{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VK6RTU7VJXXK5DJDLXOVDFJD2Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c0ab69816eb364a056b231a7266aefd1df413be74e252190e7abcb2b715aa51a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T05:42:29Z","title_canon_sha256":"ade8200456228d3abd8b8f07eb09b5243faaba49325d76fb01a007b4f143e017"},"schema_version":"1.0","source":{"id":"2507.00018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00018","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00018v2","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00018","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"VK6RTU7VJXXK","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_16","alias_value":"VK6RTU7VJXXK5DJD","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_8","alias_value":"VK6RTU7V","created_at":"2026-07-05T11:31:47Z"}],"graph_snapshots":[{"event_id":"sha256:1159af810491a7ea074d340ba68f0219e2cb01dbedf7fedba7c27d2c631539a5","target":"graph","created_at":"2026-07-05T11:31:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.00018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training processes are essential phases in grounding pre-trained language models to real-world tasks, with learning from demonstrations or preference signals playing a crucial role in this adaptation. We present a unified theoretical framework bridging Supervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training. Through rigorous mathematical derivation, we demonstrate that both SFT and preference learning methods like Direct Preference Optimization (DPO) operate within the same optimal policy-reward subspace, with SFT representing a special case of imp","authors_text":"Bo Wang, Linyang Li, Peiji Li, Qinyuan Cheng, Qipeng Guo, Rong Bao, Runyu Peng, Xipeng Qiu, Yunhua Zhou, Zhiyuan Zeng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T05:42:29Z","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00018","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5dad49830a2c3d553e6445343f248fc8b36c1f5d31045c1da153adbb2d3da2d8","target":"record","created_at":"2026-07-05T11:31:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c0ab69816eb364a056b231a7266aefd1df413be74e252190e7abcb2b715aa51a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T05:42:29Z","title_canon_sha256":"ade8200456228d3abd8b8f07eb09b5243faaba49325d76fb01a007b4f143e017"},"schema_version":"1.0","source":{"id":"2507.00018","kind":"arxiv","version":2}},"canonical_sha256":"aabd19d3f54deeae8d235ddd519523d439d5fb60d73b8ae7eb1e94ba028dbb42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aabd19d3f54deeae8d235ddd519523d439d5fb60d73b8ae7eb1e94ba028dbb42","first_computed_at":"2026-07-05T11:31:47.062724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:47.062724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y+6EAMsQZclz6hEPGepZvdGfITmYgZVqbYfNquGSr/KIFZVYLHdWlor+0HlihK1jyam1Hb6gp2T7BurA0UOXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:47.063354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dad49830a2c3d553e6445343f248fc8b36c1f5d31045c1da153adbb2d3da2d8","sha256:1159af810491a7ea074d340ba68f0219e2cb01dbedf7fedba7c27d2c631539a5"],"state_sha256":"8becdb7597fde087b11cc5d852d68ebd21171fa63321070a5f0a019cbcfe2625"}