{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PC3PG6RQNNLPMNJ3EOOOU2OWYA","short_pith_number":"pith:PC3PG6RQ","schema_version":"1.0","canonical_sha256":"78b6f37a306b56f6353b239cea69d6c0252ae7c9b4f6e7c1daf6f6a2a4e99d3b","source":{"kind":"arxiv","id":"2407.16154","version":1},"attestation_state":"computed","paper":{"title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chenchen Zhang, Congnan Liu, Ge Zhang, Haoran Que, Jiaheng Liu, Jiakai Wang, Jiamang Wang, Jie Liu, Jinyang Guo, Ken Deng, Lin Qu, Wenbo Su, Yanan Wu, Yuanxing Zhang, Zhiqi Bai","submitted_at":"2024-07-23T03:47:28Z","abstract_excerpt":"Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve the performance of a smaller LLM (i.e., the student model) by transferring knowledge from a high-performing LLM (i.e., the teacher model). Prevailing techniques in LLM distillation typically use a black-box model API to generate high-quality pretrained and aligned datasets, or utilize white-box distillation by altering the loss function to better transfer kn"},"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":"2407.16154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T03:47:28Z","cross_cats_sorted":[],"title_canon_sha256":"dd1378e7e9de5ad6cd27bc9caa162f92ce80ce32a00a5835ff70798f5c8660c2","abstract_canon_sha256":"11f8dc602529ed3d01af149cc23179fb577869b8743db13adc241bdfc4532434"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:28.013831Z","signature_b64":"Ftr+HqRA7f3SG/Ev0Vk2akiUhzLbS4hTLGD6H9Kzd3uR20THNMFfEtWeI/YbBlu/mLAoR+rq6Bq5poV+Z/NaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78b6f37a306b56f6353b239cea69d6c0252ae7c9b4f6e7c1daf6f6a2a4e99d3b","last_reissued_at":"2026-07-05T08:47:28.013448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:28.013448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chenchen Zhang, Congnan Liu, Ge Zhang, Haoran Que, Jiaheng Liu, Jiakai Wang, Jiamang Wang, Jie Liu, Jinyang Guo, Ken Deng, Lin Qu, Wenbo Su, Yanan Wu, Yuanxing Zhang, Zhiqi Bai","submitted_at":"2024-07-23T03:47:28Z","abstract_excerpt":"Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve the performance of a smaller LLM (i.e., the student model) by transferring knowledge from a high-performing LLM (i.e., the teacher model). Prevailing techniques in LLM distillation typically use a black-box model API to generate high-quality pretrained and aligned datasets, or utilize white-box distillation by altering the loss function to better transfer kn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16154","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/2407.16154/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":"2407.16154","created_at":"2026-07-05T08:47:28.013503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16154v1","created_at":"2026-07-05T08:47:28.013503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16154","created_at":"2026-07-05T08:47:28.013503+00:00"},{"alias_kind":"pith_short_12","alias_value":"PC3PG6RQNNLP","created_at":"2026-07-05T08:47:28.013503+00:00"},{"alias_kind":"pith_short_16","alias_value":"PC3PG6RQNNLPMNJ3","created_at":"2026-07-05T08:47:28.013503+00:00"},{"alias_kind":"pith_short_8","alias_value":"PC3PG6RQ","created_at":"2026-07-05T08:47:28.013503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05716","citing_title":"A Survey of the State-of-the-Art in Conversational Question Answering Systems","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA","json":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA.json","graph_json":"https://pith.science/api/pith-number/PC3PG6RQNNLPMNJ3EOOOU2OWYA/graph.json","events_json":"https://pith.science/api/pith-number/PC3PG6RQNNLPMNJ3EOOOU2OWYA/events.json","paper":"https://pith.science/paper/PC3PG6RQ"},"agent_actions":{"view_html":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA","download_json":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA.json","view_paper":"https://pith.science/paper/PC3PG6RQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16154&json=true","fetch_graph":"https://pith.science/api/pith-number/PC3PG6RQNNLPMNJ3EOOOU2OWYA/graph.json","fetch_events":"https://pith.science/api/pith-number/PC3PG6RQNNLPMNJ3EOOOU2OWYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA/action/storage_attestation","attest_author":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA/action/author_attestation","sign_citation":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA/action/citation_signature","submit_replication":"https://pith.science/pith/PC3PG6RQNNLPMNJ3EOOOU2OWYA/action/replication_record"}},"created_at":"2026-07-05T08:47:28.013503+00:00","updated_at":"2026-07-05T08:47:28.013503+00:00"}