{"as_of":"2026-08-10T11:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a142c1d27f965617c2f11b3c62a436d5d8665dbac28aadb3c3030285e6c88099","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":"2026-08-10T06:31:04.303077+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":"2026-08-08T13:35:24.484692Z","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":"2026-05-11T20:23:30.864963Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.09760","last_updated":"2025-03-07T15:26:03Z","snapshot_observed_at":"2026-07-06T18:30:50.693663Z","submitted_at":"2024-06-14T06:57:18Z","title":"Bootstrapping Language Models with DPO Implicit Rewards","version":2},"cited_work":{"arxiv_id":"2406.09760","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09760","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.09760 , year=","venue":null,"work_id":"07ce534c-bb2d-451e-9084-262d65835727","year":null},"citing_paper":{"arxiv_id":"2502.01456","last_updated":"2025-09-26T09:25:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-03T15:43:48Z","title":"Process Reinforcement through Implicit Rewards","version":2},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-05-11T20:23:30.763794Z"},"links":{"cited_paper":"/paper/2406.09760","citing_paper":"/paper/2502.01456"},"observation_digest":"sha256:b8696493268a33bafd8aba8c0d81ad364e0c3d5ab2ba03134d9bf8209b860408","observation_id":"9a1b0d02-e1bc-4f64-8097-16095c5e772b","resolution":{"observed_at":"2026-05-11T20:23:30.867865Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09760","last_updated":"2025-03-07T15:26:03Z","snapshot_observed_at":"2026-07-06T18:30:50.693663Z","submitted_at":"2024-06-14T06:57:18Z","title":"Bootstrapping Language Models with DPO Implicit Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09760","snapshot_observed_at":"2026-08-08T13:35:24.484692Z","title":"Bootstrapping lan- guage models with dpo implicit rewards","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.07191","last_updated":"2025-02-17T03:54:05Z","snapshot_observed_at":"2026-08-09T05:18:33.083500Z","submitted_at":"2025-02-11T02:31:11Z","title":"Bag of Tricks for Inference-time Computation of LLM Reasoning","version":4},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T13:35:24.484692Z"},"links":{"cited_paper":"/paper/2406.09760","citing_paper":"/paper/2502.07191"},"observation_digest":"sha256:e9f06bd2955f6a6dd4930063f318973cef12ec2c4683297222d3aa576cc43b79","observation_id":"39528a95-91ea-43c2-9c92-7c574016c962","resolution":{"observed_at":"2026-08-08T13:35:24.484692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09760","last_updated":"2025-03-07T15:26:03Z","snapshot_observed_at":"2026-07-06T18:30:50.693663Z","submitted_at":"2024-06-14T06:57:18Z","title":"Bootstrapping Language Models with DPO Implicit Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09760","snapshot_observed_at":"2026-08-07T05:40:17.861184Z","title":"Bootstrapping language models with DPO implicit rewards","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07492","last_updated":"2025-06-09T07:11:01Z","snapshot_observed_at":"2026-08-09T13:22:13.526160Z","submitted_at":"2025-06-09T07:11:01Z","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T05:40:17.861184Z"},"links":{"cited_paper":"/paper/2406.09760","citing_paper":"/paper/2506.07492"},"observation_digest":"sha256:0d7feb73c08923e78b2ba89fac311adec897e38e80093d39867ef82ba9aac2e9","observation_id":"48ce16f0-6567-4693-b4f1-353b408a368f","resolution":{"observed_at":"2026-08-07T05:40:17.861184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09760","last_updated":"2025-03-07T15:26:03Z","snapshot_observed_at":"2026-07-06T18:30:50.693663Z","submitted_at":"2024-06-14T06:57:18Z","title":"Bootstrapping Language Models with DPO Implicit Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09760","snapshot_observed_at":"2026-08-03T16:43:54.381657Z","title":"Chen, H., Feng, Y ., Liu, Z., Yao, W., Prabhakar, A., Hei- necke, S., Ho, R., Mui, P., Savarese, S., Xiong, C., and Wang, H","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.12576","last_updated":"2026-05-23T02:48:11Z","snapshot_observed_at":"2026-08-07T00:51:43.825252Z","submitted_at":"2025-12-14T07:03:51Z","title":"Coupled Variational Reinforcement Learning for Language Model General Reasoning","version":3},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-03T16:43:54.381657Z"},"links":{"cited_paper":"/paper/2406.09760","citing_paper":"/paper/2512.12576"},"observation_digest":"sha256:44dc938fcbb91ba2ac6d5038f05aa5b12d91adf14494c1ba4ae1fedbecc96787","observation_id":"5b33c3c0-dcd0-458f-92a1-1ca91077afc9","resolution":{"observed_at":"2026-08-03T16:43:54.381657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.09760/citation-record","integrity":"/paper/2406.09760/integrity","json":"/paper/2406.09760/citation-record.json","paper":"/paper/2406.09760"},"outbound":[],"paper":{"arxiv_id":"2406.09760","last_updated":"2025-03-07T15:26:03Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:30:50.693663Z","submitted_at":"2024-06-14T06:57:18Z","title":"Bootstrapping Language Models with DPO Implicit Rewards"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2406.09760."}