{"as_of":"2026-08-05T12:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f0a5aadcacfb848158f6c7e7b7df84326f75bcca41be40292e66abc511e1266e","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":"2026-08-05T06:32:48.257954+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":"2026-08-03T06:52:56.188957Z","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":"2026-05-19T01:16:57.081496Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.21438","last_updated":"2026-05-07T19:45:35Z","snapshot_observed_at":"2026-07-06T19:41:06.495019Z","submitted_at":"2024-10-28T18:34:25Z","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function","version":3},"cited_work":{"arxiv_id":"2410.21438","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.21438","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function","venue":"cs.CL","work_id":"74923039-4a54-4a44-8232-d7000e8d9503","year":2024},"citing_paper":{"arxiv_id":"2508.00222","last_updated":"2026-04-15T11:41:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-31T23:55:29Z","title":"RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-19T01:15:49.658412Z"},"links":{"cited_paper":"/paper/2410.21438","citing_paper":"/paper/2508.00222"},"observation_digest":"sha256:d39dabe45a42f0df49b6022cf21f600bc1145d13f8806cb8b4b96b8cea70860a","observation_id":"7e1e3c82-2fa3-4b9b-8617-47f0d56dc2e1","resolution":{"observed_at":"2026-05-19T01:16:57.084581Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21438","last_updated":"2026-05-07T19:45:35Z","snapshot_observed_at":"2026-07-06T19:41:06.495019Z","submitted_at":"2024-10-28T18:34:25Z","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21438","snapshot_observed_at":"2026-08-03T06:52:56.188957Z","title":"Uft: Unifying fine-tuning of sft and rlhf/dpo/una through a generalized implicit reward function","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.21909","last_updated":"2026-05-28T16:50:42Z","snapshot_observed_at":"2026-08-03T06:52:36.202528Z","submitted_at":"2026-01-29T16:00:48Z","title":"From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-03T06:52:56.188957Z"},"links":{"cited_paper":"/paper/2410.21438","citing_paper":"/paper/2601.21909"},"observation_digest":"sha256:a72974567064e8466383b16b38882901cb8a063d2e540b92f5429e69f6d6be03","observation_id":"3b9fa72b-c343-4503-a22c-74467f29fb60","resolution":{"observed_at":"2026-08-03T06:52:56.188957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21438","last_updated":"2026-05-07T19:45:35Z","snapshot_observed_at":"2026-07-06T19:41:06.495019Z","submitted_at":"2024-10-28T18:34:25Z","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function","version":3},"cited_work":{"arxiv_id":"2410.21438","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.21438","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function","venue":"cs.CL","work_id":"74923039-4a54-4a44-8232-d7000e8d9503","year":2024},"citing_paper":{"arxiv_id":"2605.06632","last_updated":"2026-05-07T17:44:07Z","snapshot_observed_at":"2026-07-30T07:26:22.311737Z","submitted_at":"2026-05-07T17:44:07Z","title":"Crafting Reversible SFT Behaviors in Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-08T12:16:16.104176Z"},"links":{"cited_paper":"/paper/2410.21438","citing_paper":"/paper/2605.06632"},"observation_digest":"sha256:dfb2eacd24fde04f4e026564bfff085d4460a4a3726a1a0ea37fcf5dc2f9e791","observation_id":"4892f287-79a0-4f44-9379-3d1721e0090e","resolution":{"observed_at":"2026-05-11T19:21:07.387461Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.21438/citation-record","integrity":"/paper/2410.21438/integrity","json":"/paper/2410.21438/citation-record.json","paper":"/paper/2410.21438"},"outbound":[],"paper":{"arxiv_id":"2410.21438","last_updated":"2026-05-07T19:45:35Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T19:41:06.495019Z","submitted_at":"2024-10-28T18:34:25Z","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.21438."}