{"as_of":"2026-08-18T01:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f52d92d24e9e329f15235e079e3e09b73d3d246c42b7128a0fa1a7aef3e3581a","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T10:59:58.956067Z","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":"2026-08-10T20:53:52.919258Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.06286","last_updated":"2022-06-08T05:25:37Z","snapshot_observed_at":"2026-08-16T18:52:02.204173Z","submitted_at":"2021-01-15T19:42:10Z","title":"Reinforcement learning based recommender systems: A survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06286","snapshot_observed_at":"2026-08-14T10:59:58.956067Z","title":", Crump, T","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"1909.01095","last_updated":"2022-11-20T08:08:58Z","snapshot_observed_at":"2026-08-17T00:00:39.611975Z","submitted_at":"2019-08-26T20:54:42Z","title":"Defining the scope of AI regulations","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-14T10:59:58.956067Z"},"links":{"cited_paper":"/paper/2101.06286","citing_paper":"/paper/1909.01095"},"observation_digest":"sha256:4909d5c138c32855a2b86d820f47e44dda44e5c66ece16a1382d40a55d946cab","observation_id":"a8d1d33a-5783-4593-8cd7-18365ef7bf59","resolution":{"observed_at":"2026-08-14T10:59:58.956067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06286","last_updated":"2022-06-08T05:25:37Z","snapshot_observed_at":"2026-08-16T18:52:02.204173Z","submitted_at":"2021-01-15T19:42:10Z","title":"Reinforcement learning based recommender systems: A survey","version":2},"cited_work":{"arxiv_id":"2101.06286","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.06286","snapshot_observed_at":"2026-08-10T20:53:52.919258Z","title":"Reinforcement learning based recommender systems: A survey","venue":"cs.IR","work_id":"5c8e3a46-06de-4514-b77b-1ac3943a8d8d","year":2021},"citing_paper":{"arxiv_id":"2501.07085","last_updated":"2025-01-13T06:40:40Z","snapshot_observed_at":"2026-08-18T01:42:19.888484Z","submitted_at":"2025-01-13T06:40:40Z","title":"PPO-Q: Proximal Policy Optimization with Parametrized Quantum Policies or Values","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T20:53:52.493475Z"},"links":{"cited_paper":"/paper/2101.06286","citing_paper":"/paper/2501.07085"},"observation_digest":"sha256:efc4c1aa03e682c2263c1719fb0307f8f8ea2f2e33e2bf99c03bedb1d1fb60d7","observation_id":"dd206164-e838-44c0-9098-f5c9d1487860","resolution":{"observed_at":"2026-08-10T20:53:52.924344Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06286","last_updated":"2022-06-08T05:25:37Z","snapshot_observed_at":"2026-08-16T18:52:02.204173Z","submitted_at":"2021-01-15T19:42:10Z","title":"Reinforcement learning based recommender systems: A survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06286","snapshot_observed_at":"2026-08-03T01:15:20.483852Z","title":"Mehdi Afsar, Trafford Crump, and Behrouz Far","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.10226","last_updated":"2026-08-02T17:44:50Z","snapshot_observed_at":"2026-08-16T10:58:10.810652Z","submitted_at":"2026-02-10T19:16:52Z","title":"Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T01:15:20.483852Z"},"links":{"cited_paper":"/paper/2101.06286","citing_paper":"/paper/2602.10226"},"observation_digest":"sha256:866830760abddc6bc3832b200d8083d09e95faeca4d79818f31ecc75890aff6c","observation_id":"dffe9ec5-9c19-4606-b88d-44e1e21dd763","resolution":{"observed_at":"2026-08-03T01:15:20.483852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06286","last_updated":"2022-06-08T05:25:37Z","snapshot_observed_at":"2026-08-16T18:52:02.204173Z","submitted_at":"2021-01-15T19:42:10Z","title":"Reinforcement learning based recommender systems: A survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06286","snapshot_observed_at":"2026-08-04T06:05:26.795335Z","title":"Mehdi Afsar, Trafford Crump, and Behrouz Far","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.10226","last_updated":"2026-08-02T17:44:50Z","snapshot_observed_at":"2026-08-16T10:58:10.810652Z","submitted_at":"2026-02-10T19:16:52Z","title":"Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T06:05:26.795335Z"},"links":{"cited_paper":"/paper/2101.06286","citing_paper":"/paper/2602.10226"},"observation_digest":"sha256:7a77d789012e939f95d5f66b885a7622d45637c0ed615302514f0eadc3c5e565","observation_id":"2796e22b-1eae-4c27-b982-16717a5d4534","resolution":{"observed_at":"2026-08-04T06:05:26.795335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2101.06286/citation-record","integrity":"/paper/2101.06286/integrity","json":"/paper/2101.06286/citation-record.json","paper":"/paper/2101.06286"},"outbound":[],"paper":{"arxiv_id":"2101.06286","last_updated":"2022-06-08T05:25:37Z","latest_version":2,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-16T18:52:02.204173Z","submitted_at":"2021-01-15T19:42:10Z","title":"Reinforcement learning based recommender systems: A survey"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2101.06286."}