{"as_of":"2026-08-12T16:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6ecfd0320eee5b8ff782b69efc6e43af545084b1a65979c81fa17dc4099e454d","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T16:58:02.589047Z","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":"2026-05-22T19:32:01.388139Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.01511","last_updated":"2024-08-07T03:46:30Z","snapshot_observed_at":"2026-08-11T16:51:56.755134Z","submitted_at":"2024-05-02T17:44:41Z","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.01511","snapshot_observed_at":"2026-08-10T16:58:02.589047Z","title":"D2po: Discriminator-guided dpo with response evaluation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12735","last_updated":"2025-02-07T02:13:27Z","snapshot_observed_at":"2026-08-10T16:48:54.578052Z","submitted_at":"2025-01-22T09:12:09Z","title":"Online Preference Alignment for Language Models via Count-based Exploration","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-10T16:58:02.589047Z"},"links":{"cited_paper":"/paper/2405.01511","citing_paper":"/paper/2501.12735"},"observation_digest":"sha256:4da6c9dd3d16c3ff110c4461783b4cd247a146671467a282c8d913dbdedeab3e","observation_id":"83b75950-a1ae-4a1c-81e5-8a156403d141","resolution":{"observed_at":"2026-08-10T16:58:02.589047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.01511","last_updated":"2024-08-07T03:46:30Z","snapshot_observed_at":"2026-08-11T16:51:56.755134Z","submitted_at":"2024-05-02T17:44:41Z","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","version":2},"cited_work":{"arxiv_id":"2405.01511","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.01511","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"D2po: Discriminator- guided dpo with response evaluation models","venue":null,"work_id":"8273890f-b569-4139-b26f-352f5082b0f0","year":2024},"citing_paper":{"arxiv_id":"2504.12501","last_updated":"2026-08-03T01:47:58Z","snapshot_observed_at":"2026-08-07T16:01:39.307745Z","submitted_at":"2025-04-16T21:36:46Z","title":"Reinforcement Learning from Human Feedback","version":9},"reference_index":204,"source":"pdf_text","source_observed_at":"2026-05-22T19:27:40.991325Z"},"links":{"cited_paper":"/paper/2405.01511","citing_paper":"/paper/2504.12501"},"observation_digest":"sha256:93b8bfa79db5120037d5390c6bb16842ead5bf71ee0895f641b2a9040f5d5db7","observation_id":"cd1c0e5d-9df2-489d-a8b3-8aee36feba07","resolution":{"observed_at":"2026-05-22T19:32:01.390258Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.01511","last_updated":"2024-08-07T03:46:30Z","snapshot_observed_at":"2026-08-11T16:51:56.755134Z","submitted_at":"2024-05-02T17:44:41Z","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","version":2},"cited_work":{"arxiv_id":"2405.01511","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.01511","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"D2po: Discriminator- guided dpo with response evaluation models","venue":null,"work_id":"8273890f-b569-4139-b26f-352f5082b0f0","year":2024},"citing_paper":{"arxiv_id":"2506.01937","last_updated":"2026-04-23T14:42:19Z","snapshot_observed_at":"2026-07-06T21:35:12.872021Z","submitted_at":"2025-06-02T17:54:04Z","title":"RewardBench 2: Advancing Reward Model Evaluation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-19T11:18:03.965711Z"},"links":{"cited_paper":"/paper/2405.01511","citing_paper":"/paper/2506.01937"},"observation_digest":"sha256:4e508cc6797969c01a0c11bc6322ad660fd2e4dd1e2309c729b3ae986c3ed42d","observation_id":"bfe5a185-0800-46f8-9fd4-583a5933b30b","resolution":{"observed_at":"2026-05-19T11:22:16.695728Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.01511/citation-record","integrity":"/paper/2405.01511/integrity","json":"/paper/2405.01511/citation-record.json","paper":"/paper/2405.01511"},"outbound":[],"paper":{"arxiv_id":"2405.01511","last_updated":"2024-08-07T03:46:30Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-11T16:51:56.755134Z","submitted_at":"2024-05-02T17:44:41Z","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2405.01511."}