{"as_of":"2026-08-08T12:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:78d2b9bac71d8255e7c1745ff045c658a9d08776e288033bceb2a7d73954d5b4","coverage":[{"denominator":2,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:44:22.002422Z","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":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.01884/citation-record","integrity":"/paper/2506.01884/integrity","json":"/paper/2506.01884/citation-record.json","paper":"/paper/2506.01884"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1910.07113","last_updated":"2019-10-16T00:59:05Z","snapshot_observed_at":"2026-08-02T15:37:37.200292Z","submitted_at":"2019-10-16T00:59:05Z","title":"Solving Rubik's Cube with a Robot Hand","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07113","snapshot_observed_at":"2026-08-07T11:44:21.927377Z","title":"Apprenticeship learning via inverse re- inforcement learning.International Conference on Machine learning, 2004 (cited on page 102)","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.01884","last_updated":"2025-06-02T17:12:24Z","snapshot_observed_at":"2026-08-07T11:29:43.351194Z","submitted_at":"2025-06-02T17:12:24Z","title":"Agnostic Reinforcement Learning: Foundations and Algorithms","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:44:21.927377Z"},"links":{"cited_paper":"/paper/1910.07113","citing_paper":"/paper/2506.01884"},"observation_digest":"sha256:4c1b5b5f0639bd176554d0a2dfba4fc45de6724a468813f1152a3ab07d0f7b60","observation_id":"544a64fd-701c-40a7-90bf-03fa13b96448","resolution":{"observed_at":"2026-08-07T11:44:21.927377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.01962","last_updated":"2023-06-30T13:05:42Z","snapshot_observed_at":"2026-07-06T14:14:06.039306Z","submitted_at":"2022-11-03T16:42:40Z","title":"GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01962","snapshot_observed_at":"2026-08-07T11:44:22.002422Z","title":"Math, 1951 (cited on page 76)","venue":null,"work_id":null,"year":1951},"citing_paper":{"arxiv_id":"2506.01884","last_updated":"2025-06-02T17:12:24Z","snapshot_observed_at":"2026-08-07T11:29:43.351194Z","submitted_at":"2025-06-02T17:12:24Z","title":"Agnostic Reinforcement Learning: Foundations and Algorithms","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-07T11:44:22.002422Z"},"links":{"cited_paper":"/paper/2211.01962","citing_paper":"/paper/2506.01884"},"observation_digest":"sha256:890057a33c9260a8b5300bb5336b951f0f5b96c3263a122f3924780e454c4e05","observation_id":"fd2c9fcb-d3b4-417b-9801-4835d4a943f9","resolution":{"observed_at":"2026-08-07T11:44:22.002422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.01884","last_updated":"2025-06-02T17:12:24Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T11:29:43.351194Z","submitted_at":"2025-06-02T17:12:24Z","title":"Agnostic Reinforcement Learning: Foundations and Algorithms"},"reference_resolution":{"displayed":2,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":2},"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 2 of 2 outbound references and 0 inbound Pith citation observations for arXiv:2506.01884."}