{"as_of":"2026-08-21T19:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9c5e4c200233f8fcd49f7d0b2746433eb5c59f4adc9c9c3daf9fe59e85b57dac","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":"2026-08-21T06:32:19.484+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":"2026-08-08T22:36:35.241972Z","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":"2026-05-25T05:05:23.114663Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.16430","last_updated":"2024-03-25T06:32:49Z","snapshot_observed_at":"2026-08-21T10:57:04.533622Z","submitted_at":"2023-12-27T06:34:54Z","title":"Preference as Reward, Maximum Preference Optimization with Importance Sampling","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.16430","snapshot_observed_at":"2026-08-08T22:36:35.241972Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.04498","last_updated":"2025-02-06T20:57:36Z","snapshot_observed_at":"2026-08-13T05:00:36.654030Z","submitted_at":"2025-02-06T20:57:36Z","title":"Verifiable Format Control for Large Language Model Generations","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T22:36:35.241972Z"},"links":{"cited_paper":"/paper/2312.16430","citing_paper":"/paper/2502.04498"},"observation_digest":"sha256:609389ea3633dcb057ff6a4c0e2419d098c65dc542d47e07a6ec02464cb9249e","observation_id":"d6bd876a-41a0-4e90-aa9a-60e71b132304","resolution":{"observed_at":"2026-08-08T22:36:35.241972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.16430","last_updated":"2024-03-25T06:32:49Z","snapshot_observed_at":"2026-08-21T10:57:04.533622Z","submitted_at":"2023-12-27T06:34:54Z","title":"Preference as Reward, Maximum Preference Optimization with Importance Sampling","version":5},"cited_work":{"arxiv_id":"2312.16430","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.16430","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2312.16430 , year=","venue":null,"work_id":"b7d6a30b-9b66-4755-bec9-c61db6d2c076","year":null},"citing_paper":{"arxiv_id":"2605.23244","last_updated":"2026-05-22T05:25:00Z","snapshot_observed_at":"2026-08-15T08:23:12.242169Z","submitted_at":"2026-05-22T05:25:00Z","title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-05-25T05:01:31.560963Z"},"links":{"cited_paper":"/paper/2312.16430","citing_paper":"/paper/2605.23244"},"observation_digest":"sha256:125f3bc555838f23dc09a3d061c70415cc3719e9be5d2902f8b9a9fe4a90076e","observation_id":"27bbe9cd-5cc9-4f21-a05b-92b83ff28012","resolution":{"observed_at":"2026-05-25T05:05:23.117586Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.16430/citation-record","integrity":"/paper/2312.16430/integrity","json":"/paper/2312.16430/citation-record.json","paper":"/paper/2312.16430"},"outbound":[],"paper":{"arxiv_id":"2312.16430","last_updated":"2024-03-25T06:32:49Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-21T10:57:04.533622Z","submitted_at":"2023-12-27T06:34:54Z","title":"Preference as Reward, Maximum Preference Optimization with Importance Sampling"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2312.16430."}