{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BKFZBPFEFO7F35UX3YTRB6ZPBN","short_pith_number":"pith:BKFZBPFE","schema_version":"1.0","canonical_sha256":"0a8b90bca42bbe5df697de2710fb2f0b6bcfe42c8648e88b4ebeb29ac4a68537","source":{"kind":"arxiv","id":"2401.14895","version":2},"attestation_state":"computed","paper":{"title":"MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-Yeu (Andy) Wu, Yu-Shan Tai","submitted_at":"2024-01-26T14:25:15Z","abstract_excerpt":"While vision transformers (ViTs) have shown great potential in computer vision tasks, their intense computation and memory requirements pose challenges for practical applications. Existing post-training quantization methods leverage value redistribution or specialized quantizers to address the non-normal distribution in ViTs. However, without considering the asymmetry in activations and relying on hand-crafted settings, these methods often struggle to maintain performance under low-bit quantization. To overcome these challenges, we introduce SmoothQuant with bias term (SQ-b) to alleviate the a"},"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":"2401.14895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-26T14:25:15Z","cross_cats_sorted":[],"title_canon_sha256":"c6580e922a7f55395d645c494066e84dc50553f55424cc733bfe262c1a4d110e","abstract_canon_sha256":"88bdda83e93cf303ea181411ea1eb45073bdf3897cd8fd1d87ed77bde9a689f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:06.792049Z","signature_b64":"NvAgrKWdkkLlvPd37Mwzpv679wQrgacrx6WknVUx4UIcr4XAYP+XSljAB55Z0IzpuBj77JDfefvdGAM6dmn4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a8b90bca42bbe5df697de2710fb2f0b6bcfe42c8648e88b4ebeb29ac4a68537","last_reissued_at":"2026-07-05T07:40:06.791540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:06.791540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-Yeu (Andy) Wu, Yu-Shan Tai","submitted_at":"2024-01-26T14:25:15Z","abstract_excerpt":"While vision transformers (ViTs) have shown great potential in computer vision tasks, their intense computation and memory requirements pose challenges for practical applications. Existing post-training quantization methods leverage value redistribution or specialized quantizers to address the non-normal distribution in ViTs. However, without considering the asymmetry in activations and relying on hand-crafted settings, these methods often struggle to maintain performance under low-bit quantization. To overcome these challenges, we introduce SmoothQuant with bias term (SQ-b) to alleviate the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14895","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/2401.14895/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":"2401.14895","created_at":"2026-07-05T07:40:06.791604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14895v2","created_at":"2026-07-05T07:40:06.791604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14895","created_at":"2026-07-05T07:40:06.791604+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKFZBPFEFO7F","created_at":"2026-07-05T07:40:06.791604+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKFZBPFEFO7F35UX","created_at":"2026-07-05T07:40:06.791604+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKFZBPFE","created_at":"2026-07-05T07:40:06.791604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07317","citing_title":"Amortized-Precision Quantization for Early-Exit Vision Transformers","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN","json":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN.json","graph_json":"https://pith.science/api/pith-number/BKFZBPFEFO7F35UX3YTRB6ZPBN/graph.json","events_json":"https://pith.science/api/pith-number/BKFZBPFEFO7F35UX3YTRB6ZPBN/events.json","paper":"https://pith.science/paper/BKFZBPFE"},"agent_actions":{"view_html":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN","download_json":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN.json","view_paper":"https://pith.science/paper/BKFZBPFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14895&json=true","fetch_graph":"https://pith.science/api/pith-number/BKFZBPFEFO7F35UX3YTRB6ZPBN/graph.json","fetch_events":"https://pith.science/api/pith-number/BKFZBPFEFO7F35UX3YTRB6ZPBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN/action/storage_attestation","attest_author":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN/action/author_attestation","sign_citation":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN/action/citation_signature","submit_replication":"https://pith.science/pith/BKFZBPFEFO7F35UX3YTRB6ZPBN/action/replication_record"}},"created_at":"2026-07-05T07:40:06.791604+00:00","updated_at":"2026-07-05T07:40:06.791604+00:00"}