{"as_of":"2026-08-08T11:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:60165e0270ee8a1795c6bb0f51de0c6f1a75901ea2ee90f25bcad08ba92f211b","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:57:46.095320Z","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":"2026-08-07T14:57:46.937870Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.19805","last_updated":"2024-05-28T07:57:57Z","snapshot_observed_at":"2026-07-06T16:40:39.567420Z","submitted_at":"2023-10-07T00:02:05Z","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","version":4},"cited_work":{"arxiv_id":"2310.19805","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.19805","snapshot_observed_at":"2026-08-07T14:57:46.937870Z","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","venue":"cs.LG","work_id":"8fb24d8f-9f33-4c11-a580-7ef587b2552f","year":2023},"citing_paper":{"arxiv_id":"2505.16856","last_updated":"2025-05-22T16:14:08Z","snapshot_observed_at":"2026-08-07T14:51:50.965265Z","submitted_at":"2025-05-22T16:14:08Z","title":"Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:57:46.095320Z"},"links":{"cited_paper":"/paper/2310.19805","citing_paper":"/paper/2505.16856"},"observation_digest":"sha256:0c43ef0d1b010020b7a0752b7823bf05837b36e7e02c4bb09c84d7352616bab3","observation_id":"5e013ce3-a10a-471b-aa15-3e97c64c1a33","resolution":{"observed_at":"2026-08-07T14:57:47.046425Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.19805/citation-record","integrity":"/paper/2310.19805/integrity","json":"/paper/2310.19805/citation-record.json","paper":"/paper/2310.19805"},"outbound":[],"paper":{"arxiv_id":"2310.19805","last_updated":"2024-05-28T07:57:57Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T16:40:39.567420Z","submitted_at":"2023-10-07T00:02:05Z","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration"},"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":"2026-08-08T06:32:00.761636+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 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2310.19805."}