{"as_of":"2026-08-17T09:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:32949264b791725edb2eed8d1900f37b2dbeaea009c4e287dfd0ef0c43a4d076","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":"2026-08-17T06:30:58.91139+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":"2026-08-15T19:38:50.578945Z","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":"2026-08-06T19:58:57.853797Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.03691","last_updated":"2020-12-03T01:34:00Z","snapshot_observed_at":"2026-08-16T19:15:04.857580Z","submitted_at":"2020-10-07T23:38:47Z","title":"Regularized Inverse Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03691","snapshot_observed_at":"2026-08-15T19:38:50.578945Z","title":"Regularized inverse rein- forcement learning.arXiv preprint arXiv:2010.03691,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.15421","last_updated":"2025-06-18T12:46:39Z","snapshot_observed_at":"2026-08-16T17:35:22.013765Z","submitted_at":"2025-06-18T12:46:39Z","title":"Reward Models in Deep Reinforcement Learning: A Survey","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T19:38:50.578945Z"},"links":{"cited_paper":"/paper/2010.03691","citing_paper":"/paper/2506.15421"},"observation_digest":"sha256:baff6c608a72c0e71027fe38f7ad25e96e639d1c98e9d56a9348e667d67e59f0","observation_id":"f4a188ef-28ba-45b9-b6d5-9f3237367050","resolution":{"observed_at":"2026-08-15T19:38:50.578945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03691","last_updated":"2020-12-03T01:34:00Z","snapshot_observed_at":"2026-08-16T19:15:04.857580Z","submitted_at":"2020-10-07T23:38:47Z","title":"Regularized Inverse Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2010.03691","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.03691","snapshot_observed_at":"2026-08-06T19:58:57.853797Z","title":"Regularized Inverse Reinforcement Learning","venue":"cs.LG","work_id":"35deda01-8245-469a-aae4-dbf09d38892b","year":2020},"citing_paper":{"arxiv_id":"2507.04396","last_updated":"2025-07-06T13:56:02Z","snapshot_observed_at":"2026-08-17T00:48:02.764161Z","submitted_at":"2025-07-06T13:56:02Z","title":"Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic Optimization","version":1},"reference_index":500,"source":"pdf_text","source_observed_at":"2026-08-06T19:58:55.819721Z"},"links":{"cited_paper":"/paper/2010.03691","citing_paper":"/paper/2507.04396"},"observation_digest":"sha256:d779393c6ec07ce996a040a7994f48a46fa7d8038b68b7edded204905b6059e6","observation_id":"32b137b8-f760-406d-919e-53a95a647e76","resolution":{"observed_at":"2026-08-06T19:58:57.919764Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2010.03691/citation-record","integrity":"/paper/2010.03691/integrity","json":"/paper/2010.03691/citation-record.json","paper":"/paper/2010.03691"},"outbound":[],"paper":{"arxiv_id":"2010.03691","last_updated":"2020-12-03T01:34:00Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T19:15:04.857580Z","submitted_at":"2020-10-07T23:38:47Z","title":"Regularized Inverse 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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2010.03691."}