{"as_of":"2026-08-10T19:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3a077a111e9629e749cda7a67d56f2afb377761e42b17a84751aa6e09485fc8f","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":"2026-08-07T22:06:36.942850Z","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":"2026-05-11T05:16:33.055593Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1605.03143","last_updated":"2016-05-10T18:28:57Z","snapshot_observed_at":"2026-07-06T04:55:47.659995Z","submitted_at":"2016-05-10T18:28:57Z","title":"Avoiding Wireheading with Value Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"1605.03143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1605.03143","snapshot_observed_at":"2026-07-04T21:00:50.940799Z","title":"Avoiding wireheading with value reinforcement learning","venue":null,"work_id":"44d734e7-24cd-468d-9732-dfea575cd185","year":2016},"citing_paper":{"arxiv_id":"1606.06565","last_updated":"2016-07-25T17:23:29Z","snapshot_observed_at":"2026-07-06T05:00:46.434335Z","submitted_at":"2016-06-21T13:37:05Z","title":"Concrete Problems in AI Safety","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-11T05:16:31.970352Z"},"links":{"cited_paper":"/paper/1605.03143","citing_paper":"/paper/1606.06565"},"observation_digest":"sha256:91234a93f5dbc40d60918fcd21eeeaf2b8013e2583ad757e8f6a807ceecc9f2b","observation_id":"608889d1-a6e7-4999-b9e4-e195ed002ee2","resolution":{"observed_at":"2026-07-04T21:00:50.940799Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"1605.03143","last_updated":"2016-05-10T18:28:57Z","snapshot_observed_at":"2026-07-06T04:55:47.659995Z","submitted_at":"2016-05-10T18:28:57Z","title":"Avoiding Wireheading with Value Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.03143","snapshot_observed_at":"2026-08-07T22:06:36.942850Z","title":"& Hutter, M","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.09288","last_updated":"2025-02-14T16:11:22Z","snapshot_observed_at":"2026-08-10T14:56:45.554745Z","submitted_at":"2025-02-13T13:04:59Z","title":"AI Safety for Everyone","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T22:06:36.942850Z"},"links":{"cited_paper":"/paper/1605.03143","citing_paper":"/paper/2502.09288"},"observation_digest":"sha256:ee0d249fddee24b95a34add704648a5a429d1dfd937712ac03f81e6e19f25755","observation_id":"4b0777c7-124f-4eec-906c-8e2b0b7c2c51","resolution":{"observed_at":"2026-08-07T22:06:36.942850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1605.03143/citation-record","integrity":"/paper/1605.03143/integrity","json":"/paper/1605.03143/citation-record.json","paper":"/paper/1605.03143"},"outbound":[],"paper":{"arxiv_id":"1605.03143","last_updated":"2016-05-10T18:28:57Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T04:55:47.659995Z","submitted_at":"2016-05-10T18:28:57Z","title":"Avoiding Wireheading with Value Reinforcement 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":"2026-08-10T06:31:04.303077+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:1605.03143."}