{"as_of":"2026-08-07T21:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ee3b3aa6f3a91fb349f1ff6ccf53c59cdae9537beac3e72e3cb9469e88b0cb1","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T11:21:40.015790Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T05:50:42.560369Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.18248","last_updated":"2024-07-25T17:59:16Z","snapshot_observed_at":"2026-08-05T00:01:46.859793Z","submitted_at":"2024-07-25T17:59:16Z","title":"Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.18248","snapshot_observed_at":"2026-08-07T11:21:40.015790Z","title":"Self-training with direct preference optimization improves chain-of- thought reasoning.arXiv preprint arXiv:2407.18248, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02726","last_updated":"2025-06-03T10:36:38Z","snapshot_observed_at":"2026-08-07T11:15:01.802013Z","submitted_at":"2025-06-03T10:36:38Z","title":"RACE-Align: Retrieval-Augmented and Chain-of-Thought Enhanced Preference Alignment for Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:21:40.015790Z"},"links":{"cited_paper":"/paper/2407.18248","citing_paper":"/paper/2506.02726"},"observation_digest":"sha256:0c9f7df5d1e3ed26ab532fecd187c75eb183b7e30db2d642daa7148b36b827d4","observation_id":"903b4620-bbfa-4740-b989-c9aa6a4f3c2d","resolution":{"observed_at":"2026-08-07T11:21:40.015790Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.18248","last_updated":"2024-07-25T17:59:16Z","snapshot_observed_at":"2026-08-05T00:01:46.859793Z","submitted_at":"2024-07-25T17:59:16Z","title":"Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning","version":1},"cited_work":{"arxiv_id":"2407.18248","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.18248","snapshot_observed_at":"2026-08-07T05:50:42.560369Z","title":"Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning","venue":"cs.CL","work_id":"5a00d22a-3da5-40da-abdd-242197a86a9d","year":2024},"citing_paper":{"arxiv_id":"2506.07047","last_updated":"2025-06-08T09:04:14Z","snapshot_observed_at":"2026-08-07T05:40:58.238740Z","submitted_at":"2025-06-08T09:04:14Z","title":"Mathesis: Towards Formal Theorem Proving from Natural Languages","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:50:38.943317Z"},"links":{"cited_paper":"/paper/2407.18248","citing_paper":"/paper/2506.07047"},"observation_digest":"sha256:510b3e74cf5d819b9b80e1a2ea4b8fe9d8a27b5343035cdfd04c7fe5e4c0d1f9","observation_id":"82bb1ed3-d7fd-4eff-b99b-7a65b964e075","resolution":{"observed_at":"2026-08-07T05:50:42.695376Z","resolver_source":"local_arxiv","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/2407.18248/citation-record","integrity":"/paper/2407.18248/integrity","json":"/paper/2407.18248/citation-record.json","paper":"/paper/2407.18248"},"outbound":[],"paper":{"arxiv_id":"2407.18248","last_updated":"2024-07-25T17:59:16Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T00:01:46.859793Z","submitted_at":"2024-07-25T17:59:16Z","title":"Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning"},"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 2 inbound Pith citation observations for arXiv:2407.18248."}