{"as_of":"2026-08-17T02:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8c37cccd0b370e39f7f71c139752433f2131f97bad1546a02980ec2f3c0b962b","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T11:22:28.826130Z","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":"2026-07-04T07:59:40.610458Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2208.07914","last_updated":"2023-05-29T19:29:13Z","snapshot_observed_at":"2026-08-16T16:38:50.673375Z","submitted_at":"2022-08-16T19:23:02Z","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.07914","snapshot_observed_at":"2026-08-09T11:22:28.826130Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02743","last_updated":"2025-02-04T22:09:43Z","snapshot_observed_at":"2026-08-14T11:59:50.011836Z","submitted_at":"2025-02-04T22:09:43Z","title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T11:22:28.826130Z"},"links":{"cited_paper":"/paper/2208.07914","citing_paper":"/paper/2502.02743"},"observation_digest":"sha256:f3efb4f782765e20cef0561ed2d7647844e96ab5b9ad1729b8ab336c26e7c34a","observation_id":"f57a25b6-fd3f-4e7a-b931-8f65302520c6","resolution":{"observed_at":"2026-08-09T11:22:28.826130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.07914","last_updated":"2023-05-29T19:29:13Z","snapshot_observed_at":"2026-08-16T16:38:50.673375Z","submitted_at":"2022-08-16T19:23:02Z","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","version":3},"cited_work":{"arxiv_id":"2208.07914","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.07914","snapshot_observed_at":"2026-07-04T07:59:40.610458Z","title":"Pd-morl: Preference-driven multi- objective reinforcement learning algorithm","venue":null,"work_id":"17ef4c2b-211b-4184-8870-06e9814b5ab3","year":2022},"citing_paper":{"arxiv_id":"2605.08946","last_updated":"2026-05-09T13:35:50Z","snapshot_observed_at":"2026-07-06T23:21:06.773761Z","submitted_at":"2026-05-09T13:35:50Z","title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-12T02:21:30.413575Z"},"links":{"cited_paper":"/paper/2208.07914","citing_paper":"/paper/2605.08946"},"observation_digest":"sha256:bbd287d016c0945af03845da40b8007123626cde05b8f97b07fe5c4749983b14","observation_id":"52f95e38-7c22-4f83-85bf-7b7d08fbb034","resolution":{"observed_at":"2026-05-12T07:41:41.806542Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.07914","last_updated":"2023-05-29T19:29:13Z","snapshot_observed_at":"2026-08-16T16:38:50.673375Z","submitted_at":"2022-08-16T19:23:02Z","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","version":3},"cited_work":{"arxiv_id":"2208.07914","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.07914","snapshot_observed_at":"2026-07-04T07:59:40.610458Z","title":"Pd-morl: Preference-driven multi- objective reinforcement learning algorithm","venue":null,"work_id":"17ef4c2b-211b-4184-8870-06e9814b5ab3","year":2022},"citing_paper":{"arxiv_id":"2606.21943","last_updated":"2026-06-20T08:20:41Z","snapshot_observed_at":"2026-08-15T21:55:25.625601Z","submitted_at":"2026-06-20T08:20:41Z","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T12:15:08.304150Z"},"links":{"cited_paper":"/paper/2208.07914","citing_paper":"/paper/2606.21943"},"observation_digest":"sha256:208ed7d7751c9e05407b627c807f51480dfe8af3f45a45cb06c4872ea5eb0872","observation_id":"21d65909-4359-483c-8c95-c234f0721b3c","resolution":{"observed_at":"2026-07-04T07:59:40.611967Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2208.07914/citation-record","integrity":"/paper/2208.07914/integrity","json":"/paper/2208.07914/citation-record.json","paper":"/paper/2208.07914"},"outbound":[],"paper":{"arxiv_id":"2208.07914","last_updated":"2023-05-29T19:29:13Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T16:38:50.673375Z","submitted_at":"2022-08-16T19:23:02Z","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2208.07914."}