{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:26WQK5PW3TCPG5LOMPMZAGCQEU","short_pith_number":"pith:26WQK5PW","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"},"canonical_sha256":"d7ad0575f6dcc4f3756e63d990185025159e356cc9e828d36a6840e048edacbe","source":{"kind":"arxiv","id":"2404.11202","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11202","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11202v2","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11202","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"pith_short_12","alias_value":"26WQK5PW3TCP","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"pith_short_16","alias_value":"26WQK5PW3TCPG5LO","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"pith_short_8","alias_value":"26WQK5PW","created_at":"2026-07-05T08:10:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:26WQK5PW3TCPG5LOMPMZAGCQEU","target":"record","payload":{"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"},"canonical_sha256":"d7ad0575f6dcc4f3756e63d990185025159e356cc9e828d36a6840e048edacbe","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"},"source_kind":"arxiv","source_id":"2404.11202","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sHf4HzLGlRiqZour0Buff/T3WQF/iTcM5vqF4QkhhiuxskCwp7owI+FLRshXLK0WnRJiwyDJMCUIYJtA8qDHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:35:31.830298Z"},"content_sha256":"338230b0ae95a0dd30aa23eaab60cdcddf1ffad509fba1333ec5ebdcf4f32d4a","schema_version":"1.0","event_id":"sha256:338230b0ae95a0dd30aa23eaab60cdcddf1ffad509fba1333ec5ebdcf4f32d4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:26WQK5PW3TCPG5LOMPMZAGCQEU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUV+7+vr2SypANpgnyzTNnUYAjiSxBEv+QLtp4gu24p6mVMJza5JAepSTOBJIEA6aCT0Fp9cspi/ToU+LQUhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:35:31.830788Z"},"content_sha256":"f930d2a6246e5f699a97877c933fb74745c829b403442fac15f650ec9b5997a2","schema_version":"1.0","event_id":"sha256:f930d2a6246e5f699a97877c933fb74745c829b403442fac15f650ec9b5997a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/bundle.json","state_url":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T00:35:31Z","links":{"resolver":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU","bundle":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/bundle.json","state":"https://pith.science/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26WQK5PW3TCPG5LOMPMZAGCQEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:26WQK5PW3TCPG5LOMPMZAGCQEU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a4736c0d84aca28f793f656b11044c9bcec9baea0e67d22f05655f97f44cb80d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T09:33:31Z","title_canon_sha256":"71b0a676762e72ccc044b395e60300eaddb384e69f4bfd4134a8d22b7f934422"},"schema_version":"1.0","source":{"id":"2404.11202","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11202","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11202v2","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11202","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"pith_short_12","alias_value":"26WQK5PW3TCP","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"pith_short_16","alias_value":"26WQK5PW3TCPG5LO","created_at":"2026-07-05T08:10:26Z"},{"alias_kind":"pith_short_8","alias_value":"26WQK5PW","created_at":"2026-07-05T08:10:26Z"}],"graph_snapshots":[{"event_id":"sha256:f930d2a6246e5f699a97877c933fb74745c829b403442fac15f650ec9b5997a2","target":"graph","created_at":"2026-07-05T08:10:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.11202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kai Han, Yehui Tang, Yunhe Wang, Zhenhua Liu, Zhiwei Hao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T09:33:31Z","title":"GhostNetV3: Exploring the Training Strategies for Compact Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11202","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:338230b0ae95a0dd30aa23eaab60cdcddf1ffad509fba1333ec5ebdcf4f32d4a","target":"record","created_at":"2026-07-05T08:10:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a4736c0d84aca28f793f656b11044c9bcec9baea0e67d22f05655f97f44cb80d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T09:33:31Z","title_canon_sha256":"71b0a676762e72ccc044b395e60300eaddb384e69f4bfd4134a8d22b7f934422"},"schema_version":"1.0","source":{"id":"2404.11202","kind":"arxiv","version":2}},"canonical_sha256":"d7ad0575f6dcc4f3756e63d990185025159e356cc9e828d36a6840e048edacbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7ad0575f6dcc4f3756e63d990185025159e356cc9e828d36a6840e048edacbe","first_computed_at":"2026-07-05T08:10:26.824958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:26.824958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"con1zMDQ5hbtGIc0f18S40GqKBkjEk0n0FnOlIdBr7k9tfmhLYYIS9VDF+OOWbRdU8RtrcqGO95jqUQIaWsXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:26.825309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11202","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:338230b0ae95a0dd30aa23eaab60cdcddf1ffad509fba1333ec5ebdcf4f32d4a","sha256:f930d2a6246e5f699a97877c933fb74745c829b403442fac15f650ec9b5997a2"],"state_sha256":"1039e30e7b1409eed404777a0f5b64025c056a5785cded92ebfd73ed82aa178d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ElE0TZ5DL90fcAvAIIKOkSBLb+ISPY4dBuVfNMtHHH0uZW4EdHFAEQ4oFAaxWimMDURiHJzBerKmb1+KtyMSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:35:31.836402Z","bundle_sha256":"14f796fd60c69c99340fbb229999b7d9504fb4b7749ad970edbb3e40eae0d6b8"}}