{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:54EQ762GSGHSNEBS4PM6IRZHDS","short_pith_number":"pith:54EQ762G","schema_version":"1.0","canonical_sha256":"ef090ffb46918f269032e3d9e447271c9da8dabaf783462413c5d0768ce8337b","source":{"kind":"arxiv","id":"2103.00793","version":3},"attestation_state":"computed","paper":{"title":"Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangliang Cheng, Qi Zhao, Shuchang Lyu, Ting-Bing Xu, Zhiwei Zhang","submitted_at":"2021-03-01T06:35:31Z","abstract_excerpt":"In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct depth-level/width-level dynamic neural networks which is hard to prove the accuracy of each sub-net. In this article, we propose an elegant Depth-Level Dynamic Neural Network (DDNN) integrated different-depth sub-nets of similar architectures. To improve the generalization of sub-nets, we design the Embedded-Knowledge-Distillation (EKD) training mechanism for th"},"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":"2103.00793","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-01T06:35:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe593f253cbad669afd5f2b22d01b96bbde416ea411efa2e87a04f35349b0e89","abstract_canon_sha256":"70c365f0e1c35c7a05198774c7c8eb83ee55329a1aee55b9fb984ce6e75731c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:21.540694Z","signature_b64":"gDvPMmsFUI0aL0qKCrvscMcVwizCIKpTk8PSCjEDEiTUctR9Mix33/IY7tYq923cvEX5AvRh8AZzEDexiMhsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef090ffb46918f269032e3d9e447271c9da8dabaf783462413c5d0768ce8337b","last_reissued_at":"2026-07-05T03:04:21.540260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:21.540260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangliang Cheng, Qi Zhao, Shuchang Lyu, Ting-Bing Xu, Zhiwei Zhang","submitted_at":"2021-03-01T06:35:31Z","abstract_excerpt":"In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct depth-level/width-level dynamic neural networks which is hard to prove the accuracy of each sub-net. In this article, we propose an elegant Depth-Level Dynamic Neural Network (DDNN) integrated different-depth sub-nets of similar architectures. To improve the generalization of sub-nets, we design the Embedded-Knowledge-Distillation (EKD) training mechanism for th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00793","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/2103.00793/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":"2103.00793","created_at":"2026-07-05T03:04:21.540325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00793v3","created_at":"2026-07-05T03:04:21.540325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00793","created_at":"2026-07-05T03:04:21.540325+00:00"},{"alias_kind":"pith_short_12","alias_value":"54EQ762GSGHS","created_at":"2026-07-05T03:04:21.540325+00:00"},{"alias_kind":"pith_short_16","alias_value":"54EQ762GSGHSNEBS","created_at":"2026-07-05T03:04:21.540325+00:00"},{"alias_kind":"pith_short_8","alias_value":"54EQ762G","created_at":"2026-07-05T03:04:21.540325+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/54EQ762GSGHSNEBS4PM6IRZHDS","json":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS.json","graph_json":"https://pith.science/api/pith-number/54EQ762GSGHSNEBS4PM6IRZHDS/graph.json","events_json":"https://pith.science/api/pith-number/54EQ762GSGHSNEBS4PM6IRZHDS/events.json","paper":"https://pith.science/paper/54EQ762G"},"agent_actions":{"view_html":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS","download_json":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS.json","view_paper":"https://pith.science/paper/54EQ762G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00793&json=true","fetch_graph":"https://pith.science/api/pith-number/54EQ762GSGHSNEBS4PM6IRZHDS/graph.json","fetch_events":"https://pith.science/api/pith-number/54EQ762GSGHSNEBS4PM6IRZHDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS/action/storage_attestation","attest_author":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS/action/author_attestation","sign_citation":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS/action/citation_signature","submit_replication":"https://pith.science/pith/54EQ762GSGHSNEBS4PM6IRZHDS/action/replication_record"}},"created_at":"2026-07-05T03:04:21.540325+00:00","updated_at":"2026-07-05T03:04:21.540325+00:00"}