{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7LB3ORAHDWPAMRQLMJNNOQD76G","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":"99f5d28024a625d5f06ab0793aea5b25b4793895ae506801a6c6aea44f2c9173","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T14:57:31Z","title_canon_sha256":"ee2002f3a17b1aabcf2e96d47177173e215e93255e73781d0b6086e5349422b4"},"schema_version":"1.0","source":{"id":"2410.06961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06961","created_at":"2026-07-05T09:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06961v1","created_at":"2026-07-05T09:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06961","created_at":"2026-07-05T09:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"7LB3ORAHDWPA","created_at":"2026-07-05T09:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"7LB3ORAHDWPAMRQL","created_at":"2026-07-05T09:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"7LB3ORAH","created_at":"2026-07-05T09:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:f2f38c922737ee26885d834fa24796c1df21f334aad3d7962a803c6258380bc8","target":"graph","created_at":"2026-07-05T09:18:09Z","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/2410.06961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Through alignment with human preferences, Large Language Models (LLMs) have advanced significantly in generating honest, harmless, and helpful responses. However, collecting high-quality preference data is a resource-intensive and creativity-demanding process, especially for the continual improvement of LLMs. We introduce SynPO, a self-boosting paradigm that leverages synthetic preference data for model alignment. SynPO employs an iterative mechanism wherein a self-prompt generator creates diverse prompts, and a response improver refines model responses progressively. This approach trains LLMs","authors_text":"Furu Wei, Li Dong, Qingxiu Dong, Xingxing Zhang, Zhifang Sui","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T14:57:31Z","title":"Self-Boosting Large Language Models with Synthetic Preference Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06961","kind":"arxiv","version":1},"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":"sha256:1142aa19ce0be7f7b90e83a4a03881b310f09e72081508341ffde901374c94fc","target":"record","created_at":"2026-07-05T09:18:09Z","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":"99f5d28024a625d5f06ab0793aea5b25b4793895ae506801a6c6aea44f2c9173","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T14:57:31Z","title_canon_sha256":"ee2002f3a17b1aabcf2e96d47177173e215e93255e73781d0b6086e5349422b4"},"schema_version":"1.0","source":{"id":"2410.06961","kind":"arxiv","version":1}},"canonical_sha256":"fac3b744071d9e06460b625ad7407ff197c0454bc73fa045f460069027089ed8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fac3b744071d9e06460b625ad7407ff197c0454bc73fa045f460069027089ed8","first_computed_at":"2026-07-05T09:18:09.026478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:09.026478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bkvseT2YWTejETPU9v7zZMkgM/La1hHPvHrRgbfbdg3CEQzz+TIpnXNWchSVH4wtcJTJJNMErErfUinYU2wmCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:09.026873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1142aa19ce0be7f7b90e83a4a03881b310f09e72081508341ffde901374c94fc","sha256:f2f38c922737ee26885d834fa24796c1df21f334aad3d7962a803c6258380bc8"],"state_sha256":"a5b2069d5e248e811c8078c8564503df3f664ff1a6d0b83470ec45dd43b7cf79"}