a436f655a5a6","resolution":{"observed_at":"2026-06-29T08:43:15.332447Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1912.05663/citation-record","integrity":"/paper/1912.05663/integrity","json":"/paper/1912.05663/citation-record.json","paper":"/paper/1912.05663"},"outbound":[],"paper":{"arxiv_id":"1912.05663","last_updated":"2020-02-12T19:23:15Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-07-06T08:43:55.093635Z","submitted_at":"2019-12-10T17:50:33Z","title":"Measuring the Reliability of Reinforcement Learning Algorithms"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1912.05663."}