{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4OIO474N7Y47XRTIUGEN7BRNSK","short_pith_number":"pith:4OIO474N","canonical_record":{"source":{"id":"2409.17066","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T16:25:45Z","cross_cats_sorted":[],"title_canon_sha256":"1f70b4c4ebedd6a871cfc2e81e83adb6a98f595a31c84bb43e6aab412af6e6ce","abstract_canon_sha256":"5523cc411e3593e850f9a573e033e11c29ac269c5df54ac7154b2e5929bfb7ac"},"schema_version":"1.0"},"canonical_sha256":"e390ee7f8dfe39fbc668a188df862d92a993feecec851c6a99d6ec753f75202e","source":{"kind":"arxiv","id":"2409.17066","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17066","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17066v2","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17066","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"pith_short_12","alias_value":"4OIO474N7Y47","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"pith_short_16","alias_value":"4OIO474N7Y47XRTI","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"pith_short_8","alias_value":"4OIO474N","created_at":"2026-07-05T09:23:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4OIO474N7Y47XRTIUGEN7BRNSK","target":"record","payload":{"canonical_record":{"source":{"id":"2409.17066","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T16:25:45Z","cross_cats_sorted":[],"title_canon_sha256":"1f70b4c4ebedd6a871cfc2e81e83adb6a98f595a31c84bb43e6aab412af6e6ce","abstract_canon_sha256":"5523cc411e3593e850f9a573e033e11c29ac269c5df54ac7154b2e5929bfb7ac"},"schema_version":"1.0"},"canonical_sha256":"e390ee7f8dfe39fbc668a188df862d92a993feecec851c6a99d6ec753f75202e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:59.576712Z","signature_b64":"9pSHyhDZw1jLr1i2HHlconpBa04lBfutEKK9ehNlrdAWIgqszL9hlC3UkQpT2M91LFpbs2VHIBdMqBKJtVhOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e390ee7f8dfe39fbc668a188df862d92a993feecec851c6a99d6ec753f75202e","last_reissued_at":"2026-07-05T09:23:59.576161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:59.576161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.17066","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":"2026-07-05T09:23:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEbCuufqrh4oTvEXzWB405TTXhEo6IBPe2MOhyVXLw5vxtgmOVt/fsIV7ESSVokjFYzt7BG93qTfMSQgxcldDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:36:58.411430Z"},"content_sha256":"7c24bef20e869625ef99938b65419484626e33ef429379faf19170866e9c1828","schema_version":"1.0","event_id":"sha256:7c24bef20e869625ef99938b65419484626e33ef429379faf19170866e9c1828"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4OIO474N7Y47XRTIUGEN7BRNSK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Li, Jicheng Wen, Li Lyna Zhang, Mao Yang, Shengyu Ye, Ting Cao, Yang Wang, Yifei Liu","submitted_at":"2024-09-25T16:25:45Z","abstract_excerpt":"Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits). It reduces memory requirements, optimizes storage costs, and decreases memory bandwidth needs during inference. However, due to numerical representation limitations, traditional scalar-based weight quantization struggles to achieve such extreme low-bit. Recent research on Vector Quantization (VQ) for LLMs has demonstrated the potential for extrem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17066","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/2409.17066/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":"2026-07-05T09:23:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mTxnu88YyEzG3thWUNX98+X0cxYDAjwMpbLz5pYSxuw2mFxEBd0pmWo55VohMyIygiHb5u6zHvE11cGQk8MNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:36:58.414135Z"},"content_sha256":"3df587b5ab6505554504f4982135f48e77812125e75e2a8f5f0c4e60f2b5ef5c","schema_version":"1.0","event_id":"sha256:3df587b5ab6505554504f4982135f48e77812125e75e2a8f5f0c4e60f2b5ef5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OIO474N7Y47XRTIUGEN7BRNSK/bundle.json","state_url":"https://pith.science/pith/4OIO474N7Y47XRTIUGEN7BRNSK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OIO474N7Y47XRTIUGEN7BRNSK/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":"2026-08-07T10:36:58Z","links":{"resolver":"https://pith.science/pith/4OIO474N7Y47XRTIUGEN7BRNSK","bundle":"https://pith.science/pith/4OIO474N7Y47XRTIUGEN7BRNSK/bundle.json","state":"https://pith.science/pith/4OIO474N7Y47XRTIUGEN7BRNSK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OIO474N7Y47XRTIUGEN7BRNSK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4OIO474N7Y47XRTIUGEN7BRNSK","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":"5523cc411e3593e850f9a573e033e11c29ac269c5df54ac7154b2e5929bfb7ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T16:25:45Z","title_canon_sha256":"1f70b4c4ebedd6a871cfc2e81e83adb6a98f595a31c84bb43e6aab412af6e6ce"},"schema_version":"1.0","source":{"id":"2409.17066","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17066","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17066v2","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17066","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"pith_short_12","alias_value":"4OIO474N7Y47","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"pith_short_16","alias_value":"4OIO474N7Y47XRTI","created_at":"2026-07-05T09:23:59Z"},{"alias_kind":"pith_short_8","alias_value":"4OIO474N","created_at":"2026-07-05T09:23:59Z"}],"graph_snapshots":[{"event_id":"sha256:3df587b5ab6505554504f4982135f48e77812125e75e2a8f5f0c4e60f2b5ef5c","target":"graph","created_at":"2026-07-05T09:23:59Z","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/2409.17066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down to 2 bits). It reduces memory requirements, optimizes storage costs, and decreases memory bandwidth needs during inference. However, due to numerical representation limitations, traditional scalar-based weight quantization struggles to achieve such extreme low-bit. Recent research on Vector Quantization (VQ) for LLMs has demonstrated the potential for extrem","authors_text":"Cheng Li, Jicheng Wen, Li Lyna Zhang, Mao Yang, Shengyu Ye, Ting Cao, Yang Wang, Yifei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T16:25:45Z","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17066","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":"sha256:7c24bef20e869625ef99938b65419484626e33ef429379faf19170866e9c1828","target":"record","created_at":"2026-07-05T09:23:59Z","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":"5523cc411e3593e850f9a573e033e11c29ac269c5df54ac7154b2e5929bfb7ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T16:25:45Z","title_canon_sha256":"1f70b4c4ebedd6a871cfc2e81e83adb6a98f595a31c84bb43e6aab412af6e6ce"},"schema_version":"1.0","source":{"id":"2409.17066","kind":"arxiv","version":2}},"canonical_sha256":"e390ee7f8dfe39fbc668a188df862d92a993feecec851c6a99d6ec753f75202e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e390ee7f8dfe39fbc668a188df862d92a993feecec851c6a99d6ec753f75202e","first_computed_at":"2026-07-05T09:23:59.576161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:59.576161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9pSHyhDZw1jLr1i2HHlconpBa04lBfutEKK9ehNlrdAWIgqszL9hlC3UkQpT2M91LFpbs2VHIBdMqBKJtVhOBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:59.576712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17066","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c24bef20e869625ef99938b65419484626e33ef429379faf19170866e9c1828","sha256:3df587b5ab6505554504f4982135f48e77812125e75e2a8f5f0c4e60f2b5ef5c"],"state_sha256":"2741e81eaf8952aad7942be5dec40a301d82740d74b087b9aeb1b2abff12d6a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yzUk+VEnE3Km5SkkMeVUmlDmbg4dLxjefzK8TZ3yQs3zopOW1V027hQBdKNCXRwqA1g7UoF3Vojd2sqCjkq9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:36:58.433050Z","bundle_sha256":"5f0eee2175f641984cca3d7090efe32de4d705ee20b6f3b1f0945b8a240b440d"}}