{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J2YO4JMAD7FCIZOX3WSWL4AZKK","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":"ec408cd8d9499f48f8b665ca6d2fb651109d9b3696dadf2284536ef3abb15996","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T12:38:48Z","title_canon_sha256":"1b884478df78666258abbe05c814d367c6c38197e956683b9f40260ee5260cc3"},"schema_version":"1.0","source":{"id":"2407.16724","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16724","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16724v3","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16724","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"J2YO4JMAD7FC","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"J2YO4JMAD7FCIZOX","created_at":"2026-07-05T10:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"J2YO4JMA","created_at":"2026-07-05T10:14:43Z"}],"graph_snapshots":[{"event_id":"sha256:06db4a3eff30459103d6d62b1d114a018242a34460f2b3cf2a0beeae5b52672a","target":"graph","created_at":"2026-07-05T10:14:43Z","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/2407.16724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fan Zhou, Jieping Ye, Kai Liu, Rongxin Jiang, Wei Zhang, Yaowu Chen, Yue Wu, Ze Chen, Zhihang Fu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T12:38:48Z","title":"Structure-aware Domain Knowledge Injection for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16724","kind":"arxiv","version":3},"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":"sha256:7674f592ff9e10986f3fc9f0dc5fba57be0e0cf51a859f38901fb27a72c30bf2","target":"record","created_at":"2026-07-05T10:14:43Z","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":"ec408cd8d9499f48f8b665ca6d2fb651109d9b3696dadf2284536ef3abb15996","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T12:38:48Z","title_canon_sha256":"1b884478df78666258abbe05c814d367c6c38197e956683b9f40260ee5260cc3"},"schema_version":"1.0","source":{"id":"2407.16724","kind":"arxiv","version":3}},"canonical_sha256":"4eb0ee25801fca2465d7dda565f01952955c24f7ef4ff2d27065a87b0119b40e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eb0ee25801fca2465d7dda565f01952955c24f7ef4ff2d27065a87b0119b40e","first_computed_at":"2026-07-05T10:14:43.793268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:43.793268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4iBLSGC9hbJkWX2Tqd7URH89oJqh/610cq/63DrTTi7wIQy4NMePGDGIBPPj8HfFLuiEjTY2vs8WLGmM6YT2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:43.793769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16724","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7674f592ff9e10986f3fc9f0dc5fba57be0e0cf51a859f38901fb27a72c30bf2","sha256:06db4a3eff30459103d6d62b1d114a018242a34460f2b3cf2a0beeae5b52672a"],"state_sha256":"d0e7353f2cfabd77e57bcd42e20c73dcbe315714f2257621da8968347267d181"}