{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CGQZJ6RIDDWQHEPOI56KG2ZQYW","short_pith_number":"pith:CGQZJ6RI","schema_version":"1.0","canonical_sha256":"11a194fa2818ed0391ee477ca36b30c5a526adef37976686b61c1610baa18f15","source":{"kind":"arxiv","id":"2112.11294","version":2},"attestation_state":"computed","paper":{"title":"Extending CLIP for Category-to-image Retrieval in E-commerce","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Ernst Kuiper, Maarten de Rijke, Mariya Hendriksen, Maurits Bleeker, Nanne van Noord, Svitlana Vakulenko","submitted_at":"2021-12-21T15:33:23Z","abstract_excerpt":"E-commerce provides rich multimodal data that is barely leveraged in practice. One aspect of this data is a category tree that is being used in search and recommendation. However, in practice, during a user's session there is often a mismatch between a textual and a visual representation of a given category. Motivated by the problem, we introduce the task of category-to-image retrieval in e-commerce and propose a model for the task, CLIP-ITA. The model leverages information from multiple modalities (textual, visual, and attribute modality) to create product representations. We explore how addi"},"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":"2112.11294","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T15:33:23Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"aadd78d8afc7a9e7202d22ab45d4e8a74b74da453ba2ea158e756f018db9c3d8","abstract_canon_sha256":"07545afefbcd4d6e7ad337a266b360a53a60618203b7ceeb6ff814db5e01e998"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:12.890864Z","signature_b64":"5wiwtXJ7CMN9e02AWtIVIyNvXqsGzs26AtfjgXhDNGLKtpI3VGg1UQX00CPX6svxZPYiWCNzXEzaUHkP4mZ+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11a194fa2818ed0391ee477ca36b30c5a526adef37976686b61c1610baa18f15","last_reissued_at":"2026-07-05T03:45:12.890406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:12.890406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extending CLIP for Category-to-image Retrieval in E-commerce","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Ernst Kuiper, Maarten de Rijke, Mariya Hendriksen, Maurits Bleeker, Nanne van Noord, Svitlana Vakulenko","submitted_at":"2021-12-21T15:33:23Z","abstract_excerpt":"E-commerce provides rich multimodal data that is barely leveraged in practice. One aspect of this data is a category tree that is being used in search and recommendation. However, in practice, during a user's session there is often a mismatch between a textual and a visual representation of a given category. Motivated by the problem, we introduce the task of category-to-image retrieval in e-commerce and propose a model for the task, CLIP-ITA. The model leverages information from multiple modalities (textual, visual, and attribute modality) to create product representations. We explore how addi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11294","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/2112.11294/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":"2112.11294","created_at":"2026-07-05T03:45:12.890466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11294v2","created_at":"2026-07-05T03:45:12.890466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11294","created_at":"2026-07-05T03:45:12.890466+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGQZJ6RIDDWQ","created_at":"2026-07-05T03:45:12.890466+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGQZJ6RIDDWQHEPO","created_at":"2026-07-05T03:45:12.890466+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGQZJ6RI","created_at":"2026-07-05T03:45:12.890466+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/CGQZJ6RIDDWQHEPOI56KG2ZQYW","json":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW.json","graph_json":"https://pith.science/api/pith-number/CGQZJ6RIDDWQHEPOI56KG2ZQYW/graph.json","events_json":"https://pith.science/api/pith-number/CGQZJ6RIDDWQHEPOI56KG2ZQYW/events.json","paper":"https://pith.science/paper/CGQZJ6RI"},"agent_actions":{"view_html":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW","download_json":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW.json","view_paper":"https://pith.science/paper/CGQZJ6RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11294&json=true","fetch_graph":"https://pith.science/api/pith-number/CGQZJ6RIDDWQHEPOI56KG2ZQYW/graph.json","fetch_events":"https://pith.science/api/pith-number/CGQZJ6RIDDWQHEPOI56KG2ZQYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/action/storage_attestation","attest_author":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/action/author_attestation","sign_citation":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/action/citation_signature","submit_replication":"https://pith.science/pith/CGQZJ6RIDDWQHEPOI56KG2ZQYW/action/replication_record"}},"created_at":"2026-07-05T03:45:12.890466+00:00","updated_at":"2026-07-05T03:45:12.890466+00:00"}