{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K3DEZO4LIQXNRX6PI5BIBCNAMX","short_pith_number":"pith:K3DEZO4L","schema_version":"1.0","canonical_sha256":"56c64cbb8b442ed8dfcf47428089a065eb584c971f8417efdb1ca062d1998139","source":{"kind":"arxiv","id":"2204.02473","version":2},"attestation_state":"computed","paper":{"title":"\"Does it come in black?\" CLIP-like models are zero-shot recommenders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ciro Greco, Diogo Goncalves, Federico Bianchi, Jacopo Tagliabue, Patrick John Chia","submitted_at":"2022-04-05T20:15:23Z","abstract_excerpt":"Product discovery is a crucial component for online shopping. However, item-to-item recommendations today do not allow users to explore changes along selected dimensions: given a query item, can a model suggest something similar but in a different color? We consider item recommendations of the comparative nature (e.g. \"something darker\") and show how CLIP-based models can support this use case in a zero-shot manner. Leveraging a large model built for fashion, we introduce GradREC and its industry potential, and offer a first rounded assessment of its strength and weaknesses."},"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":"2204.02473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-04-05T20:15:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c490b38129835a5a9be9778da31852597087b856e1d156281461a2be1c32df6f","abstract_canon_sha256":"4de9a0fb0b5ec0998f2b3e3d08a601a8d51188358cbbed305190651cadc5e5ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:14.888356Z","signature_b64":"xFf4onehhYC/wUjjvyGXTEr7j1qJxUSRUQEga5AP4pUa0+wN+cAW+PZRIsVqJIBQpsO6RJnStgnAoCiHN0BhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56c64cbb8b442ed8dfcf47428089a065eb584c971f8417efdb1ca062d1998139","last_reissued_at":"2026-07-05T04:13:14.887945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:14.887945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Does it come in black?\" CLIP-like models are zero-shot recommenders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ciro Greco, Diogo Goncalves, Federico Bianchi, Jacopo Tagliabue, Patrick John Chia","submitted_at":"2022-04-05T20:15:23Z","abstract_excerpt":"Product discovery is a crucial component for online shopping. However, item-to-item recommendations today do not allow users to explore changes along selected dimensions: given a query item, can a model suggest something similar but in a different color? We consider item recommendations of the comparative nature (e.g. \"something darker\") and show how CLIP-based models can support this use case in a zero-shot manner. Leveraging a large model built for fashion, we introduce GradREC and its industry potential, and offer a first rounded assessment of its strength and weaknesses."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02473","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/2204.02473/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":"2204.02473","created_at":"2026-07-05T04:13:14.888009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02473v2","created_at":"2026-07-05T04:13:14.888009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02473","created_at":"2026-07-05T04:13:14.888009+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3DEZO4LIQXN","created_at":"2026-07-05T04:13:14.888009+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3DEZO4LIQXNRX6P","created_at":"2026-07-05T04:13:14.888009+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3DEZO4L","created_at":"2026-07-05T04:13:14.888009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16096","citing_title":"ENCLIP: Ensembling and Clustering-Based Contrastive Language-Image Pretraining for Fashion Multimodal Search with Limited Data and Low-Quality Images","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX","json":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX.json","graph_json":"https://pith.science/api/pith-number/K3DEZO4LIQXNRX6PI5BIBCNAMX/graph.json","events_json":"https://pith.science/api/pith-number/K3DEZO4LIQXNRX6PI5BIBCNAMX/events.json","paper":"https://pith.science/paper/K3DEZO4L"},"agent_actions":{"view_html":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX","download_json":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX.json","view_paper":"https://pith.science/paper/K3DEZO4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02473&json=true","fetch_graph":"https://pith.science/api/pith-number/K3DEZO4LIQXNRX6PI5BIBCNAMX/graph.json","fetch_events":"https://pith.science/api/pith-number/K3DEZO4LIQXNRX6PI5BIBCNAMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX/action/storage_attestation","attest_author":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX/action/author_attestation","sign_citation":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX/action/citation_signature","submit_replication":"https://pith.science/pith/K3DEZO4LIQXNRX6PI5BIBCNAMX/action/replication_record"}},"created_at":"2026-07-05T04:13:14.888009+00:00","updated_at":"2026-07-05T04:13:14.888009+00:00"}