{"as_of":"2026-08-08T17:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:081d502910eced3bab773cf93c9ea2c62c11f77c51ce8d6f8cc888944573296e","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T14:48:47.878994Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":6,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2201.02373","last_updated":"2024-11-19T22:08:01Z","snapshot_observed_at":"2026-07-06T12:25:23.259452Z","submitted_at":"2022-01-07T09:16:03Z","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.02373","snapshot_observed_at":"2026-08-06T14:48:47.878994Z","title":"Mirror Learning : A Unifying Framework of Policy Optimisation , November 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17668","last_updated":"2025-09-10T12:25:27Z","snapshot_observed_at":"2026-08-08T15:32:47.481175Z","submitted_at":"2025-07-23T16:31:38Z","title":"How Should We Meta-Learn Reinforcement Learning Algorithms?","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T14:48:47.878994Z"},"links":{"cited_paper":"/paper/2201.02373","citing_paper":"/paper/2507.17668"},"observation_digest":"sha256:1626841a4f5c2a4dc98f88162da30b769e5f3a04467ac0aeee5bc0660bc5c271","observation_id":"2517e4d0-afda-4d88-927b-a6d3a685f536","resolution":{"observed_at":"2026-08-06T14:48:47.878994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.02373","last_updated":"2024-11-19T22:08:01Z","snapshot_observed_at":"2026-07-06T12:25:23.259452Z","submitted_at":"2022-01-07T09:16:03Z","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","version":11},"cited_work":{"arxiv_id":"2201.02373","doi":"10.48550/arxiv.2201.02373","metadata_source":"pith","pith_arxiv_id":"2201.02373","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","venue":"cs.LG","work_id":"2232a6f2-eed5-4db3-b940-8507624115a6","year":2022},"citing_paper":{"arxiv_id":"2607.29559","last_updated":"2026-07-31T15:50:29Z","snapshot_observed_at":"2026-08-07T18:56:05.725689Z","submitted_at":"2026-07-31T15:50:29Z","title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","version":1},"reference_index":221,"source":"arxiv_source","source_observed_at":"2026-08-03T04:39:32.046971Z"},"links":{"cited_paper":"/paper/2201.02373","citing_paper":"/paper/2607.29559"},"observation_digest":"sha256:bb7c7109bcc2ef5054af859c1513802b4f8a96ba7ca36b09f6fbc33feb0833a6","observation_id":"c7d9ea37-0998-4071-87ac-d849cf0e21e8","resolution":{"observed_at":"2026-08-03T04:44:19.563649Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2201.02373/citation-record","integrity":"/paper/2201.02373/integrity","json":"/paper/2201.02373/citation-record.json","paper":"/paper/2201.02373"},"outbound":[],"paper":{"arxiv_id":"2201.02373","last_updated":"2024-11-19T22:08:01Z","latest_version":11,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T12:25:23.259452Z","submitted_at":"2022-01-07T09:16:03Z","title":"Mirror Learning: A Unifying Framework of Policy Optimisation"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2201.02373."}