{"as_of":"2026-08-22T07:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee18cc5af22b7d7c56aa4baef779d9c152b08b33e485e401c64889ef59bc2dfd","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":"2026-08-22T06:32:14.747728+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":"2026-08-12T18:52:13.984040Z","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":"2026-05-17T01:48:51.136385Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.12628","last_updated":"2021-10-25T04:08:57Z","snapshot_observed_at":"2026-08-16T17:46:55.921295Z","submitted_at":"2021-10-25T04:08:57Z","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.12628","snapshot_observed_at":"2026-08-12T18:52:13.984040Z","title":"Recurrent off-policy baselines for memory-based continuous control","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11188","last_updated":"2024-11-17T22:25:40Z","snapshot_observed_at":"2026-08-16T21:34:59.593098Z","submitted_at":"2024-11-17T22:25:40Z","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T18:52:13.984040Z"},"links":{"cited_paper":"/paper/2110.12628","citing_paper":"/paper/2411.11188"},"observation_digest":"sha256:bcc4fa42c50c48195265c9cc6f7762c0276892256e7900f4cdd1526d93e150cf","observation_id":"d7419ac3-2b53-4f01-a6f7-f0be2b0c8c3c","resolution":{"observed_at":"2026-08-12T18:52:13.984040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.12628","last_updated":"2021-10-25T04:08:57Z","snapshot_observed_at":"2026-08-16T17:46:55.921295Z","submitted_at":"2021-10-25T04:08:57Z","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","version":1},"cited_work":{"arxiv_id":"2110.12628","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.12628","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"soft robustness","venue":null,"work_id":"a0d02205-44de-4da0-9cf7-11520a69c7e0","year":2021},"citing_paper":{"arxiv_id":"2512.04341","last_updated":"2026-05-01T06:11:28Z","snapshot_observed_at":"2026-08-12T14:29:14.504650Z","submitted_at":"2025-12-04T00:07:08Z","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-17T01:46:16.923948Z"},"links":{"cited_paper":"/paper/2110.12628","citing_paper":"/paper/2512.04341"},"observation_digest":"sha256:08dee890fb5922b12030610901848bcb91ea96235ec62af4b1d7f7318ccf01db","observation_id":"68139ad2-0ff2-46b6-827f-412081389f03","resolution":{"observed_at":"2026-05-17T01:48:51.138610Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.12628/citation-record","integrity":"/paper/2110.12628/integrity","json":"/paper/2110.12628/citation-record.json","paper":"/paper/2110.12628"},"outbound":[],"paper":{"arxiv_id":"2110.12628","last_updated":"2021-10-25T04:08:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T17:46:55.921295Z","submitted_at":"2021-10-25T04:08:57Z","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2110.12628."}