{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G5GPCIJGVGWR6L7H4LRKL6TIDW","short_pith_number":"pith:G5GPCIJG","schema_version":"1.0","canonical_sha256":"374cf12126a9ad1f2fe7e2e2a5fa681d9139fda5eba983c0ea29cb7db9e5fbab","source":{"kind":"arxiv","id":"2407.19467","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Biao Wang, Bo Zheng, Feifan Yang, Han Zhu, Jian Xu, Litong Gong, Tiezheng Ge, Xiang-Rong Sheng, Yong-Nan Zhu, Yueyao Cheng, Yujing Zhang, Yuning Jiang, Zhangming Chan","submitted_at":"2024-07-28T11:36:47Z","abstract_excerpt":"Despite the recognized potential of multimodal data to improve model accuracy, many large-scale industrial recommendation systems, including Taobao display advertising system, predominantly depend on sparse ID features in their models. In this work, we explore approaches to leverage multimodal data to enhance the recommendation accuracy. We start from identifying the key challenges in adopting multimodal data in a manner that is both effective and cost-efficient for industrial systems. To address these challenges, we introduce a two-phase framework, including: 1) the pre-training of multimodal"},"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":"2407.19467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-28T11:36:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b9647e9637e874a77e6ca5144ab273ac73b346fa6c7f83c86ecbf3391a5fd7f","abstract_canon_sha256":"d7c0e943e564e9b8080008ed422f97f8e992d3756eb9d145c1a968511d1e0d21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:40.416906Z","signature_b64":"DN1etfI2bCs3pWAHRzLdeJSsTfYyx19ld7tOyb3M1aEyrxMDRzjZeNmTZMRIZ+UC1CasZWziLfg6yrjMQRqlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"374cf12126a9ad1f2fe7e2e2a5fa681d9139fda5eba983c0ea29cb7db9e5fbab","last_reissued_at":"2026-07-05T08:49:40.416480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:40.416480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Biao Wang, Bo Zheng, Feifan Yang, Han Zhu, Jian Xu, Litong Gong, Tiezheng Ge, Xiang-Rong Sheng, Yong-Nan Zhu, Yueyao Cheng, Yujing Zhang, Yuning Jiang, Zhangming Chan","submitted_at":"2024-07-28T11:36:47Z","abstract_excerpt":"Despite the recognized potential of multimodal data to improve model accuracy, many large-scale industrial recommendation systems, including Taobao display advertising system, predominantly depend on sparse ID features in their models. In this work, we explore approaches to leverage multimodal data to enhance the recommendation accuracy. We start from identifying the key challenges in adopting multimodal data in a manner that is both effective and cost-efficient for industrial systems. To address these challenges, we introduce a two-phase framework, including: 1) the pre-training of multimodal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19467","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/2407.19467/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":"2407.19467","created_at":"2026-07-05T08:49:40.416536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19467v1","created_at":"2026-07-05T08:49:40.416536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19467","created_at":"2026-07-05T08:49:40.416536+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5GPCIJGVGWR","created_at":"2026-07-05T08:49:40.416536+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5GPCIJGVGWR6L7H","created_at":"2026-07-05T08:49:40.416536+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5GPCIJG","created_at":"2026-07-05T08:49:40.416536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21460","citing_title":"Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW","json":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW.json","graph_json":"https://pith.science/api/pith-number/G5GPCIJGVGWR6L7H4LRKL6TIDW/graph.json","events_json":"https://pith.science/api/pith-number/G5GPCIJGVGWR6L7H4LRKL6TIDW/events.json","paper":"https://pith.science/paper/G5GPCIJG"},"agent_actions":{"view_html":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW","download_json":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW.json","view_paper":"https://pith.science/paper/G5GPCIJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19467&json=true","fetch_graph":"https://pith.science/api/pith-number/G5GPCIJGVGWR6L7H4LRKL6TIDW/graph.json","fetch_events":"https://pith.science/api/pith-number/G5GPCIJGVGWR6L7H4LRKL6TIDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW/action/storage_attestation","attest_author":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW/action/author_attestation","sign_citation":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW/action/citation_signature","submit_replication":"https://pith.science/pith/G5GPCIJGVGWR6L7H4LRKL6TIDW/action/replication_record"}},"created_at":"2026-07-05T08:49:40.416536+00:00","updated_at":"2026-07-05T08:49:40.416536+00:00"}