{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T56B4GLYCQEDAZWLL5NXKNKERN","short_pith_number":"pith:T56B4GLY","schema_version":"1.0","canonical_sha256":"9f7c1e197814083066cb5f5b7535448b7a65a77baa5cb73511c67884fb2d1c2d","source":{"kind":"arxiv","id":"2409.02026","version":2},"attestation_state":"computed","paper":{"title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Sean I. Young","submitted_at":"2024-09-03T16:20:22Z","abstract_excerpt":"In recent years, compression of large language models (LLMs) has emerged as an important problem to enable language model deployment on resource-constrained devices, reduce computational costs, and mitigate the environmental footprint of large-scale AI infrastructure. In this paper, we lay down the foundation for LLM quantization from a convex optimization perspective and propose a quantization technique that builds on this foundation for optimum quantization outcomes. Our quantization framework, CVXQ, scales to models containing hundreds of billions of weight parameters and provides users wit"},"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":"2409.02026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-03T16:20:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2210e62119f265696dde58a2e79b49946a3d382fd273648b0886443c709ef9f9","abstract_canon_sha256":"b55bb4c4ad33fa604a15078460c5cf6abd5b41f855728961d8d426aa78765b28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:14.235139Z","signature_b64":"pmKjAUJEUSA+tf/rBlO0gOif77+/O+5qWudblyT+kh6ZQnGvwUV0PrH28iLnZPbCtwusYf0xkF1Aq2YsVKuVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f7c1e197814083066cb5f5b7535448b7a65a77baa5cb73511c67884fb2d1c2d","last_reissued_at":"2026-07-05T09:15:14.234714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:14.234714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Sean I. Young","submitted_at":"2024-09-03T16:20:22Z","abstract_excerpt":"In recent years, compression of large language models (LLMs) has emerged as an important problem to enable language model deployment on resource-constrained devices, reduce computational costs, and mitigate the environmental footprint of large-scale AI infrastructure. In this paper, we lay down the foundation for LLM quantization from a convex optimization perspective and propose a quantization technique that builds on this foundation for optimum quantization outcomes. Our quantization framework, CVXQ, scales to models containing hundreds of billions of weight parameters and provides users wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02026","kind":"arxiv","version":2},"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/2409.02026/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":"2409.02026","created_at":"2026-07-05T09:15:14.234774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02026v2","created_at":"2026-07-05T09:15:14.234774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02026","created_at":"2026-07-05T09:15:14.234774+00:00"},{"alias_kind":"pith_short_12","alias_value":"T56B4GLYCQED","created_at":"2026-07-05T09:15:14.234774+00:00"},{"alias_kind":"pith_short_16","alias_value":"T56B4GLYCQEDAZWL","created_at":"2026-07-05T09:15:14.234774+00:00"},{"alias_kind":"pith_short_8","alias_value":"T56B4GLY","created_at":"2026-07-05T09:15:14.234774+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":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN","json":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN.json","graph_json":"https://pith.science/api/pith-number/T56B4GLYCQEDAZWLL5NXKNKERN/graph.json","events_json":"https://pith.science/api/pith-number/T56B4GLYCQEDAZWLL5NXKNKERN/events.json","paper":"https://pith.science/paper/T56B4GLY"},"agent_actions":{"view_html":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN","download_json":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN.json","view_paper":"https://pith.science/paper/T56B4GLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02026&json=true","fetch_graph":"https://pith.science/api/pith-number/T56B4GLYCQEDAZWLL5NXKNKERN/graph.json","fetch_events":"https://pith.science/api/pith-number/T56B4GLYCQEDAZWLL5NXKNKERN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/action/storage_attestation","attest_author":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/action/author_attestation","sign_citation":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/action/citation_signature","submit_replication":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/action/replication_record"}},"created_at":"2026-07-05T09:15:14.234774+00:00","updated_at":"2026-07-05T09:15:14.234774+00:00"}