{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LTJMF77ZMWCGJFB2CMN2QCIV5X","short_pith_number":"pith:LTJMF77Z","schema_version":"1.0","canonical_sha256":"5cd2c2fff9658464943a131ba80915ede78fea7be79b6167c097ce070b5f5061","source":{"kind":"arxiv","id":"1906.00675","version":2},"attestation_state":"computed","paper":{"title":"Deeply-supervised Knowledge Synergy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anbang Yao, Aojun Zhou, Dawei Sun, Hao Zhao","submitted_at":"2019-06-03T09:54:26Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme follows the previous way of adding supervision to the last layer of the network only and propagating error information up layer-by-layer. In this paper, we propose Deeply-supervised Knowledge Synergy (DKS), a new method aiming to train CNNs with improved generalization ability for image classification tasks without introducing extra computational cost during inference. Inspired by the deeply-supervised learning scheme, we first append au"},"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":"1906.00675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-03T09:54:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"072a39209e79bfa7619430e4839a2770959783ff5eca31b830c867a383c550e1","abstract_canon_sha256":"ba0d95e3238094dca6f0203f503a1e4283680016007074b237fae294aab49eea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:18.272873Z","signature_b64":"JO6jR7D4OPagwteOTWxb68biTI0of5N6z9RbrvLDkLRM+BpI09XUEyizwf7IMszcW51vc77TdZ4k1YPtp8IvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cd2c2fff9658464943a131ba80915ede78fea7be79b6167c097ce070b5f5061","last_reissued_at":"2026-05-17T23:44:18.272375Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:18.272375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deeply-supervised Knowledge Synergy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anbang Yao, Aojun Zhou, Dawei Sun, Hao Zhao","submitted_at":"2019-06-03T09:54:26Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme follows the previous way of adding supervision to the last layer of the network only and propagating error information up layer-by-layer. In this paper, we propose Deeply-supervised Knowledge Synergy (DKS), a new method aiming to train CNNs with improved generalization ability for image classification tasks without introducing extra computational cost during inference. Inspired by the deeply-supervised learning scheme, we first append au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00675","kind":"arxiv","version":2},"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":"1906.00675","created_at":"2026-05-17T23:44:18.272464+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00675v2","created_at":"2026-05-17T23:44:18.272464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00675","created_at":"2026-05-17T23:44:18.272464+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTJMF77ZMWCG","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTJMF77ZMWCGJFB2","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTJMF77Z","created_at":"2026-05-18T12:33:21.387695+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/LTJMF77ZMWCGJFB2CMN2QCIV5X","json":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X.json","graph_json":"https://pith.science/api/pith-number/LTJMF77ZMWCGJFB2CMN2QCIV5X/graph.json","events_json":"https://pith.science/api/pith-number/LTJMF77ZMWCGJFB2CMN2QCIV5X/events.json","paper":"https://pith.science/paper/LTJMF77Z"},"agent_actions":{"view_html":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X","download_json":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X.json","view_paper":"https://pith.science/paper/LTJMF77Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00675&json=true","fetch_graph":"https://pith.science/api/pith-number/LTJMF77ZMWCGJFB2CMN2QCIV5X/graph.json","fetch_events":"https://pith.science/api/pith-number/LTJMF77ZMWCGJFB2CMN2QCIV5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X/action/storage_attestation","attest_author":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X/action/author_attestation","sign_citation":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X/action/citation_signature","submit_replication":"https://pith.science/pith/LTJMF77ZMWCGJFB2CMN2QCIV5X/action/replication_record"}},"created_at":"2026-05-17T23:44:18.272464+00:00","updated_at":"2026-05-17T23:44:18.272464+00:00"}