{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:54M7QLOULRNBFWNASGVZSE2VVO","short_pith_number":"pith:54M7QLOU","schema_version":"1.0","canonical_sha256":"ef19f82dd45c5a12d9a091ab991355abbe9fcc292adc5f6a24cfec1a8ae3e533","source":{"kind":"arxiv","id":"2601.17187","version":2},"attestation_state":"computed","paper":{"title":"High-Rate Quantized Matrix Multiplication I","license":"http://creativecommons.org/licenses/by/4.0/","headline":"High-rate quantization theory supplies the exact rate-distortion tradeoff for generic matrix multiplication without calibration data","cross_cats":["cs.AI","math.IT"],"primary_cat":"cs.IT","authors_text":"Or Ordentlich, Yury Polyanskiy","submitted_at":"2026-01-23T21:32:44Z","abstract_excerpt":"This paper investigates the problem of quantized matrix multiplication (MatMul), which has become crucial for the efficient deployment of large language models (LLMs). We consider a Generic MatMul setting, where both matrices must be quantized (weight+activation quantization) without specific apriori (calibration) statistical information about the factors. We review the fundamental information-theoretic tradeoff between quantization rate and distortion (high-rate theory), and contrast those with the performance of popular quantization schemes (absmax INT and floating-point (FP)), for which we "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2601.17187","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2026-01-23T21:32:44Z","cross_cats_sorted":["cs.AI","math.IT"],"title_canon_sha256":"28bcc846e0410a8e212152795b8654dd2d2f8d8c9d653880774b0defc57e3612","abstract_canon_sha256":"af679655c803b83f98f81d09126d6b8465a13bdc2ddd9173821e766171303659"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:31.871668Z","signature_b64":"2f8oeMhSlcfz4sqZm2rQKJ+A/10zfbBvKpomop//uR1ZfFAEiYm7QUTbFRHSNcZykJDzjZUBqhuhiAHPBGx+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef19f82dd45c5a12d9a091ab991355abbe9fcc292adc5f6a24cfec1a8ae3e533","last_reissued_at":"2026-05-18T02:44:31.871149Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:31.871149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Rate Quantized Matrix Multiplication I","license":"http://creativecommons.org/licenses/by/4.0/","headline":"High-rate quantization theory supplies the exact rate-distortion tradeoff for generic matrix multiplication without calibration data","cross_cats":["cs.AI","math.IT"],"primary_cat":"cs.IT","authors_text":"Or Ordentlich, Yury Polyanskiy","submitted_at":"2026-01-23T21:32:44Z","abstract_excerpt":"This paper investigates the problem of quantized matrix multiplication (MatMul), which has become crucial for the efficient deployment of large language models (LLMs). We consider a Generic MatMul setting, where both matrices must be quantized (weight+activation quantization) without specific apriori (calibration) statistical information about the factors. We review the fundamental information-theoretic tradeoff between quantization rate and distortion (high-rate theory), and contrast those with the performance of popular quantization schemes (absmax INT and floating-point (FP)), for which we "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We review the fundamental information-theoretic tradeoff between quantization rate and distortion (high-rate theory), and contrast those with the performance of popular quantization schemes (absmax INT and floating-point (FP)), for which we also derive accurate heuristic approximations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The generic MatMul setting can be analyzed under the high-rate quantization regime without any a priori statistical information about the matrix factors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"High-rate quantization theory yields accurate approximations for the distortion of absmax INT and FP schemes in generic weight-plus-activation matrix multiplication.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"High-rate quantization theory supplies the exact rate-distortion tradeoff for generic matrix multiplication without calibration data","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7bc443eb058df2aed8e51aed07ee7cc0485c7aeb5ebbf2c6651408dafed870ee"},"source":{"id":"2601.17187","kind":"arxiv","version":2},"verdict":{"id":"d982e895-9e5a-4c8d-8015-8dd24e07edad","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T11:16:04.954721Z","strongest_claim":"We review the fundamental information-theoretic tradeoff between quantization rate and distortion (high-rate theory), and contrast those with the performance of popular quantization schemes (absmax INT and floating-point (FP)), for which we also derive accurate heuristic approximations.","one_line_summary":"High-rate quantization theory yields accurate approximations for the distortion of absmax INT and FP schemes in generic weight-plus-activation matrix multiplication.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The generic MatMul setting can be analyzed under the high-rate quantization regime without any a priori statistical information about the matrix factors.","pith_extraction_headline":"High-rate quantization theory supplies the exact rate-distortion tradeoff for generic matrix multiplication without calibration data"},"references":{"count":51,"sample":[{"doi":"","year":2024,"title":"Optimal quantization for matrix multiplication,","work_id":"67e0dada-22c6-4282-81b0-f8ec7b786c89","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"OPTQ: Accurate quantization for generative pre-trained transformers,","work_id":"3902ff1c-dfb5-4adc-870b-c8ec9abfbb82","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Quip: 2- bit quantization of large language models with guarantees,","work_id":"0aba206f-56c2-4635-8de8-d421053e5962","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"NestQuant: Nested lattice quantization for matrix products and LLMs,","work_id":"f992de1c-558b-403e-b88e-f81e0e9e5949","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale,","work_id":"e5a95f16-d998-4ef7-9f71-01077b057362","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":51,"snapshot_sha256":"3a839c1fa857ae7801c55a43c41d51102551b6338778401aeb66350a17eb72a9","internal_anchors":3},"formal_canon":{"evidence_count":3,"snapshot_sha256":"c0909d9ee5197e0c66e99c03234a7c7d4d637ab52bff298a627b8bde1ce34325"},"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":"2601.17187","created_at":"2026-05-18T02:44:31.871234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.17187v2","created_at":"2026-05-18T02:44:31.871234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17187","created_at":"2026-05-18T02:44:31.871234+00:00"},{"alias_kind":"pith_short_12","alias_value":"54M7QLOULRNB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"54M7QLOULRNBFWNA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"54M7QLOU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.18745","citing_title":"Contraction-Gauge Preconditioning for Quantized Matrix Multiplication","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO","json":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO.json","graph_json":"https://pith.science/api/pith-number/54M7QLOULRNBFWNASGVZSE2VVO/graph.json","events_json":"https://pith.science/api/pith-number/54M7QLOULRNBFWNASGVZSE2VVO/events.json","paper":"https://pith.science/paper/54M7QLOU"},"agent_actions":{"view_html":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO","download_json":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO.json","view_paper":"https://pith.science/paper/54M7QLOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.17187&json=true","fetch_graph":"https://pith.science/api/pith-number/54M7QLOULRNBFWNASGVZSE2VVO/graph.json","fetch_events":"https://pith.science/api/pith-number/54M7QLOULRNBFWNASGVZSE2VVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO/action/storage_attestation","attest_author":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO/action/author_attestation","sign_citation":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO/action/citation_signature","submit_replication":"https://pith.science/pith/54M7QLOULRNBFWNASGVZSE2VVO/action/replication_record"}},"created_at":"2026-05-18T02:44:31.871234+00:00","updated_at":"2026-05-18T02:44:31.871234+00:00"}