{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WGOGSU6AT454SIHURO4Y7OYA4W","short_pith_number":"pith:WGOGSU6A","schema_version":"1.0","canonical_sha256":"b19c6953c09f3bc920f48bb98fbb00e58708c8e4fb85bc9a1a92308badbf8e53","source":{"kind":"arxiv","id":"1904.01802","version":1},"attestation_state":"computed","paper":{"title":"Correlation Congruence for Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyun Peng, Dongsheng Li, Jiaheng Liu, Shunfeng Zhou, Xiao Jin, Yichao Wu, Yu Liu, Zhaoning Zhang","submitted_at":"2019-04-03T06:58:10Z","abstract_excerpt":"Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level. However, they usually ignore the correlation between multiple instances, which is also valuable for knowledge transfer. In this work, we propose a new framework named correlation congruence for knowledge distillation (CCKD), which transfers not only the instance-level information, but also the correlation between instances. Furthermore, a generalized kernel method based on Taylor series expansion is proposed to better capture the correlation between instances. Empiric"},"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":"1904.01802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-03T06:58:10Z","cross_cats_sorted":[],"title_canon_sha256":"3a9c8d9724273ea259e3d9460bde164dba555fe23f2f7544171f83aed1830301","abstract_canon_sha256":"bbd7e757456f8260a74af2958cb3ac6409d8e8ddee18b96d48c7778dc01d6e52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:29.623749Z","signature_b64":"517mBy/t+5w6uzt8DZbRx872fYOaIRPlaZkfyMyLYe06ZrEdosslg6CG4wanA+1Du7RA0uO72RWmr707WeL5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b19c6953c09f3bc920f48bb98fbb00e58708c8e4fb85bc9a1a92308badbf8e53","last_reissued_at":"2026-05-17T23:49:29.623082Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:29.623082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correlation Congruence for Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyun Peng, Dongsheng Li, Jiaheng Liu, Shunfeng Zhou, Xiao Jin, Yichao Wu, Yu Liu, Zhaoning Zhang","submitted_at":"2019-04-03T06:58:10Z","abstract_excerpt":"Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level. However, they usually ignore the correlation between multiple instances, which is also valuable for knowledge transfer. In this work, we propose a new framework named correlation congruence for knowledge distillation (CCKD), which transfers not only the instance-level information, but also the correlation between instances. Furthermore, a generalized kernel method based on Taylor series expansion is proposed to better capture the correlation between instances. Empiric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01802","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":""},"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":"1904.01802","created_at":"2026-05-17T23:49:29.623178+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01802v1","created_at":"2026-05-17T23:49:29.623178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01802","created_at":"2026-05-17T23:49:29.623178+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGOGSU6AT454","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGOGSU6AT454SIHU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGOGSU6A","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20232","citing_title":"ATMS-KD: Adaptive Temperature and Mixed Sample Knowledge Distillation for a Lightweight Residual CNN in Agricultural Embedded Systems","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W","json":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W.json","graph_json":"https://pith.science/api/pith-number/WGOGSU6AT454SIHURO4Y7OYA4W/graph.json","events_json":"https://pith.science/api/pith-number/WGOGSU6AT454SIHURO4Y7OYA4W/events.json","paper":"https://pith.science/paper/WGOGSU6A"},"agent_actions":{"view_html":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W","download_json":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W.json","view_paper":"https://pith.science/paper/WGOGSU6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01802&json=true","fetch_graph":"https://pith.science/api/pith-number/WGOGSU6AT454SIHURO4Y7OYA4W/graph.json","fetch_events":"https://pith.science/api/pith-number/WGOGSU6AT454SIHURO4Y7OYA4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W/action/storage_attestation","attest_author":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W/action/author_attestation","sign_citation":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W/action/citation_signature","submit_replication":"https://pith.science/pith/WGOGSU6AT454SIHURO4Y7OYA4W/action/replication_record"}},"created_at":"2026-05-17T23:49:29.623178+00:00","updated_at":"2026-05-17T23:49:29.623178+00:00"}