{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NMRMJ4HMJM3HODSP3DNNMHROO7","short_pith_number":"pith:NMRMJ4HM","schema_version":"1.0","canonical_sha256":"6b22c4f0ec4b36770e4fd8dad61e2e77f0754a23418cc70aad048cd92566f0a8","source":{"kind":"arxiv","id":"2505.12942","version":4},"attestation_state":"computed","paper":{"title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng Zhang, Christos-Savvas Bouganis, George A. Constantinides, Jeffrey T. H. Wong, Pedro Gimenes, Wayne Luk, Xinye Cao, Yiren Zhao","submitted_at":"2025-05-19T10:29:32Z","abstract_excerpt":"Large language models have demonstrated remarkable performance; however, their massive parameter counts make deployment highly expensive. Low-rank approximation offers a promising compression solution, yet existing approaches have two main limitations: (1) They focus on minimizing the output error of individual linear layers, without considering the architectural characteristics of Transformers, and (2) they decompose a large weight matrix into two small low-rank matrices. Consequently, these methods often fall short compared to other compression techniques like pruning and quantization, and i"},"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":"2505.12942","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T10:29:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0c608e30364cc93419908e4e451d86f304f562f89937840e180f4f424d8046ba","abstract_canon_sha256":"06c065ebdd37bfd56bc05630ef68603f94c778daa2d6b8cca815e63841db911f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:35.673700Z","signature_b64":"NkKsiK3qnipWIAg+5pF5R2rCTGJvyelgywKmTexHIAr8KDYbcWpZ0BHbmboq2UGkq9lEou6jPyOwOVyp595KAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b22c4f0ec4b36770e4fd8dad61e2e77f0754a23418cc70aad048cd92566f0a8","last_reissued_at":"2026-05-18T03:09:35.672890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:35.672890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng Zhang, Christos-Savvas Bouganis, George A. Constantinides, Jeffrey T. H. Wong, Pedro Gimenes, Wayne Luk, Xinye Cao, Yiren Zhao","submitted_at":"2025-05-19T10:29:32Z","abstract_excerpt":"Large language models have demonstrated remarkable performance; however, their massive parameter counts make deployment highly expensive. Low-rank approximation offers a promising compression solution, yet existing approaches have two main limitations: (1) They focus on minimizing the output error of individual linear layers, without considering the architectural characteristics of Transformers, and (2) they decompose a large weight matrix into two small low-rank matrices. Consequently, these methods often fall short compared to other compression techniques like pruning and quantization, and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12942","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2505.12942","created_at":"2026-05-18T03:09:35.673022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12942v4","created_at":"2026-05-18T03:09:35.673022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12942","created_at":"2026-05-18T03:09:35.673022+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMRMJ4HMJM3H","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMRMJ4HMJM3HODSP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMRMJ4HM","created_at":"2026-05-18T12:33:37.589309+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/NMRMJ4HMJM3HODSP3DNNMHROO7","json":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7.json","graph_json":"https://pith.science/api/pith-number/NMRMJ4HMJM3HODSP3DNNMHROO7/graph.json","events_json":"https://pith.science/api/pith-number/NMRMJ4HMJM3HODSP3DNNMHROO7/events.json","paper":"https://pith.science/paper/NMRMJ4HM"},"agent_actions":{"view_html":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7","download_json":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7.json","view_paper":"https://pith.science/paper/NMRMJ4HM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12942&json=true","fetch_graph":"https://pith.science/api/pith-number/NMRMJ4HMJM3HODSP3DNNMHROO7/graph.json","fetch_events":"https://pith.science/api/pith-number/NMRMJ4HMJM3HODSP3DNNMHROO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/action/storage_attestation","attest_author":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/action/author_attestation","sign_citation":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/action/citation_signature","submit_replication":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/action/replication_record"}},"created_at":"2026-05-18T03:09:35.673022+00:00","updated_at":"2026-05-18T03:09:35.673022+00:00"}