{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4PCQGAQ6XIR7PCMFCZCETVISLF","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":"a561e5c0a18811c4f0b1f42a9d385b859d2ba0054f48164bb971967e1cc79dde","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:23:28Z","title_canon_sha256":"854bc5de725565d1885a95fb6d753221357df08adbcb7fe5296ae7013800e1ef"},"schema_version":"1.0","source":{"id":"2405.11870","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11870","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11870v3","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11870","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_12","alias_value":"4PCQGAQ6XIR7","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_16","alias_value":"4PCQGAQ6XIR7PCMF","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_8","alias_value":"4PCQGAQ6","created_at":"2026-07-05T11:36:20Z"}],"graph_snapshots":[{"event_id":"sha256:62a515a3369e12f7c3a87d4064e6381ce0df028479628ae9b5a46969630a3de3","target":"graph","created_at":"2026-07-05T11:36:20Z","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/2405.11870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models (LMs) with human preferences post pre-training. While SFT excels in efficiency and PO in effectiveness, they are often combined sequentially without integrating their optimization objectives. This approach ignores the opportunities to bridge their paradigm gap and take the strengths from both. In this paper, we interpret SFT and PO with two sub-processes -- Preference Estimation and Transition Optimization -- defined at token level within the Markov Decision Process (MDP). This modeling","authors_text":"Biqing Qi, Bowen Zhou, Ermo Hua, Kai Tian, Kaiyan Zhang, Ning Ding, Xingtai Lv","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:23:28Z","title":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11870","kind":"arxiv","version":3},"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":"sha256:3f97a515b0feabc2348b8fa23ad67d1cb6ebc6fe00227b75c9c7cdfb52a9bcb4","target":"record","created_at":"2026-07-05T11:36:20Z","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":"a561e5c0a18811c4f0b1f42a9d385b859d2ba0054f48164bb971967e1cc79dde","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:23:28Z","title_canon_sha256":"854bc5de725565d1885a95fb6d753221357df08adbcb7fe5296ae7013800e1ef"},"schema_version":"1.0","source":{"id":"2405.11870","kind":"arxiv","version":3}},"canonical_sha256":"e3c503021eba23f78985164449d5125942c8e13ba9a71c90fccbba56fd60fc75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3c503021eba23f78985164449d5125942c8e13ba9a71c90fccbba56fd60fc75","first_computed_at":"2026-07-05T11:36:20.316255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:20.316255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KTzmGz7fYxQ8bBkIPHaA13eLloV4hCC/9fSem7GFEX/BJGweigvpecijY1ndrfmxDbEe+jFwTgSyMNGVxEBaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:20.316963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11870","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f97a515b0feabc2348b8fa23ad67d1cb6ebc6fe00227b75c9c7cdfb52a9bcb4","sha256:62a515a3369e12f7c3a87d4064e6381ce0df028479628ae9b5a46969630a3de3"],"state_sha256":"b360a78fad5bd59049cf99e37866f1ba9e87c83e9f59e10acc075fff4f8f9372"}