{"as_of":"2026-08-17T17:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e1cecab6bc6062c00c920202622cacbee436fe83a047e684a163731b09fff3ee","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":"2026-08-16T11:47:06.599283Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.01886","last_updated":"2024-12-13T18:59:14Z","snapshot_observed_at":"2026-08-17T07:37:46.414314Z","submitted_at":"2024-02-02T20:21:09Z","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01886","snapshot_observed_at":"2026-08-16T11:47:06.599283Z","title":"Inverse reinforcement learning by estimating expertise of demonstrators","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.14732","last_updated":"2025-04-25T21:54:56Z","snapshot_observed_at":"2026-08-17T08:01:25.751648Z","submitted_at":"2025-04-20T20:09:19Z","title":"Reinforcement Learning from Multi-level and Episodic Human Feedback","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-16T11:47:06.599283Z"},"links":{"cited_paper":"/paper/2402.01886","citing_paper":"/paper/2504.14732"},"observation_digest":"sha256:ce201c87e0993c922a536182d22db10877e44e54bd728849c62981fce0c16edd","observation_id":"34bfff6d-8e60-41a9-b0fc-719573c10ef4","resolution":{"observed_at":"2026-08-16T11:47:06.599283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01886","last_updated":"2024-12-13T18:59:14Z","snapshot_observed_at":"2026-08-17T07:37:46.414314Z","submitted_at":"2024-02-02T20:21:09Z","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","version":2},"cited_work":{"arxiv_id":"2402.01886","doi":"10.48550/arxiv.2402.01886","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.01886","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"8 Improving Zero-Shot Offline RL via Behavioral Task Sampling Borsa, D., Barreto, A., Quan, J., Mankowitz, D., Munos, R., Van Hasselt, H., Silver, D., and Schaul, T","venue":"arXiv (Cornell University)","work_id":"d967d43e-0b6f-4df0-811d-bb16cb672698","year":null},"citing_paper":{"arxiv_id":"2604.25496","last_updated":"2026-06-24T16:12:26Z","snapshot_observed_at":"2026-08-13T04:23:57.583150Z","submitted_at":"2026-04-28T10:56:54Z","title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-07T16:27:15.347522Z"},"links":{"cited_paper":"/paper/2402.01886","citing_paper":"/paper/2604.25496"},"observation_digest":"sha256:a2b7f2ac220d96585122abb265c4d948b9d8925020d86be381757a260d088593","observation_id":"ee3cb67a-3dfb-49b5-828a-b2b86baed1ca","resolution":{"observed_at":"2026-05-09T01:59:33.992214Z","resolver_source":"arxiv_id","status":"verified_exact"},"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/2402.01886/citation-record","integrity":"/paper/2402.01886/integrity","json":"/paper/2402.01886/citation-record.json","paper":"/paper/2402.01886"},"outbound":[],"paper":{"arxiv_id":"2402.01886","last_updated":"2024-12-13T18:59:14Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T07:37:46.414314Z","submitted_at":"2024-02-02T20:21:09Z","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators"},"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:2402.01886."}