{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6ILJKVT52PTRRMM5XFJ52W5YVS","short_pith_number":"pith:6ILJKVT5","schema_version":"1.0","canonical_sha256":"f21695567dd3e718b19db953dd5bb8acad1786d9ef127b332a490e00c5765f99","source":{"kind":"arxiv","id":"2412.11007","version":1},"attestation_state":"computed","paper":{"title":"FlashSparse: Minimizing Computation Redundancy for Fast Sparse Matrix Multiplications on Tensor Cores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Jinliang Shi, Rongtian Fu, Shigang Li, Tong Wu, Xueying Wang, Youxuan Xu","submitted_at":"2024-12-15T01:12:33Z","abstract_excerpt":"Sparse Matrix-matrix Multiplication (SpMM) and Sampled Dense-dense Matrix Multiplication (SDDMM) are important sparse operators in scientific computing and deep learning. Tensor Core Units (TCUs) enhance modern accelerators with superior computing power, which is promising to boost the performance of matrix operators to a higher level. However, due to the irregularity of unstructured sparse data, it is difficult to deliver practical speedups on TCUs. To this end, we propose FlashSparse, a novel approach to bridge the gap between sparse workloads and the TCU architecture. Specifically, FlashSpa"},"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":"2412.11007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-12-15T01:12:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"73dd07ba6a1aae249915ad42cc170fce2c2a79ba440a4bc6e241792734b56f93","abstract_canon_sha256":"a32468f9a333e2c79433e924eadb91751cbae726e5f74d322d7891848c8bd59f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:25.940519Z","signature_b64":"Ilr5BJChQWLPn/LweIN7Tu0g6S3YS0gdyICV8+YFOlQZcHEViTjVACBT9oQd8Axx+YOXaLcJdE969FfLKnJvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f21695567dd3e718b19db953dd5bb8acad1786d9ef127b332a490e00c5765f99","last_reissued_at":"2026-07-05T09:49:25.940062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:25.940062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlashSparse: Minimizing Computation Redundancy for Fast Sparse Matrix Multiplications on Tensor Cores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Jinliang Shi, Rongtian Fu, Shigang Li, Tong Wu, Xueying Wang, Youxuan Xu","submitted_at":"2024-12-15T01:12:33Z","abstract_excerpt":"Sparse Matrix-matrix Multiplication (SpMM) and Sampled Dense-dense Matrix Multiplication (SDDMM) are important sparse operators in scientific computing and deep learning. Tensor Core Units (TCUs) enhance modern accelerators with superior computing power, which is promising to boost the performance of matrix operators to a higher level. However, due to the irregularity of unstructured sparse data, it is difficult to deliver practical speedups on TCUs. To this end, we propose FlashSparse, a novel approach to bridge the gap between sparse workloads and the TCU architecture. Specifically, FlashSpa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11007","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/2412.11007/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":"2412.11007","created_at":"2026-07-05T09:49:25.940116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11007v1","created_at":"2026-07-05T09:49:25.940116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11007","created_at":"2026-07-05T09:49:25.940116+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ILJKVT52PTR","created_at":"2026-07-05T09:49:25.940116+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ILJKVT52PTRRMM5","created_at":"2026-07-05T09:49:25.940116+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ILJKVT5","created_at":"2026-07-05T09:49:25.940116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09251","citing_title":"Acc-SpMM: Accelerating General-purpose Sparse Matrix-Matrix Multiplication with GPU Tensor Cores","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS","json":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS.json","graph_json":"https://pith.science/api/pith-number/6ILJKVT52PTRRMM5XFJ52W5YVS/graph.json","events_json":"https://pith.science/api/pith-number/6ILJKVT52PTRRMM5XFJ52W5YVS/events.json","paper":"https://pith.science/paper/6ILJKVT5"},"agent_actions":{"view_html":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS","download_json":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS.json","view_paper":"https://pith.science/paper/6ILJKVT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11007&json=true","fetch_graph":"https://pith.science/api/pith-number/6ILJKVT52PTRRMM5XFJ52W5YVS/graph.json","fetch_events":"https://pith.science/api/pith-number/6ILJKVT52PTRRMM5XFJ52W5YVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS/action/storage_attestation","attest_author":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS/action/author_attestation","sign_citation":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS/action/citation_signature","submit_replication":"https://pith.science/pith/6ILJKVT52PTRRMM5XFJ52W5YVS/action/replication_record"}},"created_at":"2026-07-05T09:49:25.940116+00:00","updated_at":"2026-07-05T09:49:25.940116+00:00"}