{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W6LXFIKKBS4UR7PYNKF4HOQU47","short_pith_number":"pith:W6LXFIKK","schema_version":"1.0","canonical_sha256":"b79772a14a0cb948fdf86a8bc3ba14e7e54fcb78722517be2ad886216076c890","source":{"kind":"arxiv","id":"2506.11728","version":1},"attestation_state":"computed","paper":{"title":"The Cambrian Explosion of Mixed-Precision Matrix Multiplication for Quantized Deep Learning Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adri\\'an Castell\\'o, Enrique S. Quintana-Ort\\'i, Francisco D. Igual, H\\'ector Mart\\'inez","submitted_at":"2025-06-13T12:40:16Z","abstract_excerpt":"Recent advances in deep learning (DL) have led to a shift from traditional 64-bit floating point (FP64) computations toward reduced-precision formats, such as FP16, BF16, and 8- or 16-bit integers, combined with mixed-precision arithmetic. This transition enhances computational throughput, reduces memory and bandwidth usage, and improves energy efficiency, offering significant advantages for resource-constrained edge devices. To support this shift, hardware architectures have evolved accordingly, now including adapted ISAs (Instruction Set Architectures) that expose mixed-precision vector unit"},"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":"2506.11728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T12:40:16Z","cross_cats_sorted":[],"title_canon_sha256":"d9327a5cb94b07ad3d69badc4dbb95b21cdc77614de7f04ce5bb03e40de5ffca","abstract_canon_sha256":"7d6187379b48c8fe7913eaed870d832d780de49b0c6b20843122981f4d540634"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:09.815609Z","signature_b64":"+cRbMtE3ZBvbF23blnf6ESCMjhGnWvdxFi8UhRib6863LStDdf49F+PeXV9V4oLjbJ971fDe1QqEOWM3au5rAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b79772a14a0cb948fdf86a8bc3ba14e7e54fcb78722517be2ad886216076c890","last_reissued_at":"2026-07-05T11:21:09.815124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:09.815124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Cambrian Explosion of Mixed-Precision Matrix Multiplication for Quantized Deep Learning Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adri\\'an Castell\\'o, Enrique S. Quintana-Ort\\'i, Francisco D. Igual, H\\'ector Mart\\'inez","submitted_at":"2025-06-13T12:40:16Z","abstract_excerpt":"Recent advances in deep learning (DL) have led to a shift from traditional 64-bit floating point (FP64) computations toward reduced-precision formats, such as FP16, BF16, and 8- or 16-bit integers, combined with mixed-precision arithmetic. This transition enhances computational throughput, reduces memory and bandwidth usage, and improves energy efficiency, offering significant advantages for resource-constrained edge devices. To support this shift, hardware architectures have evolved accordingly, now including adapted ISAs (Instruction Set Architectures) that expose mixed-precision vector unit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11728","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/2506.11728/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":"2506.11728","created_at":"2026-07-05T11:21:09.815183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11728v1","created_at":"2026-07-05T11:21:09.815183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11728","created_at":"2026-07-05T11:21:09.815183+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6LXFIKKBS4U","created_at":"2026-07-05T11:21:09.815183+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6LXFIKKBS4UR7PY","created_at":"2026-07-05T11:21:09.815183+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6LXFIKK","created_at":"2026-07-05T11:21:09.815183+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/W6LXFIKKBS4UR7PYNKF4HOQU47","json":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47.json","graph_json":"https://pith.science/api/pith-number/W6LXFIKKBS4UR7PYNKF4HOQU47/graph.json","events_json":"https://pith.science/api/pith-number/W6LXFIKKBS4UR7PYNKF4HOQU47/events.json","paper":"https://pith.science/paper/W6LXFIKK"},"agent_actions":{"view_html":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47","download_json":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47.json","view_paper":"https://pith.science/paper/W6LXFIKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11728&json=true","fetch_graph":"https://pith.science/api/pith-number/W6LXFIKKBS4UR7PYNKF4HOQU47/graph.json","fetch_events":"https://pith.science/api/pith-number/W6LXFIKKBS4UR7PYNKF4HOQU47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47/action/storage_attestation","attest_author":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47/action/author_attestation","sign_citation":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47/action/citation_signature","submit_replication":"https://pith.science/pith/W6LXFIKKBS4UR7PYNKF4HOQU47/action/replication_record"}},"created_at":"2026-07-05T11:21:09.815183+00:00","updated_at":"2026-07-05T11:21:09.815183+00:00"}