{"as_of":"2026-08-10T08:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:30089153ede99d0a4dd925eb2dc2320c186d4493eedc1be806af7377c67d88c8","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":"2026-08-10T06:31:04.303077+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":"2026-08-08T19:23:42.450942Z","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":"2026-08-07T15:29:48.319428Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.09469","last_updated":"2021-04-19T17:33:07Z","snapshot_observed_at":"2026-08-08T23:33:53.447319Z","submitted_at":"2021-04-19T17:33:07Z","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09469","snapshot_observed_at":"2026-08-08T19:23:42.450942Z","title":", Frazier, S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.05442","last_updated":"2025-07-15T00:40:33Z","snapshot_observed_at":"2026-08-09T20:56:37.367457Z","submitted_at":"2025-02-08T04:17:28Z","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-08T19:23:42.450942Z"},"links":{"cited_paper":"/paper/2104.09469","citing_paper":"/paper/2502.05442"},"observation_digest":"sha256:6e933e1e2a022f7f40f7a844b3c5c817eb1d7efc11f605029f5c15ef8c0a0233","observation_id":"41845b1c-2c55-4e83-898f-f811de7a69a1","resolution":{"observed_at":"2026-08-08T19:23:42.450942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09469","last_updated":"2021-04-19T17:33:07Z","snapshot_observed_at":"2026-08-08T23:33:53.447319Z","submitted_at":"2021-04-19T17:33:07Z","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","version":1},"cited_work":{"arxiv_id":"2104.09469","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.09469","snapshot_observed_at":"2026-08-07T15:29:48.319428Z","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","venue":"cs.LG","work_id":"6e47911e-d053-4ce9-95bb-dde203b1fa4a","year":2021},"citing_paper":{"arxiv_id":"2505.15011","last_updated":"2025-05-21T01:32:54Z","snapshot_observed_at":"2026-08-09T22:36:27.911015Z","submitted_at":"2025-05-21T01:32:54Z","title":"HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:29:45.440912Z"},"links":{"cited_paper":"/paper/2104.09469","citing_paper":"/paper/2505.15011"},"observation_digest":"sha256:8c29268633c6c4be639ed1abd0c4d487dc6f6568ffcf77de7918e6b7f00e27c5","observation_id":"a3dbad0a-4ed1-45e7-97ba-f38945127bb1","resolution":{"observed_at":"2026-08-07T15:29:48.390968Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2104.09469/citation-record","integrity":"/paper/2104.09469/integrity","json":"/paper/2104.09469/citation-record.json","paper":"/paper/2104.09469"},"outbound":[],"paper":{"arxiv_id":"2104.09469","last_updated":"2021-04-19T17:33:07Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T23:33:53.447319Z","submitted_at":"2021-04-19T17:33:07Z","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2104.09469."}