{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OU2NRQLAITWICAIG5CFFKO4N63","short_pith_number":"pith:OU2NRQLA","schema_version":"1.0","canonical_sha256":"7534d8c16044ec810106e88a553b8df6e66250802f89ea5917e862c87e8ed5ad","source":{"kind":"arxiv","id":"2108.04468","version":1},"attestation_state":"computed","paper":{"title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Changhua Pei, Chao Li, Junfeng Ge, Qiwei Chen, Shanshan Lv, Wenwu Ou","submitted_at":"2021-08-10T06:28:29Z","abstract_excerpt":"Click-Through Rate (CTR) prediction is one of the core tasks in recommender systems (RS). It predicts a personalized click probability for each user-item pair. Recently, researchers have found that the performance of CTR model can be improved greatly by taking user behavior sequence into consideration, especially long-term user behavior sequence. The report on an e-commerce website shows that 23\\% of users have more than 1000 clicks during the past 5 months. Though there are numerous works focus on modeling sequential user behaviors, few works can handle long-term user behavior sequence due to"},"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":"2108.04468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-08-10T06:28:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b1a1c9637dc65bb523817f4d91fa76124ee60e758d72eddb0c1572ce73115d0","abstract_canon_sha256":"3b613ee90879463580a01676aa85cd9aca12f9441301e6835059e64b07843d15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:30.915328Z","signature_b64":"z/aaZWLcUC2vxPXsg3PzoDKHyZHa/YRCBIb40gS1Lv6rxa4SvuD0M6FWpdHbFCNVlkAczuKdu+HpeIheeD7lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7534d8c16044ec810106e88a553b8df6e66250802f89ea5917e862c87e8ed5ad","last_reissued_at":"2026-07-05T03:04:30.914835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:30.914835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Changhua Pei, Chao Li, Junfeng Ge, Qiwei Chen, Shanshan Lv, Wenwu Ou","submitted_at":"2021-08-10T06:28:29Z","abstract_excerpt":"Click-Through Rate (CTR) prediction is one of the core tasks in recommender systems (RS). It predicts a personalized click probability for each user-item pair. Recently, researchers have found that the performance of CTR model can be improved greatly by taking user behavior sequence into consideration, especially long-term user behavior sequence. The report on an e-commerce website shows that 23\\% of users have more than 1000 clicks during the past 5 months. Though there are numerous works focus on modeling sequential user behaviors, few works can handle long-term user behavior sequence due to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04468","kind":"arxiv","version":1},"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/2108.04468/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":"2108.04468","created_at":"2026-07-05T03:04:30.914892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04468v1","created_at":"2026-07-05T03:04:30.914892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04468","created_at":"2026-07-05T03:04:30.914892+00:00"},{"alias_kind":"pith_short_12","alias_value":"OU2NRQLAITWI","created_at":"2026-07-05T03:04:30.914892+00:00"},{"alias_kind":"pith_short_16","alias_value":"OU2NRQLAITWICAIG","created_at":"2026-07-05T03:04:30.914892+00:00"},{"alias_kind":"pith_short_8","alias_value":"OU2NRQLA","created_at":"2026-07-05T03:04:30.914892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25726","citing_title":"SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25583","citing_title":"LENS: A Staged Design for Interaction Granularity in Sequential CTR Prediction","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15650","citing_title":"Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09040","citing_title":"UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15905","citing_title":"Generative Long-term User Interest Modeling for Click-Through Rate Prediction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11066","citing_title":"Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09040","citing_title":"UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09040","citing_title":"UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24806","citing_title":"Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23810","citing_title":"Similar Users-Augmented Interest Network","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19269","citing_title":"CS3: Efficient Online Capability Synergy for Two-Tower Recommendation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12298","citing_title":"Deep Situation-Aware Interaction Network for Click-Through Rate Prediction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05314","citing_title":"Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15650","citing_title":"Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63","json":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63.json","graph_json":"https://pith.science/api/pith-number/OU2NRQLAITWICAIG5CFFKO4N63/graph.json","events_json":"https://pith.science/api/pith-number/OU2NRQLAITWICAIG5CFFKO4N63/events.json","paper":"https://pith.science/paper/OU2NRQLA"},"agent_actions":{"view_html":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63","download_json":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63.json","view_paper":"https://pith.science/paper/OU2NRQLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04468&json=true","fetch_graph":"https://pith.science/api/pith-number/OU2NRQLAITWICAIG5CFFKO4N63/graph.json","fetch_events":"https://pith.science/api/pith-number/OU2NRQLAITWICAIG5CFFKO4N63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63/action/storage_attestation","attest_author":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63/action/author_attestation","sign_citation":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63/action/citation_signature","submit_replication":"https://pith.science/pith/OU2NRQLAITWICAIG5CFFKO4N63/action/replication_record"}},"created_at":"2026-07-05T03:04:30.914892+00:00","updated_at":"2026-07-05T03:04:30.914892+00:00"}