{"as_of":"2026-08-07T21:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:46cb51a0432c85fb39ae65c1fe19717437fe24ef8c6747df14032b44088a608c","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:40:17.941137Z","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":"2026-08-06T13:49:14.274811Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.03650","last_updated":"2024-10-03T17:13:04Z","snapshot_observed_at":"2026-08-03T13:15:41.992380Z","submitted_at":"2024-09-05T16:08:19Z","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.03650","snapshot_observed_at":"2026-08-07T05:40:17.941137Z","title":"On the limited generalization capability of the implicit reward model induced by direct preference optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07492","last_updated":"2025-06-09T07:11:01Z","snapshot_observed_at":"2026-08-07T05:29:54.015791Z","submitted_at":"2025-06-09T07:11:01Z","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T05:40:17.941137Z"},"links":{"cited_paper":"/paper/2409.03650","citing_paper":"/paper/2506.07492"},"observation_digest":"sha256:04165b3e1d87fb8971de9087f82744d17c0e587be0a5e3bc60d10a059eb7267d","observation_id":"08f0ace7-0ead-474d-aaaf-3a7fb6b1e2fe","resolution":{"observed_at":"2026-08-07T05:40:17.941137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.03650","last_updated":"2024-10-03T17:13:04Z","snapshot_observed_at":"2026-08-03T13:15:41.992380Z","submitted_at":"2024-09-05T16:08:19Z","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.03650","snapshot_observed_at":"2026-08-07T05:14:47.346879Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.08446","last_updated":"2025-06-10T04:44:28Z","snapshot_observed_at":"2026-08-07T09:15:20.058485Z","submitted_at":"2025-06-10T04:44:28Z","title":"A Survey on Large Language Models for Mathematical Reasoning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T05:14:47.346879Z"},"links":{"cited_paper":"/paper/2409.03650","citing_paper":"/paper/2506.08446"},"observation_digest":"sha256:3ea88e7deecb2b1a2e2de55bac7b2fc431732762bfb9bbe5deedc47df56b09dd","observation_id":"90df85d0-0cb4-48ec-a842-12ca096028a7","resolution":{"observed_at":"2026-08-07T05:14:47.346879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.03650","last_updated":"2024-10-03T17:13:04Z","snapshot_observed_at":"2026-08-03T13:15:41.992380Z","submitted_at":"2024-09-05T16:08:19Z","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","version":2},"cited_work":{"arxiv_id":"2409.03650","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.03650","snapshot_observed_at":"2026-08-06T13:49:14.274811Z","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","venue":"cs.LG","work_id":"625bc30a-47a0-4de3-9235-590d9e9c3f44","year":2024},"citing_paper":{"arxiv_id":"2507.20181","last_updated":"2025-07-27T08:55:40Z","snapshot_observed_at":"2026-08-06T13:49:07.681314Z","submitted_at":"2025-07-27T08:55:40Z","title":"SGPO: Self-Generated Preference Optimization based on Self-Improver","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T13:49:11.026985Z"},"links":{"cited_paper":"/paper/2409.03650","citing_paper":"/paper/2507.20181"},"observation_digest":"sha256:f9061d4f47903a9e6aa0071d636908ab5d27e465ae0aa0fcb04be39af7e5e92a","observation_id":"fe9e3cb7-3729-47c1-9aab-1d4e935edfe0","resolution":{"observed_at":"2026-08-06T13:49:14.414833Z","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/2409.03650/citation-record","integrity":"/paper/2409.03650/integrity","json":"/paper/2409.03650/citation-record.json","paper":"/paper/2409.03650"},"outbound":[],"paper":{"arxiv_id":"2409.03650","last_updated":"2024-10-03T17:13:04Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T13:15:41.992380Z","submitted_at":"2024-09-05T16:08:19Z","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization"},"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 3 inbound Pith citation observations for arXiv:2409.03650."}