{"as_of":"2026-08-17T22:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:edf652794218e123eaf56627d97debd0ce3cdf546b2d8053720b4ef08b41a2c6","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":"2026-08-17T06:30:58.91139+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":"2026-08-15T21:19:41.326063Z","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":"2026-07-02T03:46:33.125499Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.10184","last_updated":"2025-05-28T11:59:41Z","snapshot_observed_at":"2026-08-16T14:18:12.275285Z","submitted_at":"2024-02-15T18:39:24Z","title":"Reward Generalization in RLHF: A Topological Perspective","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10184","snapshot_observed_at":"2026-08-15T21:19:41.326063Z","title":"Reward generalization in rlhf: A topological perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.10597","last_updated":"2025-05-19T03:28:14Z","snapshot_observed_at":"2026-08-16T01:47:23.448958Z","submitted_at":"2025-05-15T10:58:20Z","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T21:19:41.326063Z"},"links":{"cited_paper":"/paper/2402.10184","citing_paper":"/paper/2505.10597"},"observation_digest":"sha256:fcfdc35199ae949ed09ac5d2e9f37e053a4734b2354d6babf48c0f8814f737ae","observation_id":"d58fa8a7-78b0-417d-8794-d3fe9ad0c387","resolution":{"observed_at":"2026-08-15T21:19:41.326063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10184","last_updated":"2025-05-28T11:59:41Z","snapshot_observed_at":"2026-08-16T14:18:12.275285Z","submitted_at":"2024-02-15T18:39:24Z","title":"Reward Generalization in RLHF: A Topological Perspective","version":7},"cited_work":{"arxiv_id":"2402.10184","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.10184","snapshot_observed_at":"2026-07-02T03:46:33.125499Z","title":"arXiv preprint arXiv:2402.10184 , year=","venue":null,"work_id":"026284bb-3eb5-4456-981f-dab253443941","year":null},"citing_paper":{"arxiv_id":"2606.03489","last_updated":"2026-06-02T11:07:20Z","snapshot_observed_at":"2026-08-14T16:25:53.570697Z","submitted_at":"2026-06-02T11:07:20Z","title":"Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-06-28T09:40:35.258818Z"},"links":{"cited_paper":"/paper/2402.10184","citing_paper":"/paper/2606.03489"},"observation_digest":"sha256:3f8d30b43ee557e7244a7ab46ab6a503073c9708d60cbb12b0d4e5062330aabb","observation_id":"bb727221-e341-48cb-824c-8a1b7977547d","resolution":{"observed_at":"2026-07-02T03:46:33.126940Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.10184/citation-record","integrity":"/paper/2402.10184/integrity","json":"/paper/2402.10184/citation-record.json","paper":"/paper/2402.10184"},"outbound":[],"paper":{"arxiv_id":"2402.10184","last_updated":"2025-05-28T11:59:41Z","latest_version":7,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:18:12.275285Z","submitted_at":"2024-02-15T18:39:24Z","title":"Reward Generalization in RLHF: A Topological Perspective"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.10184."}