{"as_of":"2026-08-04T14:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:db943fbe9d1bf77e500478e271d2896dd19c0ea27cd3de4f5d1adcf848effc40","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":"2026-08-04T06:34:03.388597+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":"2026-05-21T14:05:37.120262Z","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":"2026-05-21T14:10:13.545009Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.03095","last_updated":"2025-02-05T11:41:43Z","snapshot_observed_at":"2026-08-03T23:39:49.515711Z","submitted_at":"2025-02-05T11:41:43Z","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","version":1},"cited_work":{"arxiv_id":"2502.03095","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.03095","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reveal the mystery of dpo: The connection between dpo and rl algorithms","venue":null,"work_id":"16d4f451-c454-4362-8297-0dc5d0185b34","year":null},"citing_paper":{"arxiv_id":"2601.21484","last_updated":"2026-05-19T09:15:43Z","snapshot_observed_at":"2026-08-03T13:18:34.276013Z","submitted_at":"2026-01-29T10:06:52Z","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-16T09:37:57.120779Z"},"links":{"cited_paper":"/paper/2502.03095","citing_paper":"/paper/2601.21484"},"observation_digest":"sha256:ad2e5932c68326ecf738e8779886330c6ebb351ae89b1cdf5cadeb79be4f4c8c","observation_id":"7bc2796f-0538-40f3-96fe-db00a8fb1dc8","resolution":{"observed_at":"2026-05-16T09:40:49.066829Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03095","last_updated":"2025-02-05T11:41:43Z","snapshot_observed_at":"2026-08-03T23:39:49.515711Z","submitted_at":"2025-02-05T11:41:43Z","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","version":1},"cited_work":{"arxiv_id":"2502.03095","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.03095","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reveal the mystery of dpo: The connection between dpo and rl algorithms","venue":null,"work_id":"16d4f451-c454-4362-8297-0dc5d0185b34","year":null},"citing_paper":{"arxiv_id":"2601.21484","last_updated":"2026-05-19T09:15:43Z","snapshot_observed_at":"2026-08-03T13:18:34.276013Z","submitted_at":"2026-01-29T10:06:52Z","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T14:05:37.120262Z"},"links":{"cited_paper":"/paper/2502.03095","citing_paper":"/paper/2601.21484"},"observation_digest":"sha256:68d9e942da51991af6ed85282fb855f69ad81b6aeb28c9464ea5bc4187de8cac","observation_id":"9e3224b3-69c0-4c35-b52f-3aa3bb9f6bac","resolution":{"observed_at":"2026-05-21T14:10:13.548018Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.03095/citation-record","integrity":"/paper/2502.03095/integrity","json":"/paper/2502.03095/citation-record.json","paper":"/paper/2502.03095"},"outbound":[],"paper":{"arxiv_id":"2502.03095","last_updated":"2025-02-05T11:41:43Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T23:39:49.515711Z","submitted_at":"2025-02-05T11:41:43Z","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2502.03095."}