{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG","short_pith_number":"pith:PF5LJ4ZC","schema_version":"1.0","canonical_sha256":"797ab4f32239733809475e319d2b3a9187d8b5fcded05f8c8ffe55654505038c","source":{"kind":"arxiv","id":"2412.19322","version":3},"attestation_state":"computed","paper":{"title":"Mixed-precision numerics in scientific applications: survey and perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.CE","authors_text":"Aditya Kashi, David Rogers, Feiyi Wang, Hao Lu, Mallikarjun Shankar, Michael Matheson, Wesley Brewer","submitted_at":"2024-12-26T18:50:17Z","abstract_excerpt":"The explosive demand for artificial intelligence (AI) workloads has led to a significant increase in silicon area dedicated to lower-precision computations on recent high-performance computing hardware designs. However, mixed-precision capabilities, which can achieve performance improvements of 8x compared to double-precision in extreme compute-intensive workloads, remain largely untapped in most scientific applications. A growing number of efforts have shown that mixed-precision algorithmic innovations can deliver superior performance without sacrificing accuracy. These developments should pr"},"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":"2412.19322","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-12-26T18:50:17Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"1b6299a284dea5cd1e0bf9cbfbdced962422a9d9bc7af59c6c11149ebe94e516","abstract_canon_sha256":"8a433acfa31724cb7b47d4d09f67f35e5d4802369a25b97d7624724dc1265815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:46.498075Z","signature_b64":"wMb6+y5B7b5r5oM2weuga4VNqFPw2ZR+22IEBsBQ8fdqfc10bEH3kpAxuB01eIh+1/SXq3hZXNiq0TVCLFLkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"797ab4f32239733809475e319d2b3a9187d8b5fcded05f8c8ffe55654505038c","last_reissued_at":"2026-07-05T12:06:46.497606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:46.497606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixed-precision numerics in scientific applications: survey and perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.CE","authors_text":"Aditya Kashi, David Rogers, Feiyi Wang, Hao Lu, Mallikarjun Shankar, Michael Matheson, Wesley Brewer","submitted_at":"2024-12-26T18:50:17Z","abstract_excerpt":"The explosive demand for artificial intelligence (AI) workloads has led to a significant increase in silicon area dedicated to lower-precision computations on recent high-performance computing hardware designs. However, mixed-precision capabilities, which can achieve performance improvements of 8x compared to double-precision in extreme compute-intensive workloads, remain largely untapped in most scientific applications. A growing number of efforts have shown that mixed-precision algorithmic innovations can deliver superior performance without sacrificing accuracy. These developments should pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19322","kind":"arxiv","version":3},"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/2412.19322/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":"2412.19322","created_at":"2026-07-05T12:06:46.497662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19322v3","created_at":"2026-07-05T12:06:46.497662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19322","created_at":"2026-07-05T12:06:46.497662+00:00"},{"alias_kind":"pith_short_12","alias_value":"PF5LJ4ZCHFZT","created_at":"2026-07-05T12:06:46.497662+00:00"},{"alias_kind":"pith_short_16","alias_value":"PF5LJ4ZCHFZTQCKH","created_at":"2026-07-05T12:06:46.497662+00:00"},{"alias_kind":"pith_short_8","alias_value":"PF5LJ4ZC","created_at":"2026-07-05T12:06:46.497662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08339","citing_title":"Floating-point autotuning with customized precisions","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23727","citing_title":"Mixed-Precision in adaptive Runge-Kutta method for large ODE systems","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25759","citing_title":"Neural-Network-Based Variational Method in Nuclear Density Functional Theory: Application to the Extended Thomas-Fermi Model","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25759","citing_title":"Neural-Network-Based Variational Method in Nuclear Density Functional Theory: Application to the Extended Thomas-Fermi Model","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG","json":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG.json","graph_json":"https://pith.science/api/pith-number/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/graph.json","events_json":"https://pith.science/api/pith-number/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/events.json","paper":"https://pith.science/paper/PF5LJ4ZC"},"agent_actions":{"view_html":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG","download_json":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG.json","view_paper":"https://pith.science/paper/PF5LJ4ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19322&json=true","fetch_graph":"https://pith.science/api/pith-number/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/graph.json","fetch_events":"https://pith.science/api/pith-number/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/action/storage_attestation","attest_author":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/action/author_attestation","sign_citation":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/action/citation_signature","submit_replication":"https://pith.science/pith/PF5LJ4ZCHFZTQCKHLYYZ2KZ2SG/action/replication_record"}},"created_at":"2026-07-05T12:06:46.497662+00:00","updated_at":"2026-07-05T12:06:46.497662+00:00"}