{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C2PDXNSE6A2SRJQLT73KQU3MSD","short_pith_number":"pith:C2PDXNSE","schema_version":"1.0","canonical_sha256":"169e3bb644f03528a60b9ff6a8536c90c3c594894d8ff39caddcbf595ba6c81c","source":{"kind":"arxiv","id":"2502.15979","version":1},"attestation_state":"computed","paper":{"title":"Visual Zero-Shot E-Commerce Product Attribute Value Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Hoda Eldardiry, Hongda Shen, Janet Jenq, Jiaying Gong, Ming Cheng, Pierre-Yves Vandenbussche","submitted_at":"2025-02-21T22:31:03Z","abstract_excerpt":"Existing zero-shot product attribute value (aspect) extraction approaches in e-Commerce industry rely on uni-modal or multi-modal models, where the sellers are asked to provide detailed textual inputs (product descriptions) for the products. However, manually providing (typing) the product descriptions is time-consuming and frustrating for the sellers. Thus, we propose a cross-modal zero-shot attribute value generation framework (ViOC-AG) based on CLIP, which only requires product images as the inputs. ViOC-AG follows a text-only training process, where a task-customized text decoder is traine"},"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":"2502.15979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-21T22:31:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b286e8e51495bcf6c8de8dd35e0c6dee6211fba51cb9d672ee4bcdb6f3bed0e8","abstract_canon_sha256":"3e40fe61ef91813066115aacae2c5fbc11834dc532421b75ca9b98858620f787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:19.263837Z","signature_b64":"tdfUKHbp6HldG0zorIJuCtTqzKRK0xAUmdvqgzFANNDari0ZVMPE2A/pQ/Mt1IrN2xGn6TrT2Xy1oQAPAfwHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"169e3bb644f03528a60b9ff6a8536c90c3c594894d8ff39caddcbf595ba6c81c","last_reissued_at":"2026-07-05T10:18:19.263390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:19.263390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Zero-Shot E-Commerce Product Attribute Value Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Hoda Eldardiry, Hongda Shen, Janet Jenq, Jiaying Gong, Ming Cheng, Pierre-Yves Vandenbussche","submitted_at":"2025-02-21T22:31:03Z","abstract_excerpt":"Existing zero-shot product attribute value (aspect) extraction approaches in e-Commerce industry rely on uni-modal or multi-modal models, where the sellers are asked to provide detailed textual inputs (product descriptions) for the products. However, manually providing (typing) the product descriptions is time-consuming and frustrating for the sellers. Thus, we propose a cross-modal zero-shot attribute value generation framework (ViOC-AG) based on CLIP, which only requires product images as the inputs. ViOC-AG follows a text-only training process, where a task-customized text decoder is traine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15979","kind":"arxiv","version":1},"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/2502.15979/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":"2502.15979","created_at":"2026-07-05T10:18:19.263448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15979v1","created_at":"2026-07-05T10:18:19.263448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15979","created_at":"2026-07-05T10:18:19.263448+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2PDXNSE6A2S","created_at":"2026-07-05T10:18:19.263448+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2PDXNSE6A2SRJQL","created_at":"2026-07-05T10:18:19.263448+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2PDXNSE","created_at":"2026-07-05T10:18:19.263448+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/C2PDXNSE6A2SRJQLT73KQU3MSD","json":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD.json","graph_json":"https://pith.science/api/pith-number/C2PDXNSE6A2SRJQLT73KQU3MSD/graph.json","events_json":"https://pith.science/api/pith-number/C2PDXNSE6A2SRJQLT73KQU3MSD/events.json","paper":"https://pith.science/paper/C2PDXNSE"},"agent_actions":{"view_html":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD","download_json":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD.json","view_paper":"https://pith.science/paper/C2PDXNSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15979&json=true","fetch_graph":"https://pith.science/api/pith-number/C2PDXNSE6A2SRJQLT73KQU3MSD/graph.json","fetch_events":"https://pith.science/api/pith-number/C2PDXNSE6A2SRJQLT73KQU3MSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD/action/storage_attestation","attest_author":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD/action/author_attestation","sign_citation":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD/action/citation_signature","submit_replication":"https://pith.science/pith/C2PDXNSE6A2SRJQLT73KQU3MSD/action/replication_record"}},"created_at":"2026-07-05T10:18:19.263448+00:00","updated_at":"2026-07-05T10:18:19.263448+00:00"}