{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7DDFUUVHB4ULHJIOXV74U7YLRH","short_pith_number":"pith:7DDFUUVH","schema_version":"1.0","canonical_sha256":"f8c65a52a70f28b3a50ebd7fca7f0b89d7081aea2ed27524f42f98d12d4a3bba","source":{"kind":"arxiv","id":"2410.17131","version":2},"attestation_state":"computed","paper":{"title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben He, Bowen Yu, Hao Xiang, Hongyu Lin, Jingren Zhou, Junyang Lin, Keming Lu, Le Sun, Xianpei Han, Yaojie Lu","submitted_at":"2024-10-22T16:04:03Z","abstract_excerpt":"The key to effective alignment lies in high-quality preference data. Recent research has focused on automated alignment, which involves developing alignment systems with minimal human intervention. However, prior research has predominantly focused on developing data generation methods, while insufficient attention has been paid to quality control mechanisms, which often produce inaccurate and unhelpful data, leading to unpredictable benefits during iterative optimization. In this paper, we present Self-Steering Optimization ($SSO$), an algorithm that autonomously generates high-quality prefere"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.17131","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T16:04:03Z","cross_cats_sorted":[],"title_canon_sha256":"a83a479d266574c3aa4f1d04ae466162540f6c5f7bc7e7056130ace2208b621d","abstract_canon_sha256":"c8c5c471b074501bf32f7967870a69bb412c214d38021ff0c8d85177c37a96f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:22.108664Z","signature_b64":"+NTsoniJeJsEb063tv/luc6IdE4mQeHm2BUN442Gu0CwL7Io0dj3ouAxMiMdV+zoYnAovr4zxHKdUHoP7sk8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c65a52a70f28b3a50ebd7fca7f0b89d7081aea2ed27524f42f98d12d4a3bba","last_reissued_at":"2026-07-05T11:19:22.108167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:22.108167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben He, Bowen Yu, Hao Xiang, Hongyu Lin, Jingren Zhou, Junyang Lin, Keming Lu, Le Sun, Xianpei Han, Yaojie Lu","submitted_at":"2024-10-22T16:04:03Z","abstract_excerpt":"The key to effective alignment lies in high-quality preference data. Recent research has focused on automated alignment, which involves developing alignment systems with minimal human intervention. However, prior research has predominantly focused on developing data generation methods, while insufficient attention has been paid to quality control mechanisms, which often produce inaccurate and unhelpful data, leading to unpredictable benefits during iterative optimization. In this paper, we present Self-Steering Optimization ($SSO$), an algorithm that autonomously generates high-quality prefere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17131","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.17131/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.17131","created_at":"2026-07-05T11:19:22.108224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17131v2","created_at":"2026-07-05T11:19:22.108224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17131","created_at":"2026-07-05T11:19:22.108224+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DDFUUVHB4UL","created_at":"2026-07-05T11:19:22.108224+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DDFUUVHB4ULHJIO","created_at":"2026-07-05T11:19:22.108224+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DDFUUVH","created_at":"2026-07-05T11:19:22.108224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.15115","citing_title":"Qwen2.5 Technical Report","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH","json":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH.json","graph_json":"https://pith.science/api/pith-number/7DDFUUVHB4ULHJIOXV74U7YLRH/graph.json","events_json":"https://pith.science/api/pith-number/7DDFUUVHB4ULHJIOXV74U7YLRH/events.json","paper":"https://pith.science/paper/7DDFUUVH"},"agent_actions":{"view_html":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH","download_json":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH.json","view_paper":"https://pith.science/paper/7DDFUUVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17131&json=true","fetch_graph":"https://pith.science/api/pith-number/7DDFUUVHB4ULHJIOXV74U7YLRH/graph.json","fetch_events":"https://pith.science/api/pith-number/7DDFUUVHB4ULHJIOXV74U7YLRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH/action/storage_attestation","attest_author":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH/action/author_attestation","sign_citation":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH/action/citation_signature","submit_replication":"https://pith.science/pith/7DDFUUVHB4ULHJIOXV74U7YLRH/action/replication_record"}},"created_at":"2026-07-05T11:19:22.108224+00:00","updated_at":"2026-07-05T11:19:22.108224+00:00"}