{"as_of":"2026-08-12T04:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0637d6f216ce8d0657d124b7d0862ddeed8f558ffac259c558a40da8bc4d36ff","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":"2026-08-11T06:34:44.6726+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":"2026-08-03T04:39:32.043122Z","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":"2026-07-12T16:08:56.612640Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2210.05639","last_updated":"2022-10-13T02:57:26Z","snapshot_observed_at":"2026-08-10T18:39:27.987980Z","submitted_at":"2022-10-11T17:32:11Z","title":"Discovered Policy Optimisation","version":2},"cited_work":{"arxiv_id":"2210.05639","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.05639","snapshot_observed_at":"2026-07-12T16:08:56.612640Z","title":"Discovered Policy Optimisation","venue":"cs.LG","work_id":"a7180249-7b8c-4466-bede-7d3a923cc863","year":2022},"citing_paper":{"arxiv_id":"2605.26012","last_updated":"2026-07-05T10:46:04Z","snapshot_observed_at":"2026-07-12T15:59:30.399361Z","submitted_at":"2026-05-25T16:31:33Z","title":"Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T15:59:38.060900Z"},"links":{"cited_paper":"/paper/2210.05639","citing_paper":"/paper/2605.26012"},"observation_digest":"sha256:c3df95f68f1f4466a79e9dd87365c1f4b502d10999c0accc10b35755e9463f16","observation_id":"32711b8f-26da-4763-9f72-9e998b7bbf33","resolution":{"observed_at":"2026-07-12T16:08:56.615108Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.05639","last_updated":"2022-10-13T02:57:26Z","snapshot_observed_at":"2026-08-10T18:39:27.987980Z","submitted_at":"2022-10-11T17:32:11Z","title":"Discovered Policy Optimisation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.05639","snapshot_observed_at":"2026-08-03T04:39:32.043122Z","title":"Discovered","venue":null,"work_id":null,"year":null},"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":220,"source":"arxiv_source","source_observed_at":"2026-08-03T04:39:32.043122Z"},"links":{"cited_paper":"/paper/2210.05639","citing_paper":"/paper/2607.29559"},"observation_digest":"sha256:e73f30eb6b144e90f0eebb71c2449caf0eb6de223134dbe7f45e19d5176fa870","observation_id":"751073d9-931d-4729-90ca-4845ccf9647a","resolution":{"observed_at":"2026-08-03T04:39:32.043122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2210.05639/citation-record","integrity":"/paper/2210.05639/integrity","json":"/paper/2210.05639/citation-record.json","paper":"/paper/2210.05639"},"outbound":[],"paper":{"arxiv_id":"2210.05639","last_updated":"2022-10-13T02:57:26Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T18:39:27.987980Z","submitted_at":"2022-10-11T17:32:11Z","title":"Discovered 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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2210.05639."}