{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4V7E3LKMKGQR5DNQ6WPE5GUXEZ","short_pith_number":"pith:4V7E3LKM","schema_version":"1.0","canonical_sha256":"e57e4dad4c51a11e8db0f59e4e9a972654ce1b9105cadabafeb9b5bf6a069008","source":{"kind":"arxiv","id":"2411.19064","version":1},"attestation_state":"computed","paper":{"title":"Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxin Ding, Lixing Chen, Nan Cao, Pan Zhou, Shenghong Li, Yang Bai, Yang Shi, Yutong Zhang, Zhe Qu","submitted_at":"2024-11-28T11:24:43Z","abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address these challenges, this paper proposes the Way-to-Specialist (WTS) framework, which synergizes retrieval-augmented generation with knowledge graphs (KGs) to enhance the specialized capability of LLMs in "},"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":"2411.19064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-28T11:24:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29f4fdcdb94f7468abfb2df00c7068229d453eefb5c38685960e80b926cb72c6","abstract_canon_sha256":"9f9c14f374f099b8ac636e128bdbe333e8d194b6f8e9f5619221b7fa48fce655"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:56.786226Z","signature_b64":"lheo4+jojLHMkSmJezB0nHnNhQU1XXxkOyOoQYOXok0RB2wD+SjjMV5uYEZoqZxBdl3t5sSN6ktpA+7oorLRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e57e4dad4c51a11e8db0f59e4e9a972654ce1b9105cadabafeb9b5bf6a069008","last_reissued_at":"2026-07-05T09:41:56.785817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:56.785817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxin Ding, Lixing Chen, Nan Cao, Pan Zhou, Shenghong Li, Yang Bai, Yang Shi, Yutong Zhang, Zhe Qu","submitted_at":"2024-11-28T11:24:43Z","abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address these challenges, this paper proposes the Way-to-Specialist (WTS) framework, which synergizes retrieval-augmented generation with knowledge graphs (KGs) to enhance the specialized capability of LLMs in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19064","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/2411.19064/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":"2411.19064","created_at":"2026-07-05T09:41:56.785876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19064v1","created_at":"2026-07-05T09:41:56.785876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19064","created_at":"2026-07-05T09:41:56.785876+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V7E3LKMKGQR","created_at":"2026-07-05T09:41:56.785876+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V7E3LKMKGQR5DNQ","created_at":"2026-07-05T09:41:56.785876+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V7E3LKM","created_at":"2026-07-05T09:41:56.785876+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/4V7E3LKMKGQR5DNQ6WPE5GUXEZ","json":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ.json","graph_json":"https://pith.science/api/pith-number/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/graph.json","events_json":"https://pith.science/api/pith-number/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/events.json","paper":"https://pith.science/paper/4V7E3LKM"},"agent_actions":{"view_html":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ","download_json":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ.json","view_paper":"https://pith.science/paper/4V7E3LKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19064&json=true","fetch_graph":"https://pith.science/api/pith-number/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/action/storage_attestation","attest_author":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/action/author_attestation","sign_citation":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/action/citation_signature","submit_replication":"https://pith.science/pith/4V7E3LKMKGQR5DNQ6WPE5GUXEZ/action/replication_record"}},"created_at":"2026-07-05T09:41:56.785876+00:00","updated_at":"2026-07-05T09:41:56.785876+00:00"}