{"as_of":"2026-08-19T20:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fb322bb02f7c25b8629945c5fb94104a3475ab2bdf6539a657a5bdfa8469a04b","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":"2026-08-19T06:32:44.657259+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":"2026-08-06T17:42:55.493100Z","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":"2026-05-24T01:25:54.660821Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1910.12802","last_updated":"2021-10-13T17:57:21Z","snapshot_observed_at":"2026-08-18T21:59:55.444720Z","submitted_at":"2019-10-28T16:56:46Z","title":"Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning","version":2},"cited_work":{"arxiv_id":"1910.12802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1910.12802","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bertsekas, Dimitri, and Steven E Shreve, 1996,Stochastic optimal control: the discrete-time case, volume 5 (Athena Scientific)","venue":null,"work_id":"b08d4bf1-c50d-4f16-90e9-861f588e0602","year":1966},"citing_paper":{"arxiv_id":"2405.03888","last_updated":"2026-04-08T01:30:05Z","snapshot_observed_at":"2026-07-06T18:10:41.264712Z","submitted_at":"2024-05-06T22:23:31Z","title":"Measurized Markov Decision Processes","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-24T01:24:31.679805Z"},"links":{"cited_paper":"/paper/1910.12802","citing_paper":"/paper/2405.03888"},"observation_digest":"sha256:3281fa5ccadbfea6324886c03005f43bfa1c029536bf77e4ad20e8be53fa4dfe","observation_id":"733741c2-1f5f-48fe-af66-7366a38459ce","resolution":{"observed_at":"2026-05-24T01:25:54.663266Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.12802","last_updated":"2021-10-13T17:57:21Z","snapshot_observed_at":"2026-08-18T21:59:55.444720Z","submitted_at":"2019-10-28T16:56:46Z","title":"Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.12802","snapshot_observed_at":"2026-08-06T17:42:55.493100Z","title":"Model-free mean-field reinforcement learning: mean-field MDP and mean-field Q-learning.arXiv:1910.12802, 2019","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2507.10142","last_updated":"2026-07-22T04:23:01Z","snapshot_observed_at":"2026-08-15T17:28:57.910671Z","submitted_at":"2025-07-14T10:39:17Z","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.493100Z"},"links":{"cited_paper":"/paper/1910.12802","citing_paper":"/paper/2507.10142"},"observation_digest":"sha256:a7c7a289a67a505649f873118304c56765531a8e28ad0af5caea336ea1c0665a","observation_id":"cf61d131-fffc-4ce6-9570-c4ede11667d5","resolution":{"observed_at":"2026-08-06T17:42:55.493100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1910.12802/citation-record","integrity":"/paper/1910.12802/integrity","json":"/paper/1910.12802/citation-record.json","paper":"/paper/1910.12802"},"outbound":[],"paper":{"arxiv_id":"1910.12802","last_updated":"2021-10-13T17:57:21Z","latest_version":2,"primary_category":"math.OC","snapshot_observed_at":"2026-08-18T21:59:55.444720Z","submitted_at":"2019-10-28T16:56:46Z","title":"Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1910.12802."}