{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4EGYECW7XYXAZCYHI6ILBSWOTI","short_pith_number":"pith:4EGYECW7","schema_version":"1.0","canonical_sha256":"e10d820adfbe2e0c8b074790b0cace9a0a7834612d7655ac0cac9213b28f8d8b","source":{"kind":"arxiv","id":"2301.12646","version":2},"attestation_state":"computed","paper":{"title":"MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ke Xu, Qingwen Liu, Sen Li, Tao Zhuang, Xiaoyang Zheng, Xiaoyi Zeng, Zilong Wang","submitted_at":"2023-01-30T03:59:36Z","abstract_excerpt":"Taobao Search consists of two phases: the retrieval phase and the ranking phase. Given a user query, the retrieval phase returns a subset of candidate products for the following ranking phase. Recently, the paradigm of pre-training and fine-tuning has shown its potential in incorporating visual clues into retrieval tasks. In this paper, we focus on solving the problem of text-to-multimodal retrieval in Taobao Search. We consider that users' attention on titles or images varies on products. Hence, we propose a novel Modal Adaptation module for cross-modal fusion, which helps assigns appropriate"},"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":"2301.12646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-01-30T03:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"c6756ef5d322765306b7802a4516eee1db786c21ace47f8763993c855d00e604","abstract_canon_sha256":"81be99794c6094a4e748e133a0f576dcf5351a4a5c86289d6d4d0847a41d84ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:19.403857Z","signature_b64":"Nqu5ncpa/jM28UDk36F1bP3sFQdvdz4f+CT/fOZA4A/4JmpNvgFh1Tk9yUSGEBU95Ig3FEyBue0AlplUZoEmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e10d820adfbe2e0c8b074790b0cace9a0a7834612d7655ac0cac9213b28f8d8b","last_reissued_at":"2026-07-05T05:43:19.403369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:19.403369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ke Xu, Qingwen Liu, Sen Li, Tao Zhuang, Xiaoyang Zheng, Xiaoyi Zeng, Zilong Wang","submitted_at":"2023-01-30T03:59:36Z","abstract_excerpt":"Taobao Search consists of two phases: the retrieval phase and the ranking phase. Given a user query, the retrieval phase returns a subset of candidate products for the following ranking phase. Recently, the paradigm of pre-training and fine-tuning has shown its potential in incorporating visual clues into retrieval tasks. In this paper, we focus on solving the problem of text-to-multimodal retrieval in Taobao Search. We consider that users' attention on titles or images varies on products. Hence, we propose a novel Modal Adaptation module for cross-modal fusion, which helps assigns appropriate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12646","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/2301.12646/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":"2301.12646","created_at":"2026-07-05T05:43:19.403425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12646v2","created_at":"2026-07-05T05:43:19.403425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12646","created_at":"2026-07-05T05:43:19.403425+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EGYECW7XYXA","created_at":"2026-07-05T05:43:19.403425+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EGYECW7XYXAZCYH","created_at":"2026-07-05T05:43:19.403425+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EGYECW7","created_at":"2026-07-05T05:43:19.403425+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/4EGYECW7XYXAZCYHI6ILBSWOTI","json":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI.json","graph_json":"https://pith.science/api/pith-number/4EGYECW7XYXAZCYHI6ILBSWOTI/graph.json","events_json":"https://pith.science/api/pith-number/4EGYECW7XYXAZCYHI6ILBSWOTI/events.json","paper":"https://pith.science/paper/4EGYECW7"},"agent_actions":{"view_html":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI","download_json":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI.json","view_paper":"https://pith.science/paper/4EGYECW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12646&json=true","fetch_graph":"https://pith.science/api/pith-number/4EGYECW7XYXAZCYHI6ILBSWOTI/graph.json","fetch_events":"https://pith.science/api/pith-number/4EGYECW7XYXAZCYHI6ILBSWOTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI/action/storage_attestation","attest_author":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI/action/author_attestation","sign_citation":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI/action/citation_signature","submit_replication":"https://pith.science/pith/4EGYECW7XYXAZCYHI6ILBSWOTI/action/replication_record"}},"created_at":"2026-07-05T05:43:19.403425+00:00","updated_at":"2026-07-05T05:43:19.403425+00:00"}