{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2M2QBC4GGEIOFYONKI2VC7T4M7","short_pith_number":"pith:2M2QBC4G","schema_version":"1.0","canonical_sha256":"d335008b863110e2e1cd5235517e7c67dd34b9a655ba120c8cb77aa545537d63","source":{"kind":"arxiv","id":"2404.10407","version":1},"attestation_state":"computed","paper":{"title":"Comprehensive Survey of Model Compression and Speed up for Vision Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyang Chen, Lisang Zhou, Xueting Pan, Ying Jiang, Ziqian Luo","submitted_at":"2024-04-16T09:19:11Z","abstract_excerpt":"Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory demands. This study addresses the challenge by evaluating four primary model compression techniques: quantization, low-rank approximation, knowledge distillation, and pruning. We methodically analyze and compare the efficacy of these techniques and their combinations in optimizing ViTs for resource-constrained environments. Our comprehensive experimental evaluation demonstrates tha"},"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":"2404.10407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T09:19:11Z","cross_cats_sorted":[],"title_canon_sha256":"b35241806751850d5b410f997f102597574a463d1d79460c92e855ec294d3a1f","abstract_canon_sha256":"33d4855eaab91372dc90d18230769894ccf0631587e337714ee388b8b06bea28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:29.976820Z","signature_b64":"+ClQOSeG7mjBNTo2RfAODyZ1v+n/VtCJV4REQrlpXQhvdVRLt+uPKxHi7fCKEPs8OdEkqdACkyY0iekb1hkADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d335008b863110e2e1cd5235517e7c67dd34b9a655ba120c8cb77aa545537d63","last_reissued_at":"2026-07-05T08:08:29.976282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:29.976282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensive Survey of Model Compression and Speed up for Vision Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyang Chen, Lisang Zhou, Xueting Pan, Ying Jiang, Ziqian Luo","submitted_at":"2024-04-16T09:19:11Z","abstract_excerpt":"Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory demands. This study addresses the challenge by evaluating four primary model compression techniques: quantization, low-rank approximation, knowledge distillation, and pruning. We methodically analyze and compare the efficacy of these techniques and their combinations in optimizing ViTs for resource-constrained environments. Our comprehensive experimental evaluation demonstrates tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10407","kind":"arxiv","version":1},"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/2404.10407/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":"2404.10407","created_at":"2026-07-05T08:08:29.976364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10407v1","created_at":"2026-07-05T08:08:29.976364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10407","created_at":"2026-07-05T08:08:29.976364+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M2QBC4GGEIO","created_at":"2026-07-05T08:08:29.976364+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M2QBC4GGEIOFYON","created_at":"2026-07-05T08:08:29.976364+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M2QBC4G","created_at":"2026-07-05T08:08:29.976364+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/2M2QBC4GGEIOFYONKI2VC7T4M7","json":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7.json","graph_json":"https://pith.science/api/pith-number/2M2QBC4GGEIOFYONKI2VC7T4M7/graph.json","events_json":"https://pith.science/api/pith-number/2M2QBC4GGEIOFYONKI2VC7T4M7/events.json","paper":"https://pith.science/paper/2M2QBC4G"},"agent_actions":{"view_html":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7","download_json":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7.json","view_paper":"https://pith.science/paper/2M2QBC4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10407&json=true","fetch_graph":"https://pith.science/api/pith-number/2M2QBC4GGEIOFYONKI2VC7T4M7/graph.json","fetch_events":"https://pith.science/api/pith-number/2M2QBC4GGEIOFYONKI2VC7T4M7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7/action/storage_attestation","attest_author":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7/action/author_attestation","sign_citation":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7/action/citation_signature","submit_replication":"https://pith.science/pith/2M2QBC4GGEIOFYONKI2VC7T4M7/action/replication_record"}},"created_at":"2026-07-05T08:08:29.976364+00:00","updated_at":"2026-07-05T08:08:29.976364+00:00"}