{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WOD52XASCB2RI6EMWJFA37A7SY","short_pith_number":"pith:WOD52XAS","schema_version":"1.0","canonical_sha256":"b387dd5c12107514788cb24a0dfc1f9601d86c534a98a2892902c73c42e03a33","source":{"kind":"arxiv","id":"2107.01378","version":4},"attestation_state":"computed","paper":{"title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Ding Jia, Han Hu, Jianyuan Guo, Kai Han, Yehui Tang, Yunhe Wang, Zhiwei Hao","submitted_at":"2021-07-03T08:28:34Z","abstract_excerpt":"In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being deployed on edge devices such as cell phones and smart watches. Knowledge distillation is a widely used paradigm for compressing cumbersome architectures via transferring information to a compact student. However, most of them are designed for convolutional neural networks (CNNs), which do not fully investigate the character of vision transformer (ViT). In this paper, we utilize t"},"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":"2107.01378","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-03T08:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"d6508396c15ea2873949f826f3af54b56dd1d13b44f83d47c3e39dd73aed8b8f","abstract_canon_sha256":"7b2232d330ae4ff8ee57768e3ba3ba74731fc8a40d3d059d3eadc214dd162285"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:26.653259Z","signature_b64":"vkPrFL+Hvd0Z8LKSm5wley2K3IV8llRRPfxI5JZbba7ghywWGDslY9E3/c2Zgo9EbPpgEzeveyYKrIvAet2dBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b387dd5c12107514788cb24a0dfc1f9601d86c534a98a2892902c73c42e03a33","last_reissued_at":"2026-07-05T04:28:26.652804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:26.652804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Ding Jia, Han Hu, Jianyuan Guo, Kai Han, Yehui Tang, Yunhe Wang, Zhiwei Hao","submitted_at":"2021-07-03T08:28:34Z","abstract_excerpt":"In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being deployed on edge devices such as cell phones and smart watches. Knowledge distillation is a widely used paradigm for compressing cumbersome architectures via transferring information to a compact student. However, most of them are designed for convolutional neural networks (CNNs), which do not fully investigate the character of vision transformer (ViT). In this paper, we utilize t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01378","kind":"arxiv","version":4},"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/2107.01378/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":"2107.01378","created_at":"2026-07-05T04:28:26.652863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01378v4","created_at":"2026-07-05T04:28:26.652863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01378","created_at":"2026-07-05T04:28:26.652863+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOD52XASCB2R","created_at":"2026-07-05T04:28:26.652863+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOD52XASCB2RI6EM","created_at":"2026-07-05T04:28:26.652863+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOD52XAS","created_at":"2026-07-05T04:28:26.652863+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/WOD52XASCB2RI6EMWJFA37A7SY","json":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY.json","graph_json":"https://pith.science/api/pith-number/WOD52XASCB2RI6EMWJFA37A7SY/graph.json","events_json":"https://pith.science/api/pith-number/WOD52XASCB2RI6EMWJFA37A7SY/events.json","paper":"https://pith.science/paper/WOD52XAS"},"agent_actions":{"view_html":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY","download_json":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY.json","view_paper":"https://pith.science/paper/WOD52XAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01378&json=true","fetch_graph":"https://pith.science/api/pith-number/WOD52XASCB2RI6EMWJFA37A7SY/graph.json","fetch_events":"https://pith.science/api/pith-number/WOD52XASCB2RI6EMWJFA37A7SY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY/action/storage_attestation","attest_author":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY/action/author_attestation","sign_citation":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY/action/citation_signature","submit_replication":"https://pith.science/pith/WOD52XASCB2RI6EMWJFA37A7SY/action/replication_record"}},"created_at":"2026-07-05T04:28:26.652863+00:00","updated_at":"2026-07-05T04:28:26.652863+00:00"}