{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YBRGYEGBEPZN2F5LO6232Y6PLC","short_pith_number":"pith:YBRGYEGB","schema_version":"1.0","canonical_sha256":"c0626c10c123f2dd17ab77b5bd63cf5880a7e4f5fe275907a5ad7c2ac179a1cd","source":{"kind":"arxiv","id":"2304.04377","version":2},"attestation_state":"computed","paper":{"title":"Delving into E-Commerce Product Retrieval with Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fuyu Lv, Qingwen Liu, Xiaoyang Zheng, Xiaoyi Zeng, Zilong Wang","submitted_at":"2023-04-10T04:28:25Z","abstract_excerpt":"E-commerce search engines comprise a retrieval phase and a ranking phase, where the first one returns a candidate product set given user queries. Recently, vision-language pre-training, combining textual information with visual clues, has been popular in the application of retrieval tasks. In this paper, we propose a novel V+L pre-training method to solve the retrieval problem in Taobao Search. We design a visual pre-training task based on contrastive learning, outperforming common regression-based visual pre-training tasks. In addition, we adopt two negative sampling schemes, tailored for the"},"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":"2304.04377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-10T04:28:25Z","cross_cats_sorted":[],"title_canon_sha256":"2f537bc7a59caadbfce86ff65d11b56897d1cc732566c92f6ad97feeffb36ad7","abstract_canon_sha256":"e03be272d86aa248c4c0acc7d099d6a2d902449ba4ecf162e06d49979a8deb3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:18.800529Z","signature_b64":"WD8edLkrhydxQqXV5uFkQ86Pq7OFJKa7PURqJ7fwNsPsS3foe3aEuJUARh9IixH3BkmQuIgRHpKsNPE/yy/LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0626c10c123f2dd17ab77b5bd63cf5880a7e4f5fe275907a5ad7c2ac179a1cd","last_reissued_at":"2026-07-05T06:01:18.800071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:18.800071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delving into E-Commerce Product Retrieval with Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fuyu Lv, Qingwen Liu, Xiaoyang Zheng, Xiaoyi Zeng, Zilong Wang","submitted_at":"2023-04-10T04:28:25Z","abstract_excerpt":"E-commerce search engines comprise a retrieval phase and a ranking phase, where the first one returns a candidate product set given user queries. Recently, vision-language pre-training, combining textual information with visual clues, has been popular in the application of retrieval tasks. In this paper, we propose a novel V+L pre-training method to solve the retrieval problem in Taobao Search. We design a visual pre-training task based on contrastive learning, outperforming common regression-based visual pre-training tasks. In addition, we adopt two negative sampling schemes, tailored for the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04377","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/2304.04377/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":"2304.04377","created_at":"2026-07-05T06:01:18.800132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04377v2","created_at":"2026-07-05T06:01:18.800132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04377","created_at":"2026-07-05T06:01:18.800132+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBRGYEGBEPZN","created_at":"2026-07-05T06:01:18.800132+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBRGYEGBEPZN2F5L","created_at":"2026-07-05T06:01:18.800132+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBRGYEGB","created_at":"2026-07-05T06:01:18.800132+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/YBRGYEGBEPZN2F5LO6232Y6PLC","json":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC.json","graph_json":"https://pith.science/api/pith-number/YBRGYEGBEPZN2F5LO6232Y6PLC/graph.json","events_json":"https://pith.science/api/pith-number/YBRGYEGBEPZN2F5LO6232Y6PLC/events.json","paper":"https://pith.science/paper/YBRGYEGB"},"agent_actions":{"view_html":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC","download_json":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC.json","view_paper":"https://pith.science/paper/YBRGYEGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04377&json=true","fetch_graph":"https://pith.science/api/pith-number/YBRGYEGBEPZN2F5LO6232Y6PLC/graph.json","fetch_events":"https://pith.science/api/pith-number/YBRGYEGBEPZN2F5LO6232Y6PLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC/action/storage_attestation","attest_author":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC/action/author_attestation","sign_citation":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC/action/citation_signature","submit_replication":"https://pith.science/pith/YBRGYEGBEPZN2F5LO6232Y6PLC/action/replication_record"}},"created_at":"2026-07-05T06:01:18.800132+00:00","updated_at":"2026-07-05T06:01:18.800132+00:00"}