{"as_of":"2026-08-07T19:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a17e6bfd945be428628d874798e8b6bc1e07fa7daf92a7f534f1c710bb41aad7","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T00:54:49.821661Z","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":"2026-07-04T07:59:40.183441Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.05193","last_updated":"2024-11-27T00:05:44Z","snapshot_observed_at":"2026-08-04T22:49:27.294856Z","submitted_at":"2024-11-07T21:36:52Z","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.05193","snapshot_observed_at":"2026-08-07T00:54:49.821661Z","title":"Dragan, and Sergey Levine","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.00018","last_updated":"2025-07-04T08:16:16Z","snapshot_observed_at":"2026-08-07T00:41:17.848176Z","submitted_at":"2025-06-15T05:42:29Z","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T00:54:49.821661Z"},"links":{"cited_paper":"/paper/2411.05193","citing_paper":"/paper/2507.00018"},"observation_digest":"sha256:f53f4fd46fb24947dcccc85f6ce2b905baf18d8eeea3573fb7d05a7e82cbe659","observation_id":"f97dd5a8-7a18-4ff5-b2f4-fbb033ad99b5","resolution":{"observed_at":"2026-08-07T00:54:49.821661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05193","last_updated":"2024-11-27T00:05:44Z","snapshot_observed_at":"2026-08-04T22:49:27.294856Z","submitted_at":"2024-11-07T21:36:52Z","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2411.05193","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.05193","snapshot_observed_at":"2026-07-04T07:59:40.183441Z","title":null,"venue":null,"work_id":"da35bdb4-aac0-4c1e-a406-141d019b979e","year":2024},"citing_paper":{"arxiv_id":"2606.21943","last_updated":"2026-06-20T08:20:41Z","snapshot_observed_at":"2026-07-06T23:56:54.959593Z","submitted_at":"2026-06-20T08:20:41Z","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-06-26T12:15:08.304150Z"},"links":{"cited_paper":"/paper/2411.05193","citing_paper":"/paper/2606.21943"},"observation_digest":"sha256:88ad5b196bd502d1be015c3e69c5743fdc4713cee9e41ef86b1fef867b8e45cb","observation_id":"7bfc2373-26c3-421d-bc93-94b66b9ae816","resolution":{"observed_at":"2026-07-04T07:59:40.184749Z","resolver_source":"arxiv_id","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/2411.05193/citation-record","integrity":"/paper/2411.05193/integrity","json":"/paper/2411.05193/citation-record.json","paper":"/paper/2411.05193"},"outbound":[],"paper":{"arxiv_id":"2411.05193","last_updated":"2024-11-27T00:05:44Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T22:49:27.294856Z","submitted_at":"2024-11-07T21:36:52Z","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning"},"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 2 inbound Pith citation observations for arXiv:2411.05193."}