{"as_of":"2026-08-18T14:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:753d433adaf394b6eba503cd3fe99b5cb9b8ec43609a2bd44d649d15bb269c08","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T18:15:15.593768Z","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":"2026-05-18T01:46:18.576711Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.04833","last_updated":"2020-12-11T17:56:03Z","snapshot_observed_at":"2026-08-18T08:14:40.541952Z","submitted_at":"2020-02-12T08:07:49Z","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","version":4},"cited_work":{"arxiv_id":"2002.04833","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.04833","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"92046c3c-72df-42e7-9e74-77de96c74188","year":2002},"citing_paper":{"arxiv_id":"2009.01325","last_updated":"2022-02-15T19:09:36Z","snapshot_observed_at":"2026-08-17T15:45:31.564132Z","submitted_at":"2020-09-02T19:54:41Z","title":"Learning to summarize from human feedback","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-18T01:46:18.486086Z"},"links":{"cited_paper":"/paper/2002.04833","citing_paper":"/paper/2009.01325"},"observation_digest":"sha256:3f6815a1430644107d8d5ef4706c325822c53c04525995a32092e33fbc85f20a","observation_id":"6673824c-992b-4fab-bd7d-6a5e75e847cf","resolution":{"observed_at":"2026-05-18T01:46:18.579394Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.04833","last_updated":"2020-12-11T17:56:03Z","snapshot_observed_at":"2026-08-18T08:14:40.541952Z","submitted_at":"2020-02-12T08:07:49Z","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.04833","snapshot_observed_at":"2026-08-12T18:15:15.593768Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.11761","last_updated":"2025-02-20T16:22:19Z","snapshot_observed_at":"2026-08-15T08:34:22.985905Z","submitted_at":"2024-11-18T17:40:42Z","title":"Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T18:15:15.593768Z"},"links":{"cited_paper":"/paper/2002.04833","citing_paper":"/paper/2411.11761"},"observation_digest":"sha256:47e29378b477077b5b06b94ecb4867ed33c2fe04884f063cf5b44aae1a7e68cc","observation_id":"460235c7-d02d-4c01-b567-90d8451b4c7d","resolution":{"observed_at":"2026-08-12T18:15:15.593768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.04833","last_updated":"2020-12-11T17:56:03Z","snapshot_observed_at":"2026-08-18T08:14:40.541952Z","submitted_at":"2020-02-12T08:07:49Z","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.04833","snapshot_observed_at":"2026-08-02T22:59:36.591876Z","title":"arXiv:2002.04833 [cs]","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2602.15206","last_updated":"2026-06-19T10:51:45Z","snapshot_observed_at":"2026-08-02T22:59:34.197898Z","submitted_at":"2026-02-16T21:36:28Z","title":"MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T22:59:36.591876Z"},"links":{"cited_paper":"/paper/2002.04833","citing_paper":"/paper/2602.15206"},"observation_digest":"sha256:980cbd47b2d14b182d56c159b35f0cdcdd8338ed6c7ea03361a761f030dc283b","observation_id":"61f29625-6a8f-4974-87b8-5875edba4c1e","resolution":{"observed_at":"2026-08-02T22:59:36.591876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2002.04833/citation-record","integrity":"/paper/2002.04833/integrity","json":"/paper/2002.04833/citation-record.json","paper":"/paper/2002.04833"},"outbound":[],"paper":{"arxiv_id":"2002.04833","last_updated":"2020-12-11T17:56:03Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T08:14:40.541952Z","submitted_at":"2020-02-12T08:07:49Z","title":"Reward-rational (implicit) choice: A unifying formalism for reward 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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2002.04833."}