{"as_of":"2026-08-10T22:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2819ed6e51a09dd8c4538a199fa4a296200ceda00878b7ed77d9c6a26e793b6f","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":"2026-08-10T06:31:04.303077+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":"2026-05-19T06:09:26.269452Z","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":"2026-05-19T06:12:07.178678Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.20830","last_updated":"2024-05-31T14:21:04Z","snapshot_observed_at":"2026-07-06T18:23:19.450809Z","submitted_at":"2024-05-31T14:21:04Z","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","version":1},"cited_work":{"arxiv_id":"2405.20830","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.20830","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self-augmented preference optimization: Off-policy paradigms for language model alignment","venue":null,"work_id":"ab9a35ef-7391-4f3b-a227-b90eb7d5bb7f","year":2024},"citing_paper":{"arxiv_id":"2507.05179","last_updated":"2026-05-31T04:19:46Z","snapshot_observed_at":"2026-08-06T19:27:53.110737Z","submitted_at":"2025-07-07T16:34:28Z","title":"From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations","version":5},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-05-19T06:09:26.269452Z"},"links":{"cited_paper":"/paper/2405.20830","citing_paper":"/paper/2507.05179"},"observation_digest":"sha256:5856574513f8c3069c536cdf0ac7038f8ee7f5fe20ff622c490700ed59112e9d","observation_id":"b1128ebd-30a9-4822-9189-8da3f796bca4","resolution":{"observed_at":"2026-05-19T06:12:07.181331Z","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":"2405.20830","last_updated":"2024-05-31T14:21:04Z","snapshot_observed_at":"2026-07-06T18:23:19.450809Z","submitted_at":"2024-05-31T14:21:04Z","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","version":1},"cited_work":{"arxiv_id":"2405.20830","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.20830","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self-augmented preference optimization: Off-policy paradigms for language model alignment","venue":null,"work_id":"ab9a35ef-7391-4f3b-a227-b90eb7d5bb7f","year":2024},"citing_paper":{"arxiv_id":"2604.20933","last_updated":"2026-04-22T11:52:21Z","snapshot_observed_at":"2026-07-30T07:55:19.034385Z","submitted_at":"2026-04-22T11:52:21Z","title":"IRIS: Interpolative R\\'enyi Iterative Self-play for Large Language Model Fine-Tuning","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-05-10T01:15:12.985803Z"},"links":{"cited_paper":"/paper/2405.20830","citing_paper":"/paper/2604.20933"},"observation_digest":"sha256:537e7e4cf443b242f0577a235a176cd79fcc6ad8f5e1a671eab469d1624b7f6b","observation_id":"131881bf-e336-43c0-9d45-ac5c936e6845","resolution":{"observed_at":"2026-05-11T13:41:05.013701Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2405.20830/citation-record","integrity":"/paper/2405.20830/integrity","json":"/paper/2405.20830/citation-record.json","paper":"/paper/2405.20830"},"outbound":[],"paper":{"arxiv_id":"2405.20830","last_updated":"2024-05-31T14:21:04Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:23:19.450809Z","submitted_at":"2024-05-31T14:21:04Z","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment"},"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 2 inbound Pith citation observations for arXiv:2405.20830."}