{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PFZUUTEPDVKPFSEN7PEQEHFRM4","short_pith_number":"pith:PFZUUTEP","schema_version":"1.0","canonical_sha256":"79734a4c8f1d54f2c88dfbc9021cb167277132c8970d7ea71c80f479e98cbdcb","source":{"kind":"arxiv","id":"2501.12273","version":1},"attestation_state":"computed","paper":{"title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuyu Zhang, Haodong Duan, Kai Chen, Maosong Cao, Mo Li, Songyang Zhang, Taolin Zhang, Yunxin Liu","submitted_at":"2025-01-21T16:44:12Z","abstract_excerpt":"The quality of Supervised Fine-Tuning (SFT) data plays a critical role in enhancing the conversational capabilities of Large Language Models (LLMs). However, as LLMs become more advanced, the availability of high-quality human-annotated SFT data has become a significant bottleneck, necessitating a greater reliance on synthetic training data. In this work, we introduce Condor, a novel two-stage synthetic data generation framework that incorporates World Knowledge Tree and Self-Reflection Refinement to produce high-quality SFT data at scale. Our experimental results demonstrate that a base model"},"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":"2501.12273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T16:44:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6fea86b218a039666f23c74facf2c4a6bf8961de838113804222c81203af95d","abstract_canon_sha256":"575c033b3920725c4fd29666044d878bd88fc886f4d6b8d3178a50c1369c4a5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:33.930690Z","signature_b64":"4v+wYvlJralVDEW20xd4ed6vwWPH9nv0Smhhm6t88Uf++zRzXCYzwOuJCoJoYDAk0KEaa7i+wIyIHVshT7IoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79734a4c8f1d54f2c88dfbc9021cb167277132c8970d7ea71c80f479e98cbdcb","last_reissued_at":"2026-07-05T10:03:33.930284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:33.930284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuyu Zhang, Haodong Duan, Kai Chen, Maosong Cao, Mo Li, Songyang Zhang, Taolin Zhang, Yunxin Liu","submitted_at":"2025-01-21T16:44:12Z","abstract_excerpt":"The quality of Supervised Fine-Tuning (SFT) data plays a critical role in enhancing the conversational capabilities of Large Language Models (LLMs). However, as LLMs become more advanced, the availability of high-quality human-annotated SFT data has become a significant bottleneck, necessitating a greater reliance on synthetic training data. In this work, we introduce Condor, a novel two-stage synthetic data generation framework that incorporates World Knowledge Tree and Self-Reflection Refinement to produce high-quality SFT data at scale. Our experimental results demonstrate that a base model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12273","kind":"arxiv","version":1},"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/2501.12273/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":"2501.12273","created_at":"2026-07-05T10:03:33.930345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12273v1","created_at":"2026-07-05T10:03:33.930345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12273","created_at":"2026-07-05T10:03:33.930345+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFZUUTEPDVKP","created_at":"2026-07-05T10:03:33.930345+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFZUUTEPDVKPFSEN","created_at":"2026-07-05T10:03:33.930345+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFZUUTEP","created_at":"2026-07-05T10:03:33.930345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4","json":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4.json","graph_json":"https://pith.science/api/pith-number/PFZUUTEPDVKPFSEN7PEQEHFRM4/graph.json","events_json":"https://pith.science/api/pith-number/PFZUUTEPDVKPFSEN7PEQEHFRM4/events.json","paper":"https://pith.science/paper/PFZUUTEP"},"agent_actions":{"view_html":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4","download_json":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4.json","view_paper":"https://pith.science/paper/PFZUUTEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12273&json=true","fetch_graph":"https://pith.science/api/pith-number/PFZUUTEPDVKPFSEN7PEQEHFRM4/graph.json","fetch_events":"https://pith.science/api/pith-number/PFZUUTEPDVKPFSEN7PEQEHFRM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4/action/storage_attestation","attest_author":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4/action/author_attestation","sign_citation":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4/action/citation_signature","submit_replication":"https://pith.science/pith/PFZUUTEPDVKPFSEN7PEQEHFRM4/action/replication_record"}},"created_at":"2026-07-05T10:03:33.930345+00:00","updated_at":"2026-07-05T10:03:33.930345+00:00"}