{"as_of":"2026-08-18T04:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fa0bbc91591fb7a415c06eac28b9330c4ef35dc6b7da5560bfe4e8f808013a39","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":"2026-08-12T18:15:15.535401Z","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":"2026-05-24T05:56:01.720626Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.07691","last_updated":"2021-01-19T15:35:30Z","snapshot_observed_at":"2026-08-16T18:51:21.995349Z","submitted_at":"2021-01-19T15:35:30Z","title":"Choice Set Misspecification in Reward Inference","version":1},"cited_work":{"arxiv_id":"2101.07691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.07691","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Choice set misspecification in reward inference","venue":null,"work_id":"0ded04cb-488b-4df6-a686-99884b7b10ec","year":null},"citing_paper":{"arxiv_id":"2310.15288","last_updated":"2026-05-07T22:20:21Z","snapshot_observed_at":"2026-08-14T23:55:56.044089Z","submitted_at":"2023-10-23T18:54:43Z","title":"Active teacher selection for reward learning","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-24T05:54:43.873174Z"},"links":{"cited_paper":"/paper/2101.07691","citing_paper":"/paper/2310.15288"},"observation_digest":"sha256:6df32ac28869be3e03ae67c85a00df21cdd86c9c368c5a37d3945da6a7e717a0","observation_id":"f2e4c707-9517-423d-a8a7-1dc0f06d4dc7","resolution":{"observed_at":"2026-05-24T05:56:01.727906Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2101.07691","last_updated":"2021-01-19T15:35:30Z","snapshot_observed_at":"2026-08-16T18:51:21.995349Z","submitted_at":"2021-01-19T15:35:30Z","title":"Choice Set Misspecification in Reward Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.07691","snapshot_observed_at":"2026-08-12T18:15:15.535401Z","title":null,"venue":null,"work_id":null,"year":2021},"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":65,"source":"pdf_text","source_observed_at":"2026-08-12T18:15:15.535401Z"},"links":{"cited_paper":"/paper/2101.07691","citing_paper":"/paper/2411.11761"},"observation_digest":"sha256:efa44764631831a06ed52b49a24940cf4d339ef761e64ab82877e6aab033ba31","observation_id":"38280829-3121-4a14-a401-71c4d8deb72f","resolution":{"observed_at":"2026-08-12T18:15:15.535401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2101.07691/citation-record","integrity":"/paper/2101.07691/integrity","json":"/paper/2101.07691/citation-record.json","paper":"/paper/2101.07691"},"outbound":[],"paper":{"arxiv_id":"2101.07691","last_updated":"2021-01-19T15:35:30Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T18:51:21.995349Z","submitted_at":"2021-01-19T15:35:30Z","title":"Choice Set Misspecification in Reward Inference"},"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 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2101.07691."}