{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QEBCFYN2SFYDGZVP5AKJVIVAHM","short_pith_number":"pith:QEBCFYN2","schema_version":"1.0","canonical_sha256":"810222e1ba91703366afe8149aa2a03b365b4996aa957c64c6ed636d279a3d1d","source":{"kind":"arxiv","id":"2108.04690","version":4},"attestation_state":"computed","paper":{"title":"POSO: Personalized Cold Start Modules for Large-scale Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Haobin Lin, Honghuan Wu, Jianying Lin, Ji Liu, Sen Yang, Shangfeng Dai, Zhe Wang, Zhichen Zhao","submitted_at":"2021-08-10T13:47:56Z","abstract_excerpt":"Recommendation for new users, also called user cold start, has been a well-recognized challenge for online recommender systems. Most existing methods view the crux as the lack of initial data. However, in this paper, we argue that there are neglected problems: 1) New users' behaviour follows much different distributions from regular users. 2) Although personalized features are involved, heavily imbalanced samples prevent the model from balancing new/regular user distributions, as if the personalized features are overwhelmed. We name the problem as the \"submergence\" of personalization. To tackl"},"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":"2108.04690","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-08-10T13:47:56Z","cross_cats_sorted":[],"title_canon_sha256":"68b86242f6132a628cd53729dab3af8354b62c7141c7d51c3499b1a8a797a42c","abstract_canon_sha256":"1dcd4842001846de3c20b2334f40337f1e19c85e2a06665511da87beb9986a04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:08.340657Z","signature_b64":"wto6KOWjY/KPeNIEQ8UmZyF064r9MQTN1U8HEjmKk3HkEw0B7Q33++fxgZguZ57wHnzkiUGW1MziALPLyGLGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"810222e1ba91703366afe8149aa2a03b365b4996aa957c64c6ed636d279a3d1d","last_reissued_at":"2026-07-05T03:08:08.340179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:08.340179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POSO: Personalized Cold Start Modules for Large-scale Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Haobin Lin, Honghuan Wu, Jianying Lin, Ji Liu, Sen Yang, Shangfeng Dai, Zhe Wang, Zhichen Zhao","submitted_at":"2021-08-10T13:47:56Z","abstract_excerpt":"Recommendation for new users, also called user cold start, has been a well-recognized challenge for online recommender systems. Most existing methods view the crux as the lack of initial data. However, in this paper, we argue that there are neglected problems: 1) New users' behaviour follows much different distributions from regular users. 2) Although personalized features are involved, heavily imbalanced samples prevent the model from balancing new/regular user distributions, as if the personalized features are overwhelmed. We name the problem as the \"submergence\" of personalization. To tackl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04690","kind":"arxiv","version":4},"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/2108.04690/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":"2108.04690","created_at":"2026-07-05T03:08:08.340236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04690v4","created_at":"2026-07-05T03:08:08.340236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04690","created_at":"2026-07-05T03:08:08.340236+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEBCFYN2SFYD","created_at":"2026-07-05T03:08:08.340236+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEBCFYN2SFYDGZVP","created_at":"2026-07-05T03:08:08.340236+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEBCFYN2","created_at":"2026-07-05T03:08:08.340236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21427","citing_title":"Dual-Attention Convolution Experts for Sparse Tensor Completion","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23310","citing_title":"From Head to Tail: Asymmetric Knowledge Transfer in Long-tail Recommendation with Generative Semantic IDs","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM","json":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM.json","graph_json":"https://pith.science/api/pith-number/QEBCFYN2SFYDGZVP5AKJVIVAHM/graph.json","events_json":"https://pith.science/api/pith-number/QEBCFYN2SFYDGZVP5AKJVIVAHM/events.json","paper":"https://pith.science/paper/QEBCFYN2"},"agent_actions":{"view_html":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM","download_json":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM.json","view_paper":"https://pith.science/paper/QEBCFYN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04690&json=true","fetch_graph":"https://pith.science/api/pith-number/QEBCFYN2SFYDGZVP5AKJVIVAHM/graph.json","fetch_events":"https://pith.science/api/pith-number/QEBCFYN2SFYDGZVP5AKJVIVAHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM/action/storage_attestation","attest_author":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM/action/author_attestation","sign_citation":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM/action/citation_signature","submit_replication":"https://pith.science/pith/QEBCFYN2SFYDGZVP5AKJVIVAHM/action/replication_record"}},"created_at":"2026-07-05T03:08:08.340236+00:00","updated_at":"2026-07-05T03:08:08.340236+00:00"}