{"as_of":"2026-08-11T21:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a410f18b582afc600a063b538c9bf6a5484ca17b6b75b90b03ac5b431f4c82b2","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":"2026-08-11T06:34:44.6726+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":"2026-08-06T22:18:41.211864Z","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":"2026-05-13T06:24:49.979840Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.13885","last_updated":"2020-11-27T18:20:04Z","snapshot_observed_at":"2026-07-06T10:18:28.593525Z","submitted_at":"2020-11-27T18:20:04Z","title":"Offline Learning from Demonstrations and Unlabeled Experience","version":1},"cited_work":{"arxiv_id":"2011.13885","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.13885","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Offline learning from demonstrations and unlabeled experience","venue":null,"work_id":"f8eef9af-f938-4960-9699-6a02bb580494","year":2011},"citing_paper":{"arxiv_id":"2205.06175","last_updated":"2022-11-11T10:04:29Z","snapshot_observed_at":"2026-08-08T03:18:33.595658Z","submitted_at":"2022-05-12T16:03:26Z","title":"A Generalist Agent","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-13T06:24:49.833638Z"},"links":{"cited_paper":"/paper/2011.13885","citing_paper":"/paper/2205.06175"},"observation_digest":"sha256:fa4b7aa79072f5eef4c254b500c305e86d7dc7fe0e3140eb121faffbe4671612","observation_id":"05c8439d-3bf9-4116-9dd3-d9e99c199736","resolution":{"observed_at":"2026-05-13T06:24:49.981311Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13885","last_updated":"2020-11-27T18:20:04Z","snapshot_observed_at":"2026-07-06T10:18:28.593525Z","submitted_at":"2020-11-27T18:20:04Z","title":"Offline Learning from Demonstrations and Unlabeled Experience","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13885","snapshot_observed_at":"2026-08-06T22:18:41.211864Z","title":"Offline learning from demonstrations and unlabeled experience","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.22008","last_updated":"2025-06-27T08:22:41Z","snapshot_observed_at":"2026-08-10T10:25:56.721930Z","submitted_at":"2025-06-27T08:22:41Z","title":"TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:18:41.211864Z"},"links":{"cited_paper":"/paper/2011.13885","citing_paper":"/paper/2506.22008"},"observation_digest":"sha256:35eda3fd87886ecd8947208b91937ae9edd81f7723e21403375ef4f7929b5bdb","observation_id":"bfbfab27-e9ab-46be-8d03-b18b17121187","resolution":{"observed_at":"2026-08-06T22:18:41.211864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13885","last_updated":"2020-11-27T18:20:04Z","snapshot_observed_at":"2026-07-06T10:18:28.593525Z","submitted_at":"2020-11-27T18:20:04Z","title":"Offline Learning from Demonstrations and Unlabeled Experience","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13885","snapshot_observed_at":"2026-08-06T19:06:06.902037Z","title":"Zolna, K., Novikov, A., Konyushkova, K., Gulcehre, C., Wang, Z., Aytar, Y ., Denil, M., de Freitas, N., and Reed, S","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.06701","last_updated":"2025-07-09T09:55:23Z","snapshot_observed_at":"2026-08-11T00:52:31.795477Z","submitted_at":"2025-07-09T09:55:23Z","title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:06:06.902037Z"},"links":{"cited_paper":"/paper/2011.13885","citing_paper":"/paper/2507.06701"},"observation_digest":"sha256:b25f16cce94de77f0d8e5a85097eec4b249cf34d35b125df41a61b3263826581","observation_id":"99c2d47e-7fff-4ee7-b1fd-7501c86f79c6","resolution":{"observed_at":"2026-08-06T19:06:06.902037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13885","last_updated":"2020-11-27T18:20:04Z","snapshot_observed_at":"2026-07-06T10:18:28.593525Z","submitted_at":"2020-11-27T18:20:04Z","title":"Offline Learning from Demonstrations and Unlabeled Experience","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13885","snapshot_observed_at":"2026-08-02T03:34:07.409979Z","title":"Offline learning from demonstrations and unlabeled experience.arXiv preprint arXiv:2011.13885,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.14180","last_updated":"2026-07-15T14:03:45Z","snapshot_observed_at":"2026-08-10T15:26:06.679153Z","submitted_at":"2026-07-15T14:03:45Z","title":"RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T03:34:07.409979Z"},"links":{"cited_paper":"/paper/2011.13885","citing_paper":"/paper/2607.14180"},"observation_digest":"sha256:47e4473b951898c997380218f3c81b4b58ac93cf0eefc5e3d09ac02b29bc4761","observation_id":"c23ed939-7c91-4a28-bad8-be69926009aa","resolution":{"observed_at":"2026-08-02T03:34:07.409979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2011.13885/citation-record","integrity":"/paper/2011.13885/integrity","json":"/paper/2011.13885/citation-record.json","paper":"/paper/2011.13885"},"outbound":[],"paper":{"arxiv_id":"2011.13885","last_updated":"2020-11-27T18:20:04Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:18:28.593525Z","submitted_at":"2020-11-27T18:20:04Z","title":"Offline Learning from Demonstrations and Unlabeled Experience"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2011.13885."}