{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:65KPRIL5HAI4D4J2BTZACIPZ5N","short_pith_number":"pith:65KPRIL5","schema_version":"1.0","canonical_sha256":"f754f8a17d3811c1f13a0cf20121f9eb6ee23fb796d300023b921adc18e023ab","source":{"kind":"arxiv","id":"2412.06875","version":1},"attestation_state":"computed","paper":{"title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hong Gu, Juncan Deng, Kedong Xu, Kejie Huang, Shuaiting Li, Zeyu Wang","submitted_at":"2024-12-09T16:17:22Z","abstract_excerpt":"The rapid growth of the big neural network models puts forward new requirements for lightweight network representation methods. The traditional methods based on model compression have achieved great success, especially VQ technology which realizes the high compression ratio of models by sharing code words. However, because each layer of the network needs to build a code table, the traditional top-down compression technology lacks attention to the underlying commonalities, resulting in limited compression rate and frequent memory access. In this paper, we propose a bottom-up method to share the"},"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":"2412.06875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T16:17:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e740074b5e0d9007046e5e21b285268ded7eeff3b2dc06b1737b0e33e32cf5bf","abstract_canon_sha256":"1cbe0b55ff1cfd6c95e237a621c1124378a2bb63461aa03b9e1ff4c8636808d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:59.106231Z","signature_b64":"oN3fXzX09A2wnlGtmprE/xSqEiAd7VKYz3iGlaDsXvsVMMlP4NB85sjGYqTKmRg//sEKDjwMzdFCTbK3i6kdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f754f8a17d3811c1f13a0cf20121f9eb6ee23fb796d300023b921adc18e023ab","last_reissued_at":"2026-07-05T09:46:59.105762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:59.105762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hong Gu, Juncan Deng, Kedong Xu, Kejie Huang, Shuaiting Li, Zeyu Wang","submitted_at":"2024-12-09T16:17:22Z","abstract_excerpt":"The rapid growth of the big neural network models puts forward new requirements for lightweight network representation methods. The traditional methods based on model compression have achieved great success, especially VQ technology which realizes the high compression ratio of models by sharing code words. However, because each layer of the network needs to build a code table, the traditional top-down compression technology lacks attention to the underlying commonalities, resulting in limited compression rate and frequent memory access. In this paper, we propose a bottom-up method to share the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06875","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/2412.06875/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":"2412.06875","created_at":"2026-07-05T09:46:59.105832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06875v1","created_at":"2026-07-05T09:46:59.105832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06875","created_at":"2026-07-05T09:46:59.105832+00:00"},{"alias_kind":"pith_short_12","alias_value":"65KPRIL5HAI4","created_at":"2026-07-05T09:46:59.105832+00:00"},{"alias_kind":"pith_short_16","alias_value":"65KPRIL5HAI4D4J2","created_at":"2026-07-05T09:46:59.105832+00:00"},{"alias_kind":"pith_short_8","alias_value":"65KPRIL5","created_at":"2026-07-05T09:46:59.105832+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/65KPRIL5HAI4D4J2BTZACIPZ5N","json":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N.json","graph_json":"https://pith.science/api/pith-number/65KPRIL5HAI4D4J2BTZACIPZ5N/graph.json","events_json":"https://pith.science/api/pith-number/65KPRIL5HAI4D4J2BTZACIPZ5N/events.json","paper":"https://pith.science/paper/65KPRIL5"},"agent_actions":{"view_html":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N","download_json":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N.json","view_paper":"https://pith.science/paper/65KPRIL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06875&json=true","fetch_graph":"https://pith.science/api/pith-number/65KPRIL5HAI4D4J2BTZACIPZ5N/graph.json","fetch_events":"https://pith.science/api/pith-number/65KPRIL5HAI4D4J2BTZACIPZ5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N/action/storage_attestation","attest_author":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N/action/author_attestation","sign_citation":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N/action/citation_signature","submit_replication":"https://pith.science/pith/65KPRIL5HAI4D4J2BTZACIPZ5N/action/replication_record"}},"created_at":"2026-07-05T09:46:59.105832+00:00","updated_at":"2026-07-05T09:46:59.105832+00:00"}