{"as_of":"2026-08-08T15:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:967f9afeaf07b860a63e2609fa43f4c8bd1b17f48b718a6d7e35fb2eb5be8eb8","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":"2026-08-08T06:32:00.761636+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":"2026-08-08T06:03:45.594050Z","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":"2026-08-05T21:34:31.000857Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.10282","last_updated":"2023-05-17T15:17:23Z","snapshot_observed_at":"2026-07-06T15:28:44.711559Z","submitted_at":"2023-05-17T15:17:23Z","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10282","snapshot_observed_at":"2026-08-08T06:03:45.594050Z","title":"D., Chi, Y., and Chen, Y","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08259","last_updated":"2025-03-10T16:30:27Z","snapshot_observed_at":"2026-08-08T05:45:31.100040Z","submitted_at":"2025-02-12T10:05:25Z","title":"Balancing optimism and pessimism in offline-to-online learning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T06:03:45.594050Z"},"links":{"cited_paper":"/paper/2305.10282","citing_paper":"/paper/2502.08259"},"observation_digest":"sha256:2a6a9867e9c4304f3bae19d08fbf5dee5bd5df3167df9f7f816c9a736bb9d420","observation_id":"ad6cfff7-faae-4f86-a40c-86a473a6e2cf","resolution":{"observed_at":"2026-08-08T06:03:45.594050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10282","last_updated":"2023-05-17T15:17:23Z","snapshot_observed_at":"2026-07-06T15:28:44.711559Z","submitted_at":"2023-05-17T15:17:23Z","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2305.10282","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.10282","snapshot_observed_at":"2026-08-05T21:34:31.000857Z","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","venue":"cs.LG","work_id":"e072ba2e-8f25-4710-8584-b026d92f8d7d","year":2023},"citing_paper":{"arxiv_id":"2508.08413","last_updated":"2025-08-11T19:07:30Z","snapshot_observed_at":"2026-08-07T12:16:45.804784Z","submitted_at":"2025-08-11T19:07:30Z","title":"Decentralized Relaxed Smooth Optimization with Gradient Descent Methods","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-05T21:34:29.418727Z"},"links":{"cited_paper":"/paper/2305.10282","citing_paper":"/paper/2508.08413"},"observation_digest":"sha256:a1802701cb6a359768227958dd92f82db2c37a416ddf6d349f0c19f9ecdb02f1","observation_id":"412ddb58-3fe5-4cfd-84a0-dfdd76f85eca","resolution":{"observed_at":"2026-08-05T21:34:31.049836Z","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/2305.10282/citation-record","integrity":"/paper/2305.10282/integrity","json":"/paper/2305.10282/citation-record.json","paper":"/paper/2305.10282"},"outbound":[],"paper":{"arxiv_id":"2305.10282","last_updated":"2023-05-17T15:17:23Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T15:28:44.711559Z","submitted_at":"2023-05-17T15:17:23Z","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement 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":"2026-08-08T06:32:00.761636+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 2 inbound Pith citation observations for arXiv:2305.10282."}