{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2YS5YSMHHBVSWG4NL5LLBO3ZPT","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":"e833a017edc5fc3ada0775388dc2d1f7828fd512f73f5691483fd113f7763984","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-21T12:47:17Z","title_canon_sha256":"ae7e60cc2acdc9a73a99d5a95562ca3a13b8d6df6b4c87218b7cbe4d579eeab3"},"schema_version":"1.0","source":{"id":"2405.12739","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12739","created_at":"2026-07-05T09:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12739v2","created_at":"2026-07-05T09:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12739","created_at":"2026-07-05T09:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"2YS5YSMHHBVS","created_at":"2026-07-05T09:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"2YS5YSMHHBVSWG4N","created_at":"2026-07-05T09:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"2YS5YSMH","created_at":"2026-07-05T09:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:fb5e87952890b3e08bedbe04ffd29203a1d11d428b1fa86ad1546417a2505490","target":"graph","created_at":"2026-07-05T09:19:09Z","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/2405.12739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with the complexity of managing multiple reward models. To address these issues, we propose Sequential Preference Optimization (SPO), a method that sequentially fine-tunes LLMs to align with multiple dimensions of human preferences. SPO avoids explicit reward modeling, directly optimizing the models to align with nuanced human preferences. We theoretically deriv","authors_text":"Dong Yan, Jian Xie, Junge Zhang, Kaiqi Huang, Lifeng Liu, Xingzhou Lou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-21T12:47:17Z","title":"SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12739","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":"sha256:5df947895da48c3f19e67d879bd35240482fdbf0882df639498d8e9fb3be7667","target":"record","created_at":"2026-07-05T09:19:09Z","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":"e833a017edc5fc3ada0775388dc2d1f7828fd512f73f5691483fd113f7763984","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-21T12:47:17Z","title_canon_sha256":"ae7e60cc2acdc9a73a99d5a95562ca3a13b8d6df6b4c87218b7cbe4d579eeab3"},"schema_version":"1.0","source":{"id":"2405.12739","kind":"arxiv","version":2}},"canonical_sha256":"d625dc4987386b2b1b8d5f56b0bb797cdb8e41b8f761376763b1f7d2f9c0b33c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d625dc4987386b2b1b8d5f56b0bb797cdb8e41b8f761376763b1f7d2f9c0b33c","first_computed_at":"2026-07-05T09:19:09.730514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:09.730514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RK43WAzccnEtROWv+SPPL2VdTOSf+PfAivOWcR7kfSYhXJ6TfcGjUobzvmTxNUsD+JawFYjsRFs0OVhd+P4fCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:09.731041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12739","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5df947895da48c3f19e67d879bd35240482fdbf0882df639498d8e9fb3be7667","sha256:fb5e87952890b3e08bedbe04ffd29203a1d11d428b1fa86ad1546417a2505490"],"state_sha256":"d6189003f3cd11092cde24941dbc7c6a9a380eec65ef0548d1d0b6ab67b68845"}