{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MEDKC5QWTOK3FVBSERRIUX3QRI","short_pith_number":"pith:MEDKC5QW","schema_version":"1.0","canonical_sha256":"6106a176169b95b2d43224628a5f708a1337224fff843af584751492a435fb2f","source":{"kind":"arxiv","id":"2209.07663","version":2},"attestation_state":"computed","paper":{"title":"Monolith: Real Time Recommendation System With Collisionless Embedding Table","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Biao Zhang, Bolin Zhu, Caihua Wang, Da Tang, Ke Wang, Leqi Zou, Peng Wu, Xuan Zou, Yijie Zhu, Youlong Cheng, Zhuoran Liu","submitted_at":"2022-09-16T00:58:16Z","abstract_excerpt":"Building a scalable and real-time recommendation system is vital for many businesses driven by time-sensitive customer feedback, such as short-videos ranking or online ads. Despite the ubiquitous adoption of production-scale deep learning frameworks like TensorFlow or PyTorch, these general-purpose frameworks fall short of business demands in recommendation scenarios for various reasons: on one hand, tweaking systems based on static parameters and dense computations for recommendation with dynamic and sparse features is detrimental to model quality; on the other hand, such frameworks are desig"},"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":"2209.07663","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-09-16T00:58:16Z","cross_cats_sorted":[],"title_canon_sha256":"6cd5f08b7235698c0a1209146ee1db629716908fdd6c98153fbfc3f40aff88fe","abstract_canon_sha256":"a515cb771febf2e5e0fc673833de90711d29117702da978dc4599686241ad9e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:41.113078Z","signature_b64":"VnRsRaxZWd6AMXEqd9ErwjmdWFhKDhcoGmNun64+HqEspfTQ2CKWR8Sa7wsgGhdBANMVs/NBDs02QzWP+8VGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6106a176169b95b2d43224628a5f708a1337224fff843af584751492a435fb2f","last_reissued_at":"2026-07-05T05:01:41.112682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:41.112682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monolith: Real Time Recommendation System With Collisionless Embedding Table","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Biao Zhang, Bolin Zhu, Caihua Wang, Da Tang, Ke Wang, Leqi Zou, Peng Wu, Xuan Zou, Yijie Zhu, Youlong Cheng, Zhuoran Liu","submitted_at":"2022-09-16T00:58:16Z","abstract_excerpt":"Building a scalable and real-time recommendation system is vital for many businesses driven by time-sensitive customer feedback, such as short-videos ranking or online ads. Despite the ubiquitous adoption of production-scale deep learning frameworks like TensorFlow or PyTorch, these general-purpose frameworks fall short of business demands in recommendation scenarios for various reasons: on one hand, tweaking systems based on static parameters and dense computations for recommendation with dynamic and sparse features is detrimental to model quality; on the other hand, such frameworks are desig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07663","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/2209.07663/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":"2209.07663","created_at":"2026-07-05T05:01:41.112743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07663v2","created_at":"2026-07-05T05:01:41.112743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07663","created_at":"2026-07-05T05:01:41.112743+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEDKC5QWTOK3","created_at":"2026-07-05T05:01:41.112743+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEDKC5QWTOK3FVBS","created_at":"2026-07-05T05:01:41.112743+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEDKC5QW","created_at":"2026-07-05T05:01:41.112743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.24226","citing_title":"Joint Model Parameter Scaling and Universal-Domain Data Integration for E-commerce Search Ranking","ref_index":16,"is_internal_anchor":false},{"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":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16344","citing_title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI","json":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI.json","graph_json":"https://pith.science/api/pith-number/MEDKC5QWTOK3FVBSERRIUX3QRI/graph.json","events_json":"https://pith.science/api/pith-number/MEDKC5QWTOK3FVBSERRIUX3QRI/events.json","paper":"https://pith.science/paper/MEDKC5QW"},"agent_actions":{"view_html":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI","download_json":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI.json","view_paper":"https://pith.science/paper/MEDKC5QW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07663&json=true","fetch_graph":"https://pith.science/api/pith-number/MEDKC5QWTOK3FVBSERRIUX3QRI/graph.json","fetch_events":"https://pith.science/api/pith-number/MEDKC5QWTOK3FVBSERRIUX3QRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI/action/storage_attestation","attest_author":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI/action/author_attestation","sign_citation":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI/action/citation_signature","submit_replication":"https://pith.science/pith/MEDKC5QWTOK3FVBSERRIUX3QRI/action/replication_record"}},"created_at":"2026-07-05T05:01:41.112743+00:00","updated_at":"2026-07-05T05:01:41.112743+00:00"}