{"as_of":"2026-08-05T11:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5897c00a9f7c7320e82f26e4d5ad0fe38ced04e10aee66ae9113e6e8a5443bd0","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T22:06:24.412259Z","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":"2026-07-03T23:39:03.174419Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.20268","last_updated":"2025-07-24T14:21:12Z","snapshot_observed_at":"2026-07-06T21:30:52.246162Z","submitted_at":"2025-05-26T17:44:08Z","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","version":2},"cited_work":{"arxiv_id":"2505.20268","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20268","snapshot_observed_at":"2026-07-03T23:39:03.174419Z","title":"Differentially private empirical risk minimization","venue":null,"work_id":"758ed8c7-fac4-4a55-a59f-50b4b8da646b","year":2025},"citing_paper":{"arxiv_id":"2510.08539","last_updated":"2026-05-07T17:44:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-09T17:53:41Z","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T08:34:36.543874Z"},"links":{"cited_paper":"/paper/2505.20268","citing_paper":"/paper/2510.08539"},"observation_digest":"sha256:10b53132fef107f876a30f39553f6d389b09e07a417f33dad0ae823c8bb8fafe","observation_id":"0b754f7a-d39b-4cc8-9df6-fcd65096b85b","resolution":{"observed_at":"2026-05-18T08:36:07.276562Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.20268","last_updated":"2025-07-24T14:21:12Z","snapshot_observed_at":"2026-07-06T21:30:52.246162Z","submitted_at":"2025-05-26T17:44:08Z","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","version":2},"cited_work":{"arxiv_id":"2505.20268","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20268","snapshot_observed_at":"2026-07-03T23:39:03.174419Z","title":"Differentially private empirical risk minimization","venue":null,"work_id":"758ed8c7-fac4-4a55-a59f-50b4b8da646b","year":2025},"citing_paper":{"arxiv_id":"2605.07049","last_updated":"2026-05-07T23:58:28Z","snapshot_observed_at":"2026-07-06T23:19:25.538514Z","submitted_at":"2026-05-07T23:58:28Z","title":"Towards Differentially Private Reinforcement Learning with General Function Approximation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-11T01:15:59.533563Z"},"links":{"cited_paper":"/paper/2505.20268","citing_paper":"/paper/2605.07049"},"observation_digest":"sha256:c4c2d910170dea3a4a62fc05562ba019b4dd78a0cf8f6ab97dbd7e3f1e33d60d","observation_id":"c0716695-dd2f-478e-96b2-7f034332ea94","resolution":{"observed_at":"2026-05-11T04:31:00.541325Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.20268","last_updated":"2025-07-24T14:21:12Z","snapshot_observed_at":"2026-07-06T21:30:52.246162Z","submitted_at":"2025-05-26T17:44:08Z","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","version":2},"cited_work":{"arxiv_id":"2505.20268","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20268","snapshot_observed_at":"2026-07-03T23:39:03.174419Z","title":"Differentially private empirical risk minimization","venue":null,"work_id":"758ed8c7-fac4-4a55-a59f-50b4b8da646b","year":2025},"citing_paper":{"arxiv_id":"2606.18531","last_updated":"2026-06-16T22:55:45Z","snapshot_observed_at":"2026-08-04T10:57:17.249083Z","submitted_at":"2026-06-16T22:55:45Z","title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-26T22:06:24.412259Z"},"links":{"cited_paper":"/paper/2505.20268","citing_paper":"/paper/2606.18531"},"observation_digest":"sha256:1b44205e28c4cdeabaa7932125c9177a7ccc5d56fcefbba9bf3104aa9f8528f8","observation_id":"0ca2e471-63fd-473e-96bb-80f75fc32575","resolution":{"observed_at":"2026-07-03T23:39:03.177721Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.20268/citation-record","integrity":"/paper/2505.20268/integrity","json":"/paper/2505.20268/citation-record.json","paper":"/paper/2505.20268"},"outbound":[],"paper":{"arxiv_id":"2505.20268","last_updated":"2025-07-24T14:21:12Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T21:30:52.246162Z","submitted_at":"2025-05-26T17:44:08Z","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2505.20268."}