{"as_of":"2026-08-15T19:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:12c0dc2d4009e4303f8233bcac92f9ca6a9bc04f735f3480531bc0ebc36cb931","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":"2026-08-15T06:32:42.880941+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":"2026-08-07T11:04:06.774840Z","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":"2026-05-13T20:13:13.683304Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.18699","last_updated":"2025-07-22T05:25:08Z","snapshot_observed_at":"2026-08-15T02:10:49.906369Z","submitted_at":"2025-02-25T23:22:12Z","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18699","snapshot_observed_at":"2026-08-07T11:04:06.774840Z","title":"Mpo: An efficient post-processing framework for mixing diverse preference alignment,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.03637","last_updated":"2025-07-07T09:53:22Z","snapshot_observed_at":"2026-08-08T03:23:19.289933Z","submitted_at":"2025-06-04T07:30:16Z","title":"RewardAnything: Generalizable Principle-Following Reward Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:04:06.774840Z"},"links":{"cited_paper":"/paper/2502.18699","citing_paper":"/paper/2506.03637"},"observation_digest":"sha256:fe77c5d4a1bab66fe0391d208c4c2390bd020596538f4a007a6a9e2b373857b0","observation_id":"e30463e9-60e3-492e-8b33-8d61471e0f3a","resolution":{"observed_at":"2026-08-07T11:04:06.774840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18699","last_updated":"2025-07-22T05:25:08Z","snapshot_observed_at":"2026-08-15T02:10:49.906369Z","submitted_at":"2025-02-25T23:22:12Z","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","version":3},"cited_work":{"arxiv_id":"2502.18699","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.18699","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"(2025 a ), MPO : An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment","venue":null,"work_id":"18ae4a2d-b362-4390-aae6-8d5a56cb3f78","year":2025},"citing_paper":{"arxiv_id":"2604.02507","last_updated":"2026-04-02T21:04:17Z","snapshot_observed_at":"2026-08-11T17:04:44.184917Z","submitted_at":"2026-04-02T21:04:17Z","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-05-13T20:10:43.578904Z"},"links":{"cited_paper":"/paper/2502.18699","citing_paper":"/paper/2604.02507"},"observation_digest":"sha256:d3d91979232ea375c9f7df390ad055005da1aed2ea1e2ea095dfb5df638f9a5a","observation_id":"7ea3e02c-e50d-4c52-ad21-39f5b6384708","resolution":{"observed_at":"2026-05-13T20:13:13.685684Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.18699/citation-record","integrity":"/paper/2502.18699/integrity","json":"/paper/2502.18699/citation-record.json","paper":"/paper/2502.18699"},"outbound":[],"paper":{"arxiv_id":"2502.18699","last_updated":"2025-07-22T05:25:08Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T02:10:49.906369Z","submitted_at":"2025-02-25T23:22:12Z","title":"MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference 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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2502.18699."}