{"as_of":"2026-08-08T21:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5c0b21dfec60fa44e90e80ef1e3e84823ea29374e3cadc18c221d26a55907046","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:31:58.792853Z","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":"2026-05-24T11:14:23.193451Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.08827","last_updated":"2020-11-17T18:48:59Z","snapshot_observed_at":"2026-08-07T23:06:01.123740Z","submitted_at":"2020-11-17T18:48:59Z","title":"Avoiding Tampering Incentives in Deep RL via Decoupled Approval","version":1},"cited_work":{"arxiv_id":"2011.08827","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.08827","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Uesato, R","venue":null,"work_id":"3bd5d2a2-db35-4aa3-aff0-5143afb38a8b","year":2011},"citing_paper":{"arxiv_id":"2211.14275","last_updated":"2022-11-25T18:19:44Z","snapshot_observed_at":"2026-08-01T02:16:43.109337Z","submitted_at":"2022-11-25T18:19:44Z","title":"Solving math word problems with process- and outcome-based feedback","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-24T11:10:40.864420Z"},"links":{"cited_paper":"/paper/2011.08827","citing_paper":"/paper/2211.14275"},"observation_digest":"sha256:99c094554f9ddf2f3f657b51bd23ad1f8225e06e4164d6d87b5b04ca23ad2327","observation_id":"04ac25a7-d05f-4256-9fdd-14d51e4f80f8","resolution":{"observed_at":"2026-05-24T11:14:23.195998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.08827","last_updated":"2020-11-17T18:48:59Z","snapshot_observed_at":"2026-08-07T23:06:01.123740Z","submitted_at":"2020-11-17T18:48:59Z","title":"Avoiding Tampering Incentives in Deep RL via Decoupled Approval","version":1},"cited_work":{"arxiv_id":"2011.08827","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.08827","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Uesato, R","venue":null,"work_id":"3bd5d2a2-db35-4aa3-aff0-5143afb38a8b","year":2011},"citing_paper":{"arxiv_id":"2406.10162","last_updated":"2024-06-29T00:28:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-14T16:26:20Z","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-05-17T14:43:29.496457Z"},"links":{"cited_paper":"/paper/2011.08827","citing_paper":"/paper/2406.10162"},"observation_digest":"sha256:e098fb3d5b367033418ab0771bacf12ee93e7e1f059bb9240125cf6ab7a48bc8","observation_id":"ba0a7c1f-bd17-4b2c-876b-4e66dcebbc31","resolution":{"observed_at":"2026-05-17T14:43:30.081240Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.08827","last_updated":"2020-11-17T18:48:59Z","snapshot_observed_at":"2026-08-07T23:06:01.123740Z","submitted_at":"2020-11-17T18:48:59Z","title":"Avoiding Tampering Incentives in Deep RL via Decoupled Approval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.08827","snapshot_observed_at":"2026-08-07T10:31:58.792853Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.05070","last_updated":"2025-08-05T04:45:24Z","snapshot_observed_at":"2026-08-08T08:47:53.025574Z","submitted_at":"2025-06-05T14:18:21Z","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T10:31:58.792853Z"},"links":{"cited_paper":"/paper/2011.08827","citing_paper":"/paper/2506.05070"},"observation_digest":"sha256:52bced12522081e84f3004342b460bc316330f382414244b1c15be1b0ea9898f","observation_id":"b2132ac7-0138-43b4-9e8b-6ed0322c2619","resolution":{"observed_at":"2026-08-07T10:31:58.792853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.08827","last_updated":"2020-11-17T18:48:59Z","snapshot_observed_at":"2026-08-07T23:06:01.123740Z","submitted_at":"2020-11-17T18:48:59Z","title":"Avoiding Tampering Incentives in Deep RL via Decoupled Approval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.08827","snapshot_observed_at":"2026-08-01T05:03:41.453576Z","title":"arXiv preprint arXiv:2011.08827 , year=","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.22368","last_updated":"2026-07-24T14:55:19Z","snapshot_observed_at":"2026-08-06T19:52:38.505220Z","submitted_at":"2026-07-24T14:55:19Z","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-01T05:03:41.453576Z"},"links":{"cited_paper":"/paper/2011.08827","citing_paper":"/paper/2607.22368"},"observation_digest":"sha256:0ee3abb433bb4f1df57de6bd0421e0d4363a92599d60801e989eb86de51e1f2b","observation_id":"e0e3261d-bf2f-4a2e-9222-932ec166022a","resolution":{"observed_at":"2026-08-01T05:03:41.453576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2011.08827/citation-record","integrity":"/paper/2011.08827/integrity","json":"/paper/2011.08827/citation-record.json","paper":"/paper/2011.08827"},"outbound":[],"paper":{"arxiv_id":"2011.08827","last_updated":"2020-11-17T18:48:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T23:06:01.123740Z","submitted_at":"2020-11-17T18:48:59Z","title":"Avoiding Tampering Incentives in Deep RL via Decoupled Approval"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2011.08827."}