{"as_of":"2026-08-11T19:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ce1bdd072dd41cef205b82fb706f1af5bf9c89aa67eced334e911d44e73a1595","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":"2026-08-11T06:34:44.6726+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":"2026-08-06T23:57:17.153493Z","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":"2026-06-29T12:33:24.381267Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.20847","last_updated":"2025-02-28T08:47:03Z","snapshot_observed_at":"2026-08-10T06:27:48.204810Z","submitted_at":"2025-02-28T08:47:03Z","title":"Gradient Imbalance in Direct Preference Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20847","snapshot_observed_at":"2026-08-06T23:57:17.153493Z","title":"Gradient imbalance in direct preference optimization.arXiv preprint arXiv:2502.20847, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.15684","last_updated":"2025-06-18T17:59:59Z","snapshot_observed_at":"2026-08-11T10:53:18.560101Z","submitted_at":"2025-06-18T17:59:59Z","title":"Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:57:17.153493Z"},"links":{"cited_paper":"/paper/2502.20847","citing_paper":"/paper/2506.15684"},"observation_digest":"sha256:b1d0583cb7d9cbfbbe3d8072bffb14772ffe555929ba1f28546eaa446bd11f39","observation_id":"fcaf57f2-2694-489d-a4c9-634d7a450521","resolution":{"observed_at":"2026-08-06T23:57:17.153493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20847","last_updated":"2025-02-28T08:47:03Z","snapshot_observed_at":"2026-08-10T06:27:48.204810Z","submitted_at":"2025-02-28T08:47:03Z","title":"Gradient Imbalance in Direct Preference Optimization","version":1},"cited_work":{"arxiv_id":"2502.20847","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.20847","snapshot_observed_at":"2026-06-29T12:33:24.381267Z","title":"Gradient imbalance in direct preference optimization","venue":null,"work_id":"dd70dde8-cc28-4494-951d-4dd4cedaa145","year":2024},"citing_paper":{"arxiv_id":"2605.15012","last_updated":"2026-05-14T16:12:30Z","snapshot_observed_at":"2026-08-11T12:34:33.583044Z","submitted_at":"2026-05-14T16:12:30Z","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-15T03:18:26.590871Z"},"links":{"cited_paper":"/paper/2502.20847","citing_paper":"/paper/2605.15012"},"observation_digest":"sha256:5e4d4a182530df7b9dc7338407cb973079b26f17346de8d2da52d5febbdca4ca","observation_id":"9e6ae5c4-0872-4532-865d-9a2fbc70ce22","resolution":{"observed_at":"2026-05-15T03:19:43.006228Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20847","last_updated":"2025-02-28T08:47:03Z","snapshot_observed_at":"2026-08-10T06:27:48.204810Z","submitted_at":"2025-02-28T08:47:03Z","title":"Gradient Imbalance in Direct Preference Optimization","version":1},"cited_work":{"arxiv_id":"2502.20847","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.20847","snapshot_observed_at":"2026-06-29T12:33:24.381267Z","title":"Gradient imbalance in direct preference optimization","venue":null,"work_id":"dd70dde8-cc28-4494-951d-4dd4cedaa145","year":2024},"citing_paper":{"arxiv_id":"2605.28440","last_updated":"2026-05-27T13:05:49Z","snapshot_observed_at":"2026-07-06T23:37:59.285884Z","submitted_at":"2026-05-27T13:05:49Z","title":"AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T12:29:55.729913Z"},"links":{"cited_paper":"/paper/2502.20847","citing_paper":"/paper/2605.28440"},"observation_digest":"sha256:07ed9f1a6a1cb6b23f1e094cc11bc19c17498e0d5fbb41f97c6628a27eaa3d84","observation_id":"438c61d5-70c6-47a2-a157-7ed5675da6ff","resolution":{"observed_at":"2026-06-29T12:33:24.382739Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20847","last_updated":"2025-02-28T08:47:03Z","snapshot_observed_at":"2026-08-10T06:27:48.204810Z","submitted_at":"2025-02-28T08:47:03Z","title":"Gradient Imbalance in Direct Preference Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20847","snapshot_observed_at":"2026-08-01T17:47:41.496853Z","title":"Gradient imbalance in direct preference optimization.arXiv preprint arXiv:2502.20847,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17524","last_updated":"2026-07-20T03:57:22Z","snapshot_observed_at":"2026-08-06T02:55:37.951193Z","submitted_at":"2026-07-20T03:57:22Z","title":"Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T17:47:41.496853Z"},"links":{"cited_paper":"/paper/2502.20847","citing_paper":"/paper/2607.17524"},"observation_digest":"sha256:0f266a5d202ab07f38654a11254c057258853ba320f92642a9794b3d5b554542","observation_id":"4b061c23-3988-42e5-b43c-950eb3aa9a92","resolution":{"observed_at":"2026-08-01T17:47:41.496853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.20847/citation-record","integrity":"/paper/2502.20847/integrity","json":"/paper/2502.20847/citation-record.json","paper":"/paper/2502.20847"},"outbound":[],"paper":{"arxiv_id":"2502.20847","last_updated":"2025-02-28T08:47:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T06:27:48.204810Z","submitted_at":"2025-02-28T08:47:03Z","title":"Gradient Imbalance in Direct Preference Optimization"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2502.20847."}