{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TXZJCKYQRTCMJJIGLEV5BM2X6I","short_pith_number":"pith:TXZJCKYQ","schema_version":"1.0","canonical_sha256":"9df2912b108cc4c4a506592bd0b357f20424cdbf1990d86ffe576a09958d11d2","source":{"kind":"arxiv","id":"2406.10701","version":3},"attestation_state":"computed","paper":{"title":"MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baixuan Xu, Bing Yin, Changlong Yu, Chen Luo, Haochen Shi, Huihao Jing, Jiaxin Bai, Long Chen, Qingyu Yin, Tianqing Fang, Weiqi Wang, Wenxuan Ding, Xin Liu, Yangqiu Song, Zheng Li","submitted_at":"2024-06-15T17:56:09Z","abstract_excerpt":"Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquiring large-scale intentions bank on distilling large language models with human annotation for verification. Such an approach tends to generate product-centric intentions, overlook valuable visual information from product images, and incurs high costs for scalability. To address these issues, we introduce MIND, a multimodal framework that allows Large Vision-Language Models (LVLMs) to infer purchase intentions from mult"},"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":"2406.10701","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T17:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"2d7c1bef7171e62cfeb1076bb613a78e04085299f401123f5c03d536f5353627","abstract_canon_sha256":"be7d9c9fe683cbf6c89b42648d169324284f2fc75f8066ea51877336511ad5e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:29.201592Z","signature_b64":"2iJtV93bz9FtkSZ70M3HI3Lgh8l33x84cs3JmdFDXD+9fzpAwnZUCONogTo6EZyHzB18uZ0opBP4UaIbB5auDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df2912b108cc4c4a506592bd0b357f20424cdbf1990d86ffe576a09958d11d2","last_reissued_at":"2026-07-05T09:19:29.201098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:29.201098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baixuan Xu, Bing Yin, Changlong Yu, Chen Luo, Haochen Shi, Huihao Jing, Jiaxin Bai, Long Chen, Qingyu Yin, Tianqing Fang, Weiqi Wang, Wenxuan Ding, Xin Liu, Yangqiu Song, Zheng Li","submitted_at":"2024-06-15T17:56:09Z","abstract_excerpt":"Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquiring large-scale intentions bank on distilling large language models with human annotation for verification. Such an approach tends to generate product-centric intentions, overlook valuable visual information from product images, and incurs high costs for scalability. To address these issues, we introduce MIND, a multimodal framework that allows Large Vision-Language Models (LVLMs) to infer purchase intentions from mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10701","kind":"arxiv","version":3},"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/2406.10701/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":"2406.10701","created_at":"2026-07-05T09:19:29.201151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10701v3","created_at":"2026-07-05T09:19:29.201151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10701","created_at":"2026-07-05T09:19:29.201151+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXZJCKYQRTCM","created_at":"2026-07-05T09:19:29.201151+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXZJCKYQRTCMJJIG","created_at":"2026-07-05T09:19:29.201151+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXZJCKYQ","created_at":"2026-07-05T09:19:29.201151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04509","citing_title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I","json":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I.json","graph_json":"https://pith.science/api/pith-number/TXZJCKYQRTCMJJIGLEV5BM2X6I/graph.json","events_json":"https://pith.science/api/pith-number/TXZJCKYQRTCMJJIGLEV5BM2X6I/events.json","paper":"https://pith.science/paper/TXZJCKYQ"},"agent_actions":{"view_html":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I","download_json":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I.json","view_paper":"https://pith.science/paper/TXZJCKYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10701&json=true","fetch_graph":"https://pith.science/api/pith-number/TXZJCKYQRTCMJJIGLEV5BM2X6I/graph.json","fetch_events":"https://pith.science/api/pith-number/TXZJCKYQRTCMJJIGLEV5BM2X6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I/action/storage_attestation","attest_author":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I/action/author_attestation","sign_citation":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I/action/citation_signature","submit_replication":"https://pith.science/pith/TXZJCKYQRTCMJJIGLEV5BM2X6I/action/replication_record"}},"created_at":"2026-07-05T09:19:29.201151+00:00","updated_at":"2026-07-05T09:19:29.201151+00:00"}