{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XNAUCN672X57TT4DPNSRM2DDCW","short_pith_number":"pith:XNAUCN67","schema_version":"1.0","canonical_sha256":"bb414137dfd5fbf9cf837b6516686315b5a85f1564af6a684d3e833c6760bdb9","source":{"kind":"arxiv","id":"2305.12102","version":3},"attestation_state":"computed","paper":{"title":"Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Benjamin Coleman, Derek Zhiyuan Cheng, Ed H. Chi, Lichan Hong, Matthew Fahrbach, Ruoxi Wang, Wang-Cheng Kang","submitted_at":"2023-05-20T05:35:40Z","abstract_excerpt":"Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions of tokens. The standard approach is to represent each feature value as a d-dimensional embedding, introducing hundreds of billions of parameters for extremely high-cardinality features. This bottleneck has led to substantial progress in alternative embedding algorithms. Many of these methods, however, make the assumption that each feature uses an independent"},"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":"2305.12102","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T05:35:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6debfb91e9d9d03d4be377564666c3ed9022541709fc75e6d5e909deb78ae472","abstract_canon_sha256":"ab8ec8b7fcde34253d06b74c3562a397deaa90b9ce5127780d74c6bed3960f95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:59.125186Z","signature_b64":"+bjK1545j+utuzLbLtyNHpKNDNcQe5seZK5lIUdaAcy5FmvVrC8x2VWjSTGQ+WuFdNgavYk7Iek5PSv0joU9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb414137dfd5fbf9cf837b6516686315b5a85f1564af6a684d3e833c6760bdb9","last_reissued_at":"2026-07-05T08:32:59.124672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:59.124672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Benjamin Coleman, Derek Zhiyuan Cheng, Ed H. Chi, Lichan Hong, Matthew Fahrbach, Ruoxi Wang, Wang-Cheng Kang","submitted_at":"2023-05-20T05:35:40Z","abstract_excerpt":"Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions of tokens. The standard approach is to represent each feature value as a d-dimensional embedding, introducing hundreds of billions of parameters for extremely high-cardinality features. This bottleneck has led to substantial progress in alternative embedding algorithms. Many of these methods, however, make the assumption that each feature uses an independent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12102","kind":"arxiv","version":3},"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/2305.12102/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":"2305.12102","created_at":"2026-07-05T08:32:59.124737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12102v3","created_at":"2026-07-05T08:32:59.124737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12102","created_at":"2026-07-05T08:32:59.124737+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNAUCN672X57","created_at":"2026-07-05T08:32:59.124737+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNAUCN672X57TT4D","created_at":"2026-07-05T08:32:59.124737+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNAUCN67","created_at":"2026-07-05T08:32:59.124737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.17050","citing_title":"Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW","json":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW.json","graph_json":"https://pith.science/api/pith-number/XNAUCN672X57TT4DPNSRM2DDCW/graph.json","events_json":"https://pith.science/api/pith-number/XNAUCN672X57TT4DPNSRM2DDCW/events.json","paper":"https://pith.science/paper/XNAUCN67"},"agent_actions":{"view_html":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW","download_json":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW.json","view_paper":"https://pith.science/paper/XNAUCN67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12102&json=true","fetch_graph":"https://pith.science/api/pith-number/XNAUCN672X57TT4DPNSRM2DDCW/graph.json","fetch_events":"https://pith.science/api/pith-number/XNAUCN672X57TT4DPNSRM2DDCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/action/storage_attestation","attest_author":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/action/author_attestation","sign_citation":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/action/citation_signature","submit_replication":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/action/replication_record"}},"created_at":"2026-07-05T08:32:59.124737+00:00","updated_at":"2026-07-05T08:32:59.124737+00:00"}