{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J2YO4JMAD7FCIZOX3WSWL4AZKK","short_pith_number":"pith:J2YO4JMA","schema_version":"1.0","canonical_sha256":"4eb0ee25801fca2465d7dda565f01952955c24f7ef4ff2d27065a87b0119b40e","source":{"kind":"arxiv","id":"2407.16724","version":3},"attestation_state":"computed","paper":{"title":"Structure-aware Domain Knowledge Injection for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fan Zhou, Jieping Ye, Kai Liu, Rongxin Jiang, Wei Zhang, Yaowu Chen, Yue Wu, Ze Chen, Zhihang Fu","submitted_at":"2024-07-23T12:38:48Z","abstract_excerpt":"This paper introduces a pioneering methodology, termed StructTuning, to efficiently transform foundation Large Language Models (LLMs) into domain specialists. It significantly reduces the training corpus needs to a mere 5% while achieving an impressive 100% of traditional knowledge injection performance. Motivated by structured human education, we propose a novel two-stage strategy for knowledge injection and alignment: Structure-aware Continual Pre-Training (SCPT) and Structure-aware Supervised Fine-Tuning (SSFT). In the SCPT phase, we automatically extract the domain knowledge taxonomy and r"},"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":"2407.16724","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T12:38:48Z","cross_cats_sorted":[],"title_canon_sha256":"1b884478df78666258abbe05c814d367c6c38197e956683b9f40260ee5260cc3","abstract_canon_sha256":"ec408cd8d9499f48f8b665ca6d2fb651109d9b3696dadf2284536ef3abb15996"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:43.793769Z","signature_b64":"4iBLSGC9hbJkWX2Tqd7URH89oJqh/610cq/63DrTTi7wIQy4NMePGDGIBPPj8HfFLuiEjTY2vs8WLGmM6YT2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb0ee25801fca2465d7dda565f01952955c24f7ef4ff2d27065a87b0119b40e","last_reissued_at":"2026-07-05T10:14:43.793268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:43.793268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-aware Domain Knowledge Injection for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fan Zhou, Jieping Ye, Kai Liu, Rongxin Jiang, Wei Zhang, Yaowu Chen, Yue Wu, Ze Chen, Zhihang Fu","submitted_at":"2024-07-23T12:38:48Z","abstract_excerpt":"This paper introduces a pioneering methodology, termed StructTuning, to efficiently transform foundation Large Language Models (LLMs) into domain specialists. It significantly reduces the training corpus needs to a mere 5% while achieving an impressive 100% of traditional knowledge injection performance. Motivated by structured human education, we propose a novel two-stage strategy for knowledge injection and alignment: Structure-aware Continual Pre-Training (SCPT) and Structure-aware Supervised Fine-Tuning (SSFT). In the SCPT phase, we automatically extract the domain knowledge taxonomy and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16724","kind":"arxiv","version":3},"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/2407.16724/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":"2407.16724","created_at":"2026-07-05T10:14:43.793325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16724v3","created_at":"2026-07-05T10:14:43.793325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16724","created_at":"2026-07-05T10:14:43.793325+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2YO4JMAD7FC","created_at":"2026-07-05T10:14:43.793325+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2YO4JMAD7FCIZOX","created_at":"2026-07-05T10:14:43.793325+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2YO4JMA","created_at":"2026-07-05T10:14:43.793325+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/J2YO4JMAD7FCIZOX3WSWL4AZKK","json":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK.json","graph_json":"https://pith.science/api/pith-number/J2YO4JMAD7FCIZOX3WSWL4AZKK/graph.json","events_json":"https://pith.science/api/pith-number/J2YO4JMAD7FCIZOX3WSWL4AZKK/events.json","paper":"https://pith.science/paper/J2YO4JMA"},"agent_actions":{"view_html":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK","download_json":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK.json","view_paper":"https://pith.science/paper/J2YO4JMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16724&json=true","fetch_graph":"https://pith.science/api/pith-number/J2YO4JMAD7FCIZOX3WSWL4AZKK/graph.json","fetch_events":"https://pith.science/api/pith-number/J2YO4JMAD7FCIZOX3WSWL4AZKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK/action/storage_attestation","attest_author":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK/action/author_attestation","sign_citation":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK/action/citation_signature","submit_replication":"https://pith.science/pith/J2YO4JMAD7FCIZOX3WSWL4AZKK/action/replication_record"}},"created_at":"2026-07-05T10:14:43.793325+00:00","updated_at":"2026-07-05T10:14:43.793325+00:00"}