{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:26WQK5PW3TCPG5LOMPMZAGCQEU","short_pith_number":"pith:26WQK5PW","schema_version":"1.0","canonical_sha256":"d7ad0575f6dcc4f3756e63d990185025159e356cc9e828d36a6840e048edacbe","source":{"kind":"arxiv","id":"2404.11202","version":2},"attestation_state":"computed","paper":{"title":"GhostNetV3: Exploring the Training Strategies for Compact Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Han, Yehui Tang, Yunhe Wang, Zhenhua Liu, Zhiwei Hao","submitted_at":"2024-04-17T09:33:31Z","abstract_excerpt":"Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models are borrowed from that of conventional models at present, which ignores their difference in model capacity and thus may impede the performance of compact models. In this paper, by systematically investigating the impact of different training ingredients, we introduce a strong training strategy for compact models. We find that the appropriate designs of re-parameterization and knowledge distillation are crucial for tra"},"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":"2404.11202","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T09:33:31Z","cross_cats_sorted":[],"title_canon_sha256":"71b0a676762e72ccc044b395e60300eaddb384e69f4bfd4134a8d22b7f934422","abstract_canon_sha256":"a4736c0d84aca28f793f656b11044c9bcec9baea0e67d22f05655f97f44cb80d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:26.825309Z","signature_b64":"con1zMDQ5hbtGIc0f18S40GqKBkjEk0n0FnOlIdBr7k9tfmhLYYIS9VDF+OOWbRdU8RtrcqGO95jqUQIaWsXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7ad0575f6dcc4f3756e63d990185025159e356cc9e828d36a6840e048edacbe","last_reissued_at":"2026-07-05T08:10:26.824958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:26.824958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GhostNetV3: Exploring the Training Strategies for Compact Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Han, Yehui Tang, Yunhe Wang, Zhenhua Liu, Zhiwei Hao","submitted_at":"2024-04-17T09:33:31Z","abstract_excerpt":"Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models are borrowed from that of conventional models at present, which ignores their difference in model capacity and thus may impede the performance of compact models. In this paper, by systematically investigating the impact of different training ingredients, we introduce a strong training strategy for compact models. We find that the appropriate designs of re-parameterization and knowledge distillation are crucial for tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11202","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.11202/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":"2404.11202","created_at":"2026-07-05T08:10:26.825018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11202v2","created_at":"2026-07-05T08:10:26.825018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11202","created_at":"2026-07-05T08:10:26.825018+00:00"},{"alias_kind":"pith_short_12","alias_value":"26WQK5PW3TCP","created_at":"2026-07-05T08:10:26.825018+00:00"},{"alias_kind":"pith_short_16","alias_value":"26WQK5PW3TCPG5LO","created_at":"2026-07-05T08:10:26.825018+00:00"},{"alias_kind":"pith_short_8","alias_value":"26WQK5PW","created_at":"2026-07-05T08:10:26.825018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01385","citing_title":"Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU","json":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU.json","graph_json":"https://pith.science/api/pith-number/26WQK5PW3TCPG5LOMPMZAGCQEU/graph.json","events_json":"https://pith.science/api/pith-number/26WQK5PW3TCPG5LOMPMZAGCQEU/events.json","paper":"https://pith.science/paper/26WQK5PW"},"agent_actions":{"view_html":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU","download_json":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU.json","view_paper":"https://pith.science/paper/26WQK5PW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11202&json=true","fetch_graph":"https://pith.science/api/pith-number/26WQK5PW3TCPG5LOMPMZAGCQEU/graph.json","fetch_events":"https://pith.science/api/pith-number/26WQK5PW3TCPG5LOMPMZAGCQEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/action/storage_attestation","attest_author":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/action/author_attestation","sign_citation":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/action/citation_signature","submit_replication":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/action/replication_record"}},"created_at":"2026-07-05T08:10:26.825018+00:00","updated_at":"2026-07-05T08:10:26.825018+00:00"}