{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BKDH4EVMSNQKYCDQUDDDP34Q4U","short_pith_number":"pith:BKDH4EVM","schema_version":"1.0","canonical_sha256":"0a867e12ac9360ac0870a0c637ef90e50e3a087c259ed26d45a901db6f32efc1","source":{"kind":"arxiv","id":"2305.18236","version":1},"attestation_state":"computed","paper":{"title":"Fast Matrix Multiplication via Compiler-only Layered Data Reorganization and Intrinsic Lowering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Braedy Kuzma, Christopher Barton, Guido Araujo, Ivan Korostelev, Jo\\~ao P. L. de Carvalho, Jos\\'e E. Moreira, Jos\\'e Nelson Amaral","submitted_at":"2023-05-15T16:54:13Z","abstract_excerpt":"The resurgence of machine learning has increased the demand for high-performance basic linear algebra subroutines (BLAS), which have long depended on libraries to achieve peak performance on commodity hardware. High-performance BLAS implementations rely on a layered approach that consists of tiling and packing layers, for data (re)organization, and micro kernels that perform the actual computations. The creation of high-performance micro kernels requires significant development effort to write tailored assembly code for each architecture. This hand optimization task is complicated by the recen"},"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":"2305.18236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-05-15T16:54:13Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"f9d224aedc985b5d6c6a112f215bac0438328f8351127d952c15c07f8c1ec56c","abstract_canon_sha256":"ffea5488bdd11f7785273920626a73218a2fd772857e6cdad5920dbff4a4b136"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:53.915812Z","signature_b64":"u7Q9vv8N0X5sSk4uFkAXDXa42rNaE3jMZlDZeQHMDauWoX5CzMmmyAZuS29UBsYF7GragZ2iy/1KAcC/XY+CAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a867e12ac9360ac0870a0c637ef90e50e3a087c259ed26d45a901db6f32efc1","last_reissued_at":"2026-07-05T06:14:53.915361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:53.915361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Matrix Multiplication via Compiler-only Layered Data Reorganization and Intrinsic Lowering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Braedy Kuzma, Christopher Barton, Guido Araujo, Ivan Korostelev, Jo\\~ao P. L. de Carvalho, Jos\\'e E. Moreira, Jos\\'e Nelson Amaral","submitted_at":"2023-05-15T16:54:13Z","abstract_excerpt":"The resurgence of machine learning has increased the demand for high-performance basic linear algebra subroutines (BLAS), which have long depended on libraries to achieve peak performance on commodity hardware. High-performance BLAS implementations rely on a layered approach that consists of tiling and packing layers, for data (re)organization, and micro kernels that perform the actual computations. The creation of high-performance micro kernels requires significant development effort to write tailored assembly code for each architecture. This hand optimization task is complicated by the recen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18236","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/2305.18236/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":"2305.18236","created_at":"2026-07-05T06:14:53.915418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18236v1","created_at":"2026-07-05T06:14:53.915418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18236","created_at":"2026-07-05T06:14:53.915418+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKDH4EVMSNQK","created_at":"2026-07-05T06:14:53.915418+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKDH4EVMSNQKYCDQ","created_at":"2026-07-05T06:14:53.915418+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKDH4EVM","created_at":"2026-07-05T06:14:53.915418+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/BKDH4EVMSNQKYCDQUDDDP34Q4U","json":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U.json","graph_json":"https://pith.science/api/pith-number/BKDH4EVMSNQKYCDQUDDDP34Q4U/graph.json","events_json":"https://pith.science/api/pith-number/BKDH4EVMSNQKYCDQUDDDP34Q4U/events.json","paper":"https://pith.science/paper/BKDH4EVM"},"agent_actions":{"view_html":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U","download_json":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U.json","view_paper":"https://pith.science/paper/BKDH4EVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18236&json=true","fetch_graph":"https://pith.science/api/pith-number/BKDH4EVMSNQKYCDQUDDDP34Q4U/graph.json","fetch_events":"https://pith.science/api/pith-number/BKDH4EVMSNQKYCDQUDDDP34Q4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U/action/storage_attestation","attest_author":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U/action/author_attestation","sign_citation":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U/action/citation_signature","submit_replication":"https://pith.science/pith/BKDH4EVMSNQKYCDQUDDDP34Q4U/action/replication_record"}},"created_at":"2026-07-05T06:14:53.915418+00:00","updated_at":"2026-07-05T06:14:53.915418+00:00"}