{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GF6RVOOWRM2NI44UVEO5GBRAM3","short_pith_number":"pith:GF6RVOOW","schema_version":"1.0","canonical_sha256":"317d1ab9d68b34d47394a91dd3062066c9c9fb6c3c057f00f396ef8ee0d3dbc1","source":{"kind":"arxiv","id":"2306.06446","version":6},"attestation_state":"computed","paper":{"title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoran You, Huihong Shi, Yingyan Celine Lin, Yipin Guo","submitted_at":"2023-06-10T13:53:41Z","abstract_excerpt":"Vision Transformers (ViTs) have shown impressive performance and have become a unified backbone for multiple vision tasks. However, both the attention mechanism and multi-layer perceptrons (MLPs) in ViTs are not sufficiently efficient due to dense multiplications, leading to costly training and inference. To this end, we propose to reparameterize pre-trained ViTs with a mixture of multiplication primitives, e.g., bitwise shifts and additions, towards a new type of multiplication-reduced model, dubbed $\\textbf{ShiftAddViT}$, which aims to achieve end-to-end inference speedups on GPUs without re"},"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":"2306.06446","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-10T13:53:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b9d2b89a8bcc7a0231281de85136082e36883578cef133c702a009df3c0a00a6","abstract_canon_sha256":"d39ade0693b7a5fcd63e14bddc36aa4488eb59bc6208b1b1921cd974871e972c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:29.305727Z","signature_b64":"fT+2whAfvrft77ubQtGdaXeFcEUsJfTazL9dcZC4JiJy2Ot0/6MKEwhDn/oXpcYVedz0V5VwU0gzgUoF/vs/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"317d1ab9d68b34d47394a91dd3062066c9c9fb6c3c057f00f396ef8ee0d3dbc1","last_reissued_at":"2026-07-05T08:48:29.305349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:29.305349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoran You, Huihong Shi, Yingyan Celine Lin, Yipin Guo","submitted_at":"2023-06-10T13:53:41Z","abstract_excerpt":"Vision Transformers (ViTs) have shown impressive performance and have become a unified backbone for multiple vision tasks. However, both the attention mechanism and multi-layer perceptrons (MLPs) in ViTs are not sufficiently efficient due to dense multiplications, leading to costly training and inference. To this end, we propose to reparameterize pre-trained ViTs with a mixture of multiplication primitives, e.g., bitwise shifts and additions, towards a new type of multiplication-reduced model, dubbed $\\textbf{ShiftAddViT}$, which aims to achieve end-to-end inference speedups on GPUs without re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06446","kind":"arxiv","version":6},"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/2306.06446/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":"2306.06446","created_at":"2026-07-05T08:48:29.305409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06446v6","created_at":"2026-07-05T08:48:29.305409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06446","created_at":"2026-07-05T08:48:29.305409+00:00"},{"alias_kind":"pith_short_12","alias_value":"GF6RVOOWRM2N","created_at":"2026-07-05T08:48:29.305409+00:00"},{"alias_kind":"pith_short_16","alias_value":"GF6RVOOWRM2NI44U","created_at":"2026-07-05T08:48:29.305409+00:00"},{"alias_kind":"pith_short_8","alias_value":"GF6RVOOW","created_at":"2026-07-05T08:48:29.305409+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/GF6RVOOWRM2NI44UVEO5GBRAM3","json":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3.json","graph_json":"https://pith.science/api/pith-number/GF6RVOOWRM2NI44UVEO5GBRAM3/graph.json","events_json":"https://pith.science/api/pith-number/GF6RVOOWRM2NI44UVEO5GBRAM3/events.json","paper":"https://pith.science/paper/GF6RVOOW"},"agent_actions":{"view_html":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3","download_json":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3.json","view_paper":"https://pith.science/paper/GF6RVOOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06446&json=true","fetch_graph":"https://pith.science/api/pith-number/GF6RVOOWRM2NI44UVEO5GBRAM3/graph.json","fetch_events":"https://pith.science/api/pith-number/GF6RVOOWRM2NI44UVEO5GBRAM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3/action/storage_attestation","attest_author":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3/action/author_attestation","sign_citation":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3/action/citation_signature","submit_replication":"https://pith.science/pith/GF6RVOOWRM2NI44UVEO5GBRAM3/action/replication_record"}},"created_at":"2026-07-05T08:48:29.305409+00:00","updated_at":"2026-07-05T08:48:29.305409+00:00"}