{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TXZJCKYQRTCMJJIGLEV5BM2X6I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"be7d9c9fe683cbf6c89b42648d169324284f2fc75f8066ea51877336511ad5e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T17:56:09Z","title_canon_sha256":"2d7c1bef7171e62cfeb1076bb613a78e04085299f401123f5c03d536f5353627"},"schema_version":"1.0","source":{"id":"2406.10701","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10701","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10701v3","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10701","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"TXZJCKYQRTCM","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"TXZJCKYQRTCMJJIG","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"TXZJCKYQ","created_at":"2026-07-05T09:19:29Z"}],"graph_snapshots":[{"event_id":"sha256:c87e2efa71dc63c7e82784ac9051ff5309f11668878ca040741c193365f9f137","target":"graph","created_at":"2026-07-05T09:19:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.10701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T17:56:09Z","title":"MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10701","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b3463a52feef580b43c983033b8f652572490beca4928cdfd03617b2e4fe3e24","target":"record","created_at":"2026-07-05T09:19:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"be7d9c9fe683cbf6c89b42648d169324284f2fc75f8066ea51877336511ad5e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-15T17:56:09Z","title_canon_sha256":"2d7c1bef7171e62cfeb1076bb613a78e04085299f401123f5c03d536f5353627"},"schema_version":"1.0","source":{"id":"2406.10701","kind":"arxiv","version":3}},"canonical_sha256":"9df2912b108cc4c4a506592bd0b357f20424cdbf1990d86ffe576a09958d11d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9df2912b108cc4c4a506592bd0b357f20424cdbf1990d86ffe576a09958d11d2","first_computed_at":"2026-07-05T09:19:29.201098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:29.201098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2iJtV93bz9FtkSZ70M3HI3Lgh8l33x84cs3JmdFDXD+9fzpAwnZUCONogTo6EZyHzB18uZ0opBP4UaIbB5auDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:29.201592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10701","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3463a52feef580b43c983033b8f652572490beca4928cdfd03617b2e4fe3e24","sha256:c87e2efa71dc63c7e82784ac9051ff5309f11668878ca040741c193365f9f137"],"state_sha256":"32d4462e333b689e843396901add6fd66de97c686ac7a65dae5ed9a029236ad5"}