{"as_of":"2026-08-07T11:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:696332aa966e5692bcf6425754f2c8551268f55db3b3122765a7e4b8bca8fd52","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:18:05.136617Z","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":"2026-07-01T08:35:34.319361Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.01920","last_updated":"2024-10-08T20:32:15Z","snapshot_observed_at":"2026-07-06T17:24:41.012207Z","submitted_at":"2024-02-02T21:45:24Z","title":"Preference Poisoning Attacks on Reward Model Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01920","snapshot_observed_at":"2026-08-07T11:18:05.136617Z","title":"Preference poisoning attacks on reward model learning.arXiv preprint arXiv:2402.01920, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03234","last_updated":"2025-06-03T16:01:04Z","snapshot_observed_at":"2026-08-07T11:08:03.449195Z","submitted_at":"2025-06-03T16:01:04Z","title":"BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:18:05.136617Z"},"links":{"cited_paper":"/paper/2402.01920","citing_paper":"/paper/2506.03234"},"observation_digest":"sha256:d0b53eab8c19d6613280dfda01d6cf9010a66e67949ca8d6c40f44d654d1c9d4","observation_id":"d7e337ca-da47-4492-90f3-2a6be172ac8c","resolution":{"observed_at":"2026-08-07T11:18:05.136617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01920","last_updated":"2024-10-08T20:32:15Z","snapshot_observed_at":"2026-07-06T17:24:41.012207Z","submitted_at":"2024-02-02T21:45:24Z","title":"Preference Poisoning Attacks on Reward Model Learning","version":2},"cited_work":{"arxiv_id":"2402.01920","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.01920","snapshot_observed_at":"2026-07-01T08:35:34.319361Z","title":"arXiv preprint arXiv:2402.01920 , year=","venue":null,"work_id":"91f23bae-e37e-40e0-b9f9-e07bce6f7b30","year":2024},"citing_paper":{"arxiv_id":"2605.02495","last_updated":"2026-05-25T07:21:41Z","snapshot_observed_at":"2026-07-06T23:15:32.349713Z","submitted_at":"2026-05-04T11:45:38Z","title":"Efficient Preference Poisoning Attack on Offline RLHF","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-08T19:29:25.000361Z"},"links":{"cited_paper":"/paper/2402.01920","citing_paper":"/paper/2605.02495"},"observation_digest":"sha256:31829fc6bb1dac4c3cb6e62178200d6897a8ca1a3fc0ec19fc807804719739ff","observation_id":"aaa056f6-cb7b-4310-959e-4595c631ee8b","resolution":{"observed_at":"2026-05-09T05:50:27.057973Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01920","last_updated":"2024-10-08T20:32:15Z","snapshot_observed_at":"2026-07-06T17:24:41.012207Z","submitted_at":"2024-02-02T21:45:24Z","title":"Preference Poisoning Attacks on Reward Model Learning","version":2},"cited_work":{"arxiv_id":"2402.01920","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.01920","snapshot_observed_at":"2026-07-01T08:35:34.319361Z","title":"arXiv preprint arXiv:2402.01920 , year=","venue":null,"work_id":"91f23bae-e37e-40e0-b9f9-e07bce6f7b30","year":2024},"citing_paper":{"arxiv_id":"2606.30666","last_updated":"2026-06-18T10:25:09Z","snapshot_observed_at":"2026-08-06T01:04:05.837697Z","submitted_at":"2026-06-18T10:25:09Z","title":"Reframing AGI Confrontation with Off Earth Autonomy","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-01T07:18:55.451342Z"},"links":{"cited_paper":"/paper/2402.01920","citing_paper":"/paper/2606.30666"},"observation_digest":"sha256:65a40ef8d0390ca5e80331f26db32dc67519f22d599d519e35ab5ad6eeae3a49","observation_id":"9be9e1b5-c9b8-4169-acf8-88146a7e366e","resolution":{"observed_at":"2026-07-01T08:35:34.320671Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.01920/citation-record","integrity":"/paper/2402.01920/integrity","json":"/paper/2402.01920/citation-record.json","paper":"/paper/2402.01920"},"outbound":[],"paper":{"arxiv_id":"2402.01920","last_updated":"2024-10-08T20:32:15Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:24:41.012207Z","submitted_at":"2024-02-02T21:45:24Z","title":"Preference Poisoning Attacks on Reward Model 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.01920."}