{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y6DGC3WCEQXLUDED3ONWPH4K7T","short_pith_number":"pith:Y6DGC3WC","schema_version":"1.0","canonical_sha256":"c786616ec2242eba0c83db9b679f8afce9b180a6879af3e8a448653d622ba10b","source":{"kind":"arxiv","id":"2204.03281","version":2},"attestation_state":"computed","paper":{"title":"Single-shot Embedding Dimension Search in Recommender System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongzhi Yin, Liang Qu, Lixin Zhang, Ningzhi Tang, Yonghong Ye, Yuhui Shi","submitted_at":"2022-04-07T08:13:52Z","abstract_excerpt":"As a crucial component of most modern deep recommender systems, feature embedding maps high-dimensional sparse user/item features into low-dimensional dense embeddings. However, these embeddings are usually assigned a unified dimension, which suffers from the following issues: (1) high memory usage and computation cost. (2) sub-optimal performance due to inferior dimension assignments. In order to alleviate the above issues, some works focus on automated embedding dimension search by formulating it as hyper-parameter optimization or embedding pruning problems. However, they either require well"},"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":"2204.03281","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-04-07T08:13:52Z","cross_cats_sorted":[],"title_canon_sha256":"fe424f1af5a15b6ef3d0bba83746e4d15dcf3ad0b402c5f77b234e36ab535499","abstract_canon_sha256":"6f2184db5cf8bbef9d1f1f6a3c4989bf778a44868bea41b7f0197beabfa582a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:52.315942Z","signature_b64":"PhR8QBhPqIE6qZTLESjf4Owe/9G0xJBB2fkbZ0yc2rNdIMKnI8fpFJt5Cb8FveZi664nFjVUVDHF53UdIFqtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c786616ec2242eba0c83db9b679f8afce9b180a6879af3e8a448653d622ba10b","last_reissued_at":"2026-07-05T04:14:52.315507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:52.315507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-shot Embedding Dimension Search in Recommender System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongzhi Yin, Liang Qu, Lixin Zhang, Ningzhi Tang, Yonghong Ye, Yuhui Shi","submitted_at":"2022-04-07T08:13:52Z","abstract_excerpt":"As a crucial component of most modern deep recommender systems, feature embedding maps high-dimensional sparse user/item features into low-dimensional dense embeddings. However, these embeddings are usually assigned a unified dimension, which suffers from the following issues: (1) high memory usage and computation cost. (2) sub-optimal performance due to inferior dimension assignments. In order to alleviate the above issues, some works focus on automated embedding dimension search by formulating it as hyper-parameter optimization or embedding pruning problems. However, they either require well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03281","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/2204.03281/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":"2204.03281","created_at":"2026-07-05T04:14:52.315565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03281v2","created_at":"2026-07-05T04:14:52.315565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03281","created_at":"2026-07-05T04:14:52.315565+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6DGC3WCEQXL","created_at":"2026-07-05T04:14:52.315565+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6DGC3WCEQXLUDED","created_at":"2026-07-05T04:14:52.315565+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6DGC3WC","created_at":"2026-07-05T04:14:52.315565+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/Y6DGC3WCEQXLUDED3ONWPH4K7T","json":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T.json","graph_json":"https://pith.science/api/pith-number/Y6DGC3WCEQXLUDED3ONWPH4K7T/graph.json","events_json":"https://pith.science/api/pith-number/Y6DGC3WCEQXLUDED3ONWPH4K7T/events.json","paper":"https://pith.science/paper/Y6DGC3WC"},"agent_actions":{"view_html":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T","download_json":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T.json","view_paper":"https://pith.science/paper/Y6DGC3WC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03281&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6DGC3WCEQXLUDED3ONWPH4K7T/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6DGC3WCEQXLUDED3ONWPH4K7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T/action/storage_attestation","attest_author":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T/action/author_attestation","sign_citation":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T/action/citation_signature","submit_replication":"https://pith.science/pith/Y6DGC3WCEQXLUDED3ONWPH4K7T/action/replication_record"}},"created_at":"2026-07-05T04:14:52.315565+00:00","updated_at":"2026-07-05T04:14:52.315565+00:00"}