{"as_of":"2026-08-07T11:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:113916fcd2361027049333405f94e823245e4c9623dc8318aefd0494cbcf3b23","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T19:19:29.370866Z","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":"2026-05-15T01:33:27.193926Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.15669","last_updated":"2023-05-25T02:40:32Z","snapshot_observed_at":"2026-08-06T02:09:22.567502Z","submitted_at":"2023-05-25T02:40:32Z","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15669","snapshot_observed_at":"2026-08-06T19:19:29.370866Z","title":"Proto: Iterative policy regularized offline-to-online reinforcement learning.arXiv preprint arXiv:2305.15669, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.06111","last_updated":"2025-07-08T15:51:57Z","snapshot_observed_at":"2026-08-06T19:08:35.359052Z","submitted_at":"2025-07-08T15:51:57Z","title":"Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T19:19:29.370866Z"},"links":{"cited_paper":"/paper/2305.15669","citing_paper":"/paper/2507.06111"},"observation_digest":"sha256:cef1866dc5763fe04d3814ca2da4f88a2543d11b6a30744010323ea69918f6d6","observation_id":"a8f851a0-5087-40e1-879a-1118306b0361","resolution":{"observed_at":"2026-08-06T19:19:29.370866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15669","last_updated":"2023-05-25T02:40:32Z","snapshot_observed_at":"2026-08-06T02:09:22.567502Z","submitted_at":"2023-05-25T02:40:32Z","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15669","snapshot_observed_at":"2026-08-06T18:27:02.388148Z","title":"Proto: Iterative policy regularized offline-to-online reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.08387","last_updated":"2025-07-11T08:00:12Z","snapshot_observed_at":"2026-08-06T18:17:30.456700Z","submitted_at":"2025-07-11T08:00:12Z","title":"Online Pre-Training for Offline-to-Online Reinforcement Learning","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:02.388148Z"},"links":{"cited_paper":"/paper/2305.15669","citing_paper":"/paper/2507.08387"},"observation_digest":"sha256:ceec9b590f779b4a159021c24d5ca997e7f176b0e594457c95679ed71b8711df","observation_id":"a521ed32-5016-4189-875c-5695f1d06c55","resolution":{"observed_at":"2026-08-06T18:27:02.388148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15669","last_updated":"2023-05-25T02:40:32Z","snapshot_observed_at":"2026-08-06T02:09:22.567502Z","submitted_at":"2023-05-25T02:40:32Z","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15669","snapshot_observed_at":"2026-08-04T13:00:07.558566Z","title":"Proto: Iterative policy regularized offline-to-online reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.01460","last_updated":"2026-07-03T20:18:07Z","snapshot_observed_at":"2026-08-06T09:14:15.682614Z","submitted_at":"2025-10-01T20:58:14Z","title":"The Three Regimes of Offline-to-Online Reinforcement Learning","version":4},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T13:00:07.558566Z"},"links":{"cited_paper":"/paper/2305.15669","citing_paper":"/paper/2510.01460"},"observation_digest":"sha256:ff4af210c67152a6c35671898fa77025104daaf43472fa889d47efdc03f63cab","observation_id":"227a11f2-c231-4570-be1f-2d4df3c6b0d4","resolution":{"observed_at":"2026-08-04T13:00:07.558566Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15669","last_updated":"2023-05-25T02:40:32Z","snapshot_observed_at":"2026-08-06T02:09:22.567502Z","submitted_at":"2023-05-25T02:40:32Z","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2305.15669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.15669","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Proto: Iterative policy regularized offline-to-online reinforcement learn- ing.arXiv preprint arXiv:2305.15669","venue":null,"work_id":"5313d2ff-a44b-4d5c-a5cc-3dc3bc00feae","year":2023},"citing_paper":{"arxiv_id":"2605.14497","last_updated":"2026-05-14T07:35:58Z","snapshot_observed_at":"2026-08-01T11:14:55.109730Z","submitted_at":"2026-05-14T07:35:58Z","title":"ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-15T01:32:42.972836Z"},"links":{"cited_paper":"/paper/2305.15669","citing_paper":"/paper/2605.14497"},"observation_digest":"sha256:42a9f624fff3918a4d97a9369677ddfce5f42bae789abc9743e84d7e9f0f23f3","observation_id":"70215d69-c80b-4ef0-b858-61618f8bed27","resolution":{"observed_at":"2026-05-15T01:33:27.196250Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.15669/citation-record","integrity":"/paper/2305.15669/integrity","json":"/paper/2305.15669/citation-record.json","paper":"/paper/2305.15669"},"outbound":[],"paper":{"arxiv_id":"2305.15669","last_updated":"2023-05-25T02:40:32Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T02:09:22.567502Z","submitted_at":"2023-05-25T02:40:32Z","title":"PROTO: Iterative Policy Regularized Offline-to-Online 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2305.15669."}