{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NMRMJ4HMJM3HODSP3DNNMHROO7","short_pith_number":"pith:NMRMJ4HM","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"},"canonical_sha256":"6b22c4f0ec4b36770e4fd8dad61e2e77f0754a23418cc70aad048cd92566f0a8","source":{"kind":"arxiv","id":"2505.12942","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12942","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12942v4","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12942","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"NMRMJ4HMJM3H","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NMRMJ4HMJM3HODSP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NMRMJ4HM","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NMRMJ4HMJM3HODSP3DNNMHROO7","target":"record","payload":{"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"},"canonical_sha256":"6b22c4f0ec4b36770e4fd8dad61e2e77f0754a23418cc70aad048cd92566f0a8","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"},"source_kind":"arxiv","source_id":"2505.12942","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"geHVjt1EVE4bMQWYdGD4dFW1Qjyx1q+qOXWcJ/scXrBAcpXIvP+XLG2z+jydfW14epvsX4mOGB4UYuDOTcN1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:01:28.653128Z"},"content_sha256":"6ecfdd1b30e81bf7d3b44a8ce52f7364345fda786764557eaa56b713c29e6e27","schema_version":"1.0","event_id":"sha256:6ecfdd1b30e81bf7d3b44a8ce52f7364345fda786764557eaa56b713c29e6e27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NMRMJ4HMJM3HODSP3DNNMHROO7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oLE5xwFrJAlbm8JP6LZcbsN0vcNSkWM+AGXpJwdQDNCeD0nNxkCzBWNUHI61HWdGerc0qx1oiqxKt3HU1n6zCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:01:28.653780Z"},"content_sha256":"17450eb46c04f6c4d9f1aa5f1f54f3c2c2e1a98a0471f95274728626ec4e32ca","schema_version":"1.0","event_id":"sha256:17450eb46c04f6c4d9f1aa5f1f54f3c2c2e1a98a0471f95274728626ec4e32ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/bundle.json","state_url":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-23T16:01:28Z","links":{"resolver":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7","bundle":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/bundle.json","state":"https://pith.science/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMRMJ4HMJM3HODSP3DNNMHROO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NMRMJ4HMJM3HODSP3DNNMHROO7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"06c065ebdd37bfd56bc05630ef68603f94c778daa2d6b8cca815e63841db911f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T10:29:32Z","title_canon_sha256":"0c608e30364cc93419908e4e451d86f304f562f89937840e180f4f424d8046ba"},"schema_version":"1.0","source":{"id":"2505.12942","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12942","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12942v4","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12942","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"NMRMJ4HMJM3H","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NMRMJ4HMJM3HODSP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NMRMJ4HM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:17450eb46c04f6c4d9f1aa5f1f54f3c2c2e1a98a0471f95274728626ec4e32ca","target":"graph","created_at":"2026-05-18T03:09:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Cheng Zhang, Christos-Savvas Bouganis, George A. Constantinides, Jeffrey T. H. Wong, Pedro Gimenes, Wayne Luk, Xinye Cao, Yiren Zhao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T10:29:32Z","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12942","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6ecfdd1b30e81bf7d3b44a8ce52f7364345fda786764557eaa56b713c29e6e27","target":"record","created_at":"2026-05-18T03:09:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"06c065ebdd37bfd56bc05630ef68603f94c778daa2d6b8cca815e63841db911f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T10:29:32Z","title_canon_sha256":"0c608e30364cc93419908e4e451d86f304f562f89937840e180f4f424d8046ba"},"schema_version":"1.0","source":{"id":"2505.12942","kind":"arxiv","version":4}},"canonical_sha256":"6b22c4f0ec4b36770e4fd8dad61e2e77f0754a23418cc70aad048cd92566f0a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b22c4f0ec4b36770e4fd8dad61e2e77f0754a23418cc70aad048cd92566f0a8","first_computed_at":"2026-05-18T03:09:35.672890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:35.672890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NkKsiK3qnipWIAg+5pF5R2rCTGJvyelgywKmTexHIAr8KDYbcWpZ0BHbmboq2UGkq9lEou6jPyOwOVyp595KAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:35.673700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12942","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ecfdd1b30e81bf7d3b44a8ce52f7364345fda786764557eaa56b713c29e6e27","sha256:17450eb46c04f6c4d9f1aa5f1f54f3c2c2e1a98a0471f95274728626ec4e32ca"],"state_sha256":"f66de19d92aabb1a577f40aed282357bdd5671fb25717be5269bf1794410faff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0NCVxvuvzsm3gZUoEihpZCJmTj3KjXaYuPZV++kL50Iylwk1SJDQxfwZMPDLz85DKfiwLQwrMr+IDd+bHPTlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T16:01:28.656878Z","bundle_sha256":"63f0595e63d8e4635b455949266349de3e051975121587d9b9ce7c1b9ebd261f"}}