{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LHX2CXBB3EJDUB4ZEV2TDE6YZG","short_pith_number":"pith:LHX2CXBB","schema_version":"1.0","canonical_sha256":"59efa15c21d9123a079925753193d8c9b30b0e7e8813d2e71e1b957c1ab904dd","source":{"kind":"arxiv","id":"2009.09152","version":3},"attestation_state":"computed","paper":{"title":"Weight Distillation: Transferring the Knowledge in Neural Network Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Li, Jingbo Zhu, Quan Du, Tong Xiao, Yanyang Li, Ye Lin, Ziyang Wang","submitted_at":"2020-09-19T03:23:26Z","abstract_excerpt":"Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. Recent successes in pre-training suggest the effectiveness of transferring model parameters. Inspired by this, we investigate methods of model acceleration and compression in another line of research. We propose Weight Distillation to transfer the knowledge in the large network parameters through a parameter generator. Our experiments on WMT16 En-Ro, NIST12 Zh-En, and WMT14 En-De machine translation tasks show that we"},"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":"2009.09152","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-19T03:23:26Z","cross_cats_sorted":[],"title_canon_sha256":"66e46dd7f06da18cb2c31279e987a49cebc7ba187a3d88f43c5310d413abdd7d","abstract_canon_sha256":"a6d78eb48247d159b54893ab2c4487d6ad381cbc44311f679a39af43e44e415b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:36.639102Z","signature_b64":"AG+DE6wUfvzE5/MTArbKY3s2gKxXjU5bi1aWe4hroNeUk2dPeIxdyuWdipXrsS8JfK1ly52AyftNGbi+PPEoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59efa15c21d9123a079925753193d8c9b30b0e7e8813d2e71e1b957c1ab904dd","last_reissued_at":"2026-07-05T02:58:36.638545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:36.638545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weight Distillation: Transferring the Knowledge in Neural Network Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Li, Jingbo Zhu, Quan Du, Tong Xiao, Yanyang Li, Ye Lin, Ziyang Wang","submitted_at":"2020-09-19T03:23:26Z","abstract_excerpt":"Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. Recent successes in pre-training suggest the effectiveness of transferring model parameters. Inspired by this, we investigate methods of model acceleration and compression in another line of research. We propose Weight Distillation to transfer the knowledge in the large network parameters through a parameter generator. Our experiments on WMT16 En-Ro, NIST12 Zh-En, and WMT14 En-De machine translation tasks show that we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09152","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/2009.09152/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":"2009.09152","created_at":"2026-07-05T02:58:36.638603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.09152v3","created_at":"2026-07-05T02:58:36.638603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09152","created_at":"2026-07-05T02:58:36.638603+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHX2CXBB3EJD","created_at":"2026-07-05T02:58:36.638603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHX2CXBB3EJDUB4Z","created_at":"2026-07-05T02:58:36.638603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHX2CXBB","created_at":"2026-07-05T02:58:36.638603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09125","citing_title":"Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12391","citing_title":"Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG","json":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG.json","graph_json":"https://pith.science/api/pith-number/LHX2CXBB3EJDUB4ZEV2TDE6YZG/graph.json","events_json":"https://pith.science/api/pith-number/LHX2CXBB3EJDUB4ZEV2TDE6YZG/events.json","paper":"https://pith.science/paper/LHX2CXBB"},"agent_actions":{"view_html":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG","download_json":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG.json","view_paper":"https://pith.science/paper/LHX2CXBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.09152&json=true","fetch_graph":"https://pith.science/api/pith-number/LHX2CXBB3EJDUB4ZEV2TDE6YZG/graph.json","fetch_events":"https://pith.science/api/pith-number/LHX2CXBB3EJDUB4ZEV2TDE6YZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG/action/storage_attestation","attest_author":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG/action/author_attestation","sign_citation":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG/action/citation_signature","submit_replication":"https://pith.science/pith/LHX2CXBB3EJDUB4ZEV2TDE6YZG/action/replication_record"}},"created_at":"2026-07-05T02:58:36.638603+00:00","updated_at":"2026-07-05T02:58:36.638603+00:00"}