{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L27GE3N5L4WS7T65A5ZFGAOIDR","short_pith_number":"pith:L27GE3N5","schema_version":"1.0","canonical_sha256":"5ebe626dbd5f2d2fcfdd07725301c81c7df72bba0554c60c4f70a0dd51e21a86","source":{"kind":"arxiv","id":"2506.01166","version":1},"attestation_state":"computed","paper":{"title":"VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Alberto Garcia-Ortiz, Lennart Bamberg, Shereef Helal","submitted_at":"2025-06-01T20:59:20Z","abstract_excerpt":"Leveraging high degrees of unstructured sparsity is a promising approach to enhance the efficiency of deep neural network DNN accelerators - particularly important for emerging Edge-AI applications. We introduce VUSA, a systolic-array architecture that virtually grows based on the present sparsity to perform larger matrix multiplications with the same number of physical multiply-accumulate MAC units. The proposed architecture achieves saving by 37% and 68% in area and power efficiency, respectively, at the same peak-performance, compared to a baseline systolic array architecture in a commercia"},"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":"2506.01166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-06-01T20:59:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c1326eec99dcf38a6ba9b3e7126616d76af4f806627754db175339eac1140dc3","abstract_canon_sha256":"f7ee74590cf20973004a8d951f51f5ae8652d4fff4c14904d2f1feba3c642fc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:47.571114Z","signature_b64":"n3CpOXpDaMUkPtXP8nPAiixniCYbc8A8L1xlbFsQxkXw/byALHfwstaRlJENhMBw0kLn8yMhypMOROKbIWXZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ebe626dbd5f2d2fcfdd07725301c81c7df72bba0554c60c4f70a0dd51e21a86","last_reissued_at":"2026-07-05T11:13:47.570720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:47.570720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.AR","authors_text":"Alberto Garcia-Ortiz, Lennart Bamberg, Shereef Helal","submitted_at":"2025-06-01T20:59:20Z","abstract_excerpt":"Leveraging high degrees of unstructured sparsity is a promising approach to enhance the efficiency of deep neural network DNN accelerators - particularly important for emerging Edge-AI applications. We introduce VUSA, a systolic-array architecture that virtually grows based on the present sparsity to perform larger matrix multiplications with the same number of physical multiply-accumulate MAC units. The proposed architecture achieves saving by 37% and 68% in area and power efficiency, respectively, at the same peak-performance, compared to a baseline systolic array architecture in a commercia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01166","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/2506.01166/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":"2506.01166","created_at":"2026-07-05T11:13:47.570779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01166v1","created_at":"2026-07-05T11:13:47.570779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01166","created_at":"2026-07-05T11:13:47.570779+00:00"},{"alias_kind":"pith_short_12","alias_value":"L27GE3N5L4WS","created_at":"2026-07-05T11:13:47.570779+00:00"},{"alias_kind":"pith_short_16","alias_value":"L27GE3N5L4WS7T65","created_at":"2026-07-05T11:13:47.570779+00:00"},{"alias_kind":"pith_short_8","alias_value":"L27GE3N5","created_at":"2026-07-05T11:13:47.570779+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/L27GE3N5L4WS7T65A5ZFGAOIDR","json":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR.json","graph_json":"https://pith.science/api/pith-number/L27GE3N5L4WS7T65A5ZFGAOIDR/graph.json","events_json":"https://pith.science/api/pith-number/L27GE3N5L4WS7T65A5ZFGAOIDR/events.json","paper":"https://pith.science/paper/L27GE3N5"},"agent_actions":{"view_html":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR","download_json":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR.json","view_paper":"https://pith.science/paper/L27GE3N5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01166&json=true","fetch_graph":"https://pith.science/api/pith-number/L27GE3N5L4WS7T65A5ZFGAOIDR/graph.json","fetch_events":"https://pith.science/api/pith-number/L27GE3N5L4WS7T65A5ZFGAOIDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR/action/storage_attestation","attest_author":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR/action/author_attestation","sign_citation":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR/action/citation_signature","submit_replication":"https://pith.science/pith/L27GE3N5L4WS7T65A5ZFGAOIDR/action/replication_record"}},"created_at":"2026-07-05T11:13:47.570779+00:00","updated_at":"2026-07-05T11:13:47.570779+00:00"}