{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CXQNB6MW3DZFZ5C3OPFIEDQKZT","short_pith_number":"pith:CXQNB6MW","schema_version":"1.0","canonical_sha256":"15e0d0f996d8f25cf45b73ca820e0accfa94e75fc562b4fbbc0513bfc0f9019e","source":{"kind":"arxiv","id":"2401.11851","version":2},"attestation_state":"computed","paper":{"title":"BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Chao Fang, Yuhao Ji, Zhongfeng Wang","submitted_at":"2024-01-22T11:14:08Z","abstract_excerpt":"Existing binary Transformers are promising in edge deployment due to their compact model size, low computational complexity, and considerable inference accuracy. However, deploying binary Transformers faces challenges on prior processors due to inefficient execution of quantized matrix multiplication (QMM) and the energy consumption overhead caused by multi-precision activations. To tackle the challenges above, we first develop a computation flow abstraction method for binary Transformers to improve QMM execution efficiency by optimizing the computation order. Furthermore, a binarized energy-e"},"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":"2401.11851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2024-01-22T11:14:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c93f51142b0bd6c7072c9207a47e0e64f1918a332045db3d5be5cddb7518e41","abstract_canon_sha256":"e9f5f31ecbeed50636ee44226cc3dad9da8f52cf7b4997638069bff28c86caa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:25.667869Z","signature_b64":"sPYyZYtmWUgjsHWKYK5U9FxgRMkL8pr/+R0LeOceW+Pt6DvSq0UicIJ/QPgYX643L7rtnJG8lLgZjlDmYf1HBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15e0d0f996d8f25cf45b73ca820e0accfa94e75fc562b4fbbc0513bfc0f9019e","last_reissued_at":"2026-07-05T08:43:25.667322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:25.667322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Chao Fang, Yuhao Ji, Zhongfeng Wang","submitted_at":"2024-01-22T11:14:08Z","abstract_excerpt":"Existing binary Transformers are promising in edge deployment due to their compact model size, low computational complexity, and considerable inference accuracy. However, deploying binary Transformers faces challenges on prior processors due to inefficient execution of quantized matrix multiplication (QMM) and the energy consumption overhead caused by multi-precision activations. To tackle the challenges above, we first develop a computation flow abstraction method for binary Transformers to improve QMM execution efficiency by optimizing the computation order. Furthermore, a binarized energy-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11851","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/2401.11851/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":"2401.11851","created_at":"2026-07-05T08:43:25.667382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11851v2","created_at":"2026-07-05T08:43:25.667382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11851","created_at":"2026-07-05T08:43:25.667382+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXQNB6MW3DZF","created_at":"2026-07-05T08:43:25.667382+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXQNB6MW3DZFZ5C3","created_at":"2026-07-05T08:43:25.667382+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXQNB6MW","created_at":"2026-07-05T08:43:25.667382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06663","citing_title":"Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT","json":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT.json","graph_json":"https://pith.science/api/pith-number/CXQNB6MW3DZFZ5C3OPFIEDQKZT/graph.json","events_json":"https://pith.science/api/pith-number/CXQNB6MW3DZFZ5C3OPFIEDQKZT/events.json","paper":"https://pith.science/paper/CXQNB6MW"},"agent_actions":{"view_html":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT","download_json":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT.json","view_paper":"https://pith.science/paper/CXQNB6MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11851&json=true","fetch_graph":"https://pith.science/api/pith-number/CXQNB6MW3DZFZ5C3OPFIEDQKZT/graph.json","fetch_events":"https://pith.science/api/pith-number/CXQNB6MW3DZFZ5C3OPFIEDQKZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT/action/storage_attestation","attest_author":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT/action/author_attestation","sign_citation":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT/action/citation_signature","submit_replication":"https://pith.science/pith/CXQNB6MW3DZFZ5C3OPFIEDQKZT/action/replication_record"}},"created_at":"2026-07-05T08:43:25.667382+00:00","updated_at":"2026-07-05T08:43:25.667382+00:00"}