{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T56B4GLYCQEDAZWLL5NXKNKERN","short_pith_number":"pith:T56B4GLY","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"},"canonical_sha256":"9f7c1e197814083066cb5f5b7535448b7a65a77baa5cb73511c67884fb2d1c2d","source":{"kind":"arxiv","id":"2409.02026","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02026","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02026v2","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02026","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"T56B4GLYCQED","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"T56B4GLYCQEDAZWL","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"T56B4GLY","created_at":"2026-07-05T09:15:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T56B4GLYCQEDAZWLL5NXKNKERN","target":"record","payload":{"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"},"canonical_sha256":"9f7c1e197814083066cb5f5b7535448b7a65a77baa5cb73511c67884fb2d1c2d","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"},"source_kind":"arxiv","source_id":"2409.02026","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mUc+UFmMsl6Bnv7EyFTwjU6dDxX5LPUGmGsa4AAVYDLrjk+qjDDMv/GIKRWwrQIgT7BT0gEr+yp/SB2TXCrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:29:45.036703Z"},"content_sha256":"d40188af9b1f7999f691cb432b13d4d788cbc007f14782bd6a11f9250ef02df7","schema_version":"1.0","event_id":"sha256:d40188af9b1f7999f691cb432b13d4d788cbc007f14782bd6a11f9250ef02df7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T56B4GLYCQEDAZWLL5NXKNKERN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ro1NcATzkMwTxKWYXiqmGSSlkyw+zGG9wzIIxz/x2cuHSaM/JdRbAwa0likbRd/FESXbFJ44zFsQk/c2ehA/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:29:45.037169Z"},"content_sha256":"56c4b3f5c557fdfa6c4da4e4c1cf11ae5a9f1ea47e470f573c7ede6b4a8564a1","schema_version":"1.0","event_id":"sha256:56c4b3f5c557fdfa6c4da4e4c1cf11ae5a9f1ea47e470f573c7ede6b4a8564a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/bundle.json","state_url":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T56B4GLYCQEDAZWLL5NXKNKERN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T04:29:45Z","links":{"resolver":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN","bundle":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/bundle.json","state":"https://pith.science/pith/T56B4GLYCQEDAZWLL5NXKNKERN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T56B4GLYCQEDAZWLL5NXKNKERN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T56B4GLYCQEDAZWLL5NXKNKERN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b55bb4c4ad33fa604a15078460c5cf6abd5b41f855728961d8d426aa78765b28","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-03T16:20:22Z","title_canon_sha256":"2210e62119f265696dde58a2e79b49946a3d382fd273648b0886443c709ef9f9"},"schema_version":"1.0","source":{"id":"2409.02026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02026","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02026v2","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02026","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"T56B4GLYCQED","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"T56B4GLYCQEDAZWL","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"T56B4GLY","created_at":"2026-07-05T09:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:56c4b3f5c557fdfa6c4da4e4c1cf11ae5a9f1ea47e470f573c7ede6b4a8564a1","target":"graph","created_at":"2026-07-05T09:15:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.02026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Sean I. Young","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-03T16:20:22Z","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02026","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d40188af9b1f7999f691cb432b13d4d788cbc007f14782bd6a11f9250ef02df7","target":"record","created_at":"2026-07-05T09:15:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b55bb4c4ad33fa604a15078460c5cf6abd5b41f855728961d8d426aa78765b28","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-03T16:20:22Z","title_canon_sha256":"2210e62119f265696dde58a2e79b49946a3d382fd273648b0886443c709ef9f9"},"schema_version":"1.0","source":{"id":"2409.02026","kind":"arxiv","version":2}},"canonical_sha256":"9f7c1e197814083066cb5f5b7535448b7a65a77baa5cb73511c67884fb2d1c2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f7c1e197814083066cb5f5b7535448b7a65a77baa5cb73511c67884fb2d1c2d","first_computed_at":"2026-07-05T09:15:14.234714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:14.234714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pmKjAUJEUSA+tf/rBlO0gOif77+/O+5qWudblyT+kh6ZQnGvwUV0PrH28iLnZPbCtwusYf0xkF1Aq2YsVKuVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:14.235139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d40188af9b1f7999f691cb432b13d4d788cbc007f14782bd6a11f9250ef02df7","sha256:56c4b3f5c557fdfa6c4da4e4c1cf11ae5a9f1ea47e470f573c7ede6b4a8564a1"],"state_sha256":"62dfdeba5dd314ef5b52d9671c246b07315668b06471be3f4277f687a392572c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0d5+XzecofUaAfwnpqLgqA/kc9flP0YSqTZ7ndDL81iK3Dsefy7tLZ/6qwWn9B8/8+acKln4WA11g9fmYU2iAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:29:45.040307Z","bundle_sha256":"b026ee65f8b67683a682ebd6b468d591947a2716b528fa49a6734b5c688a8a2b"}}