{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z4X4O7C57UKXQAI3WDKA4EDKYY","short_pith_number":"pith:Z4X4O7C5","schema_version":"1.0","canonical_sha256":"cf2fc77c5dfd1578011bb0d40e106ac605a8a1cf179c26e84830bc10f71e6244","source":{"kind":"arxiv","id":"2605.17366","version":1},"attestation_state":"computed","paper":{"title":"Text-Guided Visual Representation Learning for Robust Multimodal E-Commerce Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"TGQ-Former uses metadata as text guidance to extract robust visual tokens from cluttered product images for e-commerce retrieval.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jing Ma, Jungong Han, Pinghua Gong, Shijie Yang, Tianlu Zhang, Weijie Ding, Yanlong Zang, Yufei Guo","submitted_at":"2026-05-17T10:20:23Z","abstract_excerpt":"Multimodal item embeddings are crucial for e-commerce item-to-item (I2I) retrieval, yet real-world product images often contain promotional overlays and background clutter that inject spurious visual cues and degrade retrieval robustness. This issue is particularly pronounced in MLRM-style pipelines, where a frozen vision encoder is connected to an LLM through a lightweight connector that must selectively aggregate visual tokens. We propose Text-Guided Q-Former (TGQ-Former), a text-guided visual representation learning framework that leverages structured metadata as semantic guidance for visua"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.17366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-17T10:20:23Z","cross_cats_sorted":[],"title_canon_sha256":"af055bd0a527e76ae5e05797ca30bc7cbcef82b3d2350800a43ee05dcf39a1a7","abstract_canon_sha256":"ced29fbc25e10a66a68bc4b20cc98ce5020e53d0926cfa1fbe8cbaf0296fefcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:54.707030Z","signature_b64":"HFYKUnl/6DTI0CfWgC5zjlQK1Oft8qhYWrHcMBOTYDNXGfuUs57+MSjpHVwzof2bMkpraHV7FdYIsnK+wYQ+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf2fc77c5dfd1578011bb0d40e106ac605a8a1cf179c26e84830bc10f71e6244","last_reissued_at":"2026-05-20T00:03:54.706133Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:54.706133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Guided Visual Representation Learning for Robust Multimodal E-Commerce Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"TGQ-Former uses metadata as text guidance to extract robust visual tokens from cluttered product images for e-commerce retrieval.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jing Ma, Jungong Han, Pinghua Gong, Shijie Yang, Tianlu Zhang, Weijie Ding, Yanlong Zang, Yufei Guo","submitted_at":"2026-05-17T10:20:23Z","abstract_excerpt":"Multimodal item embeddings are crucial for e-commerce item-to-item (I2I) retrieval, yet real-world product images often contain promotional overlays and background clutter that inject spurious visual cues and degrade retrieval robustness. This issue is particularly pronounced in MLRM-style pipelines, where a frozen vision encoder is connected to an LLM through a lightweight connector that must selectively aggregate visual tokens. We propose Text-Guided Q-Former (TGQ-Former), a text-guided visual representation learning framework that leverages structured metadata as semantic guidance for visua"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TGQ-Former consistently outperforms strong connector baselines and end-to-end MLLMs on large-scale real-world e-commerce datasets with full-pool retrieval, improving Hit Rate@100 by 6.04% on average.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Structured metadata is assumed to be accurate and sufficient to serve as reliable semantic guidance that allows the hybrid-query connector to disentangle metadata-anchored and exploratory visual streams without discarding useful visual evidence.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TGQ-Former uses metadata-guided hybrid queries and dual-gated modulation to improve visual token selection in multimodal e-commerce retrieval, raising average Hit Rate@100 by 6.04% over baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TGQ-Former uses metadata as text guidance to extract robust visual tokens from cluttered product images for e-commerce retrieval.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"572b0de41057d05f0be1b78f17e871daaa05941cb2c71e141d8e8e11c2bc2fdc"},"source":{"id":"2605.17366","kind":"arxiv","version":1},"verdict":{"id":"84bfd2c5-0856-440c-8257-5f30a4e2dc34","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T23:04:45.034157Z","strongest_claim":"TGQ-Former consistently outperforms strong connector baselines and end-to-end MLLMs on large-scale real-world e-commerce datasets with full-pool retrieval, improving Hit Rate@100 by 6.04% on average.","one_line_summary":"TGQ-Former uses metadata-guided hybrid queries and dual-gated modulation to improve visual token selection in multimodal e-commerce retrieval, raising average Hit Rate@100 by 6.04% over baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Structured metadata is assumed to be accurate and sufficient to serve as reliable semantic guidance that allows the hybrid-query connector to disentangle metadata-anchored and exploratory visual streams without discarding useful visual evidence.","pith_extraction_headline":"TGQ-Former uses metadata as text guidance to extract robust visual tokens from cluttered product images for e-commerce retrieval."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17366/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:20.074033Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:13:07.902413Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.781589Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.717398Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e232b7c4acd199a838180dc0b7124cba051141dfefc98fc4423e03bc58fd62d0"},"references":{"count":39,"sample":[{"doi":"","year":null,"title":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al","work_id":"fc034223-773d-41c1-9c67-26803f4f7b70","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems35 (2022), 23716–23736","work_id":"ff84ce1c-5fe0-420e-822f-cf901016e452","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","ref_index":3,"cited_arxiv_id":"2511.21631","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":4,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"10.1145/3331184.3331254","year":2019,"title":"Xu Chen, Hanxiong Chen, Hongteng Xu, Yongfeng Zhang, Yixin Cao, Zheng Qin, and Hongyuan Zha. 2019. Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: T","work_id":"c6b0ed6f-ffae-4f38-a2df-ae8b2c9013a5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"931c9478ce21774350dd81aa692520a0241f75c75a56a94e310139e14f003f2d","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"41629445618ad3180fcc85312e41d05e5880ec6e737e8009046d5127e89fc6a5"},"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":"2605.17366","created_at":"2026-05-20T00:03:54.706290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17366v1","created_at":"2026-05-20T00:03:54.706290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17366","created_at":"2026-05-20T00:03:54.706290+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4X4O7C57UKX","created_at":"2026-05-20T00:03:54.706290+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4X4O7C57UKXQAI3","created_at":"2026-05-20T00:03:54.706290+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4X4O7C5","created_at":"2026-05-20T00:03:54.706290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY","json":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY.json","graph_json":"https://pith.science/api/pith-number/Z4X4O7C57UKXQAI3WDKA4EDKYY/graph.json","events_json":"https://pith.science/api/pith-number/Z4X4O7C57UKXQAI3WDKA4EDKYY/events.json","paper":"https://pith.science/paper/Z4X4O7C5"},"agent_actions":{"view_html":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY","download_json":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY.json","view_paper":"https://pith.science/paper/Z4X4O7C5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17366&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4X4O7C57UKXQAI3WDKA4EDKYY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4X4O7C57UKXQAI3WDKA4EDKYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY/action/storage_attestation","attest_author":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY/action/author_attestation","sign_citation":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY/action/citation_signature","submit_replication":"https://pith.science/pith/Z4X4O7C57UKXQAI3WDKA4EDKYY/action/replication_record"}},"created_at":"2026-05-20T00:03:54.706290+00:00","updated_at":"2026-05-20T00:03:54.706290+00:00"}