{"as_of":"2026-08-07T04:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e9c0b411bff480f40ac9c317010ccd4c1ed92db62fc60c0e6a5bb592ba041988","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":"2026-08-06T06:34:29.942622+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":"2026-08-02T12:46:51.175897Z","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":"2026-05-19T09:12:14.608636Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.14495","last_updated":"2021-02-26T17:46:32Z","snapshot_observed_at":"2026-08-07T01:08:35.585223Z","submitted_at":"2020-11-30T01:36:16Z","title":"Soft-Robust Algorithms for Batch Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2011.14495","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.14495","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Soft-robust algorithms for batch reinforcement learning","venue":null,"work_id":"87895fd8-d189-461e-88fd-c55d3de3f939","year":2011},"citing_paper":{"arxiv_id":"2506.12622","last_updated":"2026-04-18T21:54:34Z","snapshot_observed_at":"2026-08-02T08:28:01.941809Z","submitted_at":"2025-06-14T20:36:44Z","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-19T09:09:51.531488Z"},"links":{"cited_paper":"/paper/2011.14495","citing_paper":"/paper/2506.12622"},"observation_digest":"sha256:8db2aa67e4161f5bcd5d0ff454ed84b778d00e251da89480c15e3ca4112194c6","observation_id":"d4e6827d-a3cc-4eaa-86fe-4520e71c50b6","resolution":{"observed_at":"2026-05-19T09:12:14.614226Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.14495","last_updated":"2021-02-26T17:46:32Z","snapshot_observed_at":"2026-08-07T01:08:35.585223Z","submitted_at":"2020-11-30T01:36:16Z","title":"Soft-Robust Algorithms for Batch Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.14495","snapshot_observed_at":"2026-08-02T12:46:51.175897Z","title":"Lu, C., Ball, P., Parker-Holder, J., Osborne, M., and Roberts, S","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.00680","last_updated":"2026-07-18T12:28:58Z","snapshot_observed_at":"2026-08-06T11:06:16.331413Z","submitted_at":"2026-05-30T11:35:26Z","title":"Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T12:46:51.175897Z"},"links":{"cited_paper":"/paper/2011.14495","citing_paper":"/paper/2606.00680"},"observation_digest":"sha256:1f24730327e491edc6925a8d7e617f977167a4e9a3b486bf52f0b4a4e5d4096a","observation_id":"3c5fce21-f63a-4560-a4aa-de5af12edb14","resolution":{"observed_at":"2026-08-02T12:46:51.175897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2011.14495/citation-record","integrity":"/paper/2011.14495/integrity","json":"/paper/2011.14495/citation-record.json","paper":"/paper/2011.14495"},"outbound":[],"paper":{"arxiv_id":"2011.14495","last_updated":"2021-02-26T17:46:32Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T01:08:35.585223Z","submitted_at":"2020-11-30T01:36:16Z","title":"Soft-Robust Algorithms for Batch 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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2011.14495."}