{"as_of":"2026-08-22T23:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4346aba531d38f8e1d2ceaaba477dd1bc38b505564b85ac7710a510e4c2b7868","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":"2026-08-22T06:32:14.747728+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":"2026-08-15T19:38:50.852504Z","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":"2026-05-12T07:11:27.159414Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.15257","last_updated":"2024-12-12T15:29:41Z","snapshot_observed_at":"2026-08-19T10:48:34.148603Z","submitted_at":"2023-09-26T20:31:19Z","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15257","snapshot_observed_at":"2026-08-15T19:38:50.852504Z","title":"Starc: A general frame- work for quantifying differences between reward functions.arXiv preprint arXiv:2309.15257,","venue":null,"work_id":null,"year":null},"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":28,"source":"pdf_text","source_observed_at":"2026-08-15T19:38:50.852504Z"},"links":{"cited_paper":"/paper/2309.15257","citing_paper":"/paper/2506.15421"},"observation_digest":"sha256:e6e32063bfd04f6056862d17e50e5d8e1517a0461542a31f05e46a60af5efca8","observation_id":"26e7ff2b-2682-45f3-8248-ac6aaa0779a6","resolution":{"observed_at":"2026-08-15T19:38:50.852504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15257","last_updated":"2024-12-12T15:29:41Z","snapshot_observed_at":"2026-08-19T10:48:34.148603Z","submitted_at":"2023-09-26T20:31:19Z","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","version":3},"cited_work":{"arxiv_id":"2309.15257","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.15257","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2309.15257 , year=","venue":null,"work_id":"991aee53-1f41-4f1d-8917-e0b0fc28504c","year":null},"citing_paper":{"arxiv_id":"2605.09217","last_updated":"2026-05-09T23:28:22Z","snapshot_observed_at":"2026-08-13T12:06:32.255527Z","submitted_at":"2026-05-09T23:28:22Z","title":"Learning the Preferences of a Learning Agent","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-05-12T03:36:27.719658Z"},"links":{"cited_paper":"/paper/2309.15257","citing_paper":"/paper/2605.09217"},"observation_digest":"sha256:62a709b7b18b1e8f334b402109ae2499a5e2c324f86286a3c4c32e39f8cdd0ea","observation_id":"55626053-9c5b-4a6b-b995-dd2db494c272","resolution":{"observed_at":"2026-05-12T07:11:27.170343Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.15257/citation-record","integrity":"/paper/2309.15257/integrity","json":"/paper/2309.15257/citation-record.json","paper":"/paper/2309.15257"},"outbound":[],"paper":{"arxiv_id":"2309.15257","last_updated":"2024-12-12T15:29:41Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T10:48:34.148603Z","submitted_at":"2023-09-26T20:31:19Z","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.15257."}