{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RD5Z466H6B2BYXDJJVEDZSQBPS","short_pith_number":"pith:RD5Z466H","schema_version":"1.0","canonical_sha256":"88fb9e7bc7f0741c5c694d483cca017cb59e1b71373eaa8432ec608639a7f6fd","source":{"kind":"arxiv","id":"2007.07203","version":2},"attestation_state":"computed","paper":{"title":"Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Chong Wang, Hui Yang, Jiankai Sun, Kai Jia, Ruofan Ding, Weihao Gao, Wenzhi Xiao, Xiangjun Fan, Xiaobing Liu, Xingyan Bin","submitted_at":"2020-07-12T06:23:51Z","abstract_excerpt":"One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an inner-product model, and then use some approximate nearest neighbor (ANN) search algorithm to find top candidates. In this paper, we present Deep Retrieval (DR), to learn a retrievable structure directly with user-item interaction data (e.g. clicks) without resorting to the Euclidean space assumption in ANN algorithms. DR's structure encodes all candidate items into "},"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":"2007.07203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-12T06:23:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"944886e488a396e66be2d599212c4b9f909e093db14292d36e0ee7cf34fc9af4","abstract_canon_sha256":"6ee09ff20f19a1a42a0823bfd5a1c4bda1473f5493b22a0d08e0d37a1df92ce2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:49.078740Z","signature_b64":"S7cwLXMP6sBfnFgU6hwNEaXVtS0LqsHgJiUUmnoxxnDTYKSTr6AfOzTDA2syZaKH7mwo05G0tTNvojZH/JdHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88fb9e7bc7f0741c5c694d483cca017cb59e1b71373eaa8432ec608639a7f6fd","last_reissued_at":"2026-07-05T02:40:49.078161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:49.078161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Chong Wang, Hui Yang, Jiankai Sun, Kai Jia, Ruofan Ding, Weihao Gao, Wenzhi Xiao, Xiangjun Fan, Xiaobing Liu, Xingyan Bin","submitted_at":"2020-07-12T06:23:51Z","abstract_excerpt":"One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an inner-product model, and then use some approximate nearest neighbor (ANN) search algorithm to find top candidates. In this paper, we present Deep Retrieval (DR), to learn a retrievable structure directly with user-item interaction data (e.g. clicks) without resorting to the Euclidean space assumption in ANN algorithms. DR's structure encodes all candidate items into "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07203","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/2007.07203/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":"2007.07203","created_at":"2026-07-05T02:40:49.078220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.07203v2","created_at":"2026-07-05T02:40:49.078220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07203","created_at":"2026-07-05T02:40:49.078220+00:00"},{"alias_kind":"pith_short_12","alias_value":"RD5Z466H6B2B","created_at":"2026-07-05T02:40:49.078220+00:00"},{"alias_kind":"pith_short_16","alias_value":"RD5Z466H6B2BYXDJ","created_at":"2026-07-05T02:40:49.078220+00:00"},{"alias_kind":"pith_short_8","alias_value":"RD5Z466H","created_at":"2026-07-05T02:40:49.078220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29970","citing_title":"From Extraction to Navigation: Progressive Retrieval with Indirectly Infinite Depth","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07546","citing_title":"Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12965","citing_title":"Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS","json":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS.json","graph_json":"https://pith.science/api/pith-number/RD5Z466H6B2BYXDJJVEDZSQBPS/graph.json","events_json":"https://pith.science/api/pith-number/RD5Z466H6B2BYXDJJVEDZSQBPS/events.json","paper":"https://pith.science/paper/RD5Z466H"},"agent_actions":{"view_html":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS","download_json":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS.json","view_paper":"https://pith.science/paper/RD5Z466H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.07203&json=true","fetch_graph":"https://pith.science/api/pith-number/RD5Z466H6B2BYXDJJVEDZSQBPS/graph.json","fetch_events":"https://pith.science/api/pith-number/RD5Z466H6B2BYXDJJVEDZSQBPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS/action/storage_attestation","attest_author":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS/action/author_attestation","sign_citation":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS/action/citation_signature","submit_replication":"https://pith.science/pith/RD5Z466H6B2BYXDJJVEDZSQBPS/action/replication_record"}},"created_at":"2026-07-05T02:40:49.078220+00:00","updated_at":"2026-07-05T02:40:49.078220+00:00"}