{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WFNOHMHO2PTNVJ4MRUGAMQ7QHK","short_pith_number":"pith:WFNOHMHO","schema_version":"1.0","canonical_sha256":"b15ae3b0eed3e6daa78c8d0c0643f03a93fd355dcc9f7f262dfd4b445cd113d3","source":{"kind":"arxiv","id":"2311.15578","version":2},"attestation_state":"computed","paper":{"title":"Experimental Analysis of Large-scale Learnable Vector Storage Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Hailin Zhang, Penghao Zhao, Tong Yang, Xupeng Miao, Yingxia Shao, Zirui Liu","submitted_at":"2023-11-27T07:11:47Z","abstract_excerpt":"Learnable embedding vector is one of the most important applications in machine learning, and is widely used in various database-related domains. However, the high dimensionality of sparse data in recommendation tasks and the huge volume of corpus in retrieval-related tasks lead to a large memory consumption of the embedding table, which poses a great challenge to the training and deployment of models. Recent research has proposed various methods to compress the embeddings at the cost of a slight decrease in model quality or the introduction of other overheads. Nevertheless, the relative perfo"},"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":"2311.15578","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T07:11:47Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"7bd31041cf7edac90aa07500dfe17a43d522bd05e1fade38cbeaefc6431f57f3","abstract_canon_sha256":"1eebef9f90d77b41698b1a2975d4c93b2f9dd93eb0b19c753503d074ece8836b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:21.799023Z","signature_b64":"RBj8qXqcJ54GmK96YsWqVQ0W7begDPXpytlHUBoMHSNf0llOFDZjslewEVmCjrbEFVqCPT4FiZZ9txMdotAGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b15ae3b0eed3e6daa78c8d0c0643f03a93fd355dcc9f7f262dfd4b445cd113d3","last_reissued_at":"2026-07-05T07:44:21.798540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:21.798540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Experimental Analysis of Large-scale Learnable Vector Storage Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Hailin Zhang, Penghao Zhao, Tong Yang, Xupeng Miao, Yingxia Shao, Zirui Liu","submitted_at":"2023-11-27T07:11:47Z","abstract_excerpt":"Learnable embedding vector is one of the most important applications in machine learning, and is widely used in various database-related domains. However, the high dimensionality of sparse data in recommendation tasks and the huge volume of corpus in retrieval-related tasks lead to a large memory consumption of the embedding table, which poses a great challenge to the training and deployment of models. Recent research has proposed various methods to compress the embeddings at the cost of a slight decrease in model quality or the introduction of other overheads. Nevertheless, the relative perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15578","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/2311.15578/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":"2311.15578","created_at":"2026-07-05T07:44:21.798599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15578v2","created_at":"2026-07-05T07:44:21.798599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15578","created_at":"2026-07-05T07:44:21.798599+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFNOHMHO2PTN","created_at":"2026-07-05T07:44:21.798599+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFNOHMHO2PTNVJ4M","created_at":"2026-07-05T07:44:21.798599+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFNOHMHO","created_at":"2026-07-05T07:44:21.798599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19561","citing_title":"Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK","json":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK.json","graph_json":"https://pith.science/api/pith-number/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/graph.json","events_json":"https://pith.science/api/pith-number/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/events.json","paper":"https://pith.science/paper/WFNOHMHO"},"agent_actions":{"view_html":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK","download_json":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK.json","view_paper":"https://pith.science/paper/WFNOHMHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15578&json=true","fetch_graph":"https://pith.science/api/pith-number/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/graph.json","fetch_events":"https://pith.science/api/pith-number/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/action/storage_attestation","attest_author":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/action/author_attestation","sign_citation":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/action/citation_signature","submit_replication":"https://pith.science/pith/WFNOHMHO2PTNVJ4MRUGAMQ7QHK/action/replication_record"}},"created_at":"2026-07-05T07:44:21.798599+00:00","updated_at":"2026-07-05T07:44:21.798599+00:00"}