{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B6PYWSDNQWE225LJBTSOXN7LCT","short_pith_number":"pith:B6PYWSDN","schema_version":"1.0","canonical_sha256":"0f9f8b486d8589ad75690ce4ebb7eb14f94e5071165924db4dd0da381b6d54b7","source":{"kind":"arxiv","id":"2302.03084","version":2},"attestation_state":"computed","paper":{"title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen-Yu Lee, Chun-Liang Li, Kate Saenko, Kihyuk Sohn, Kuniaki Saito, Tomas Pfister, Xiang Zhang","submitted_at":"2023-02-06T19:40:04Z","abstract_excerpt":"In Composed Image Retrieval (CIR), a user combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text specification, and the target image. Labeling such triplets is expensive and hinders broad applicability of CIR. In this work, we propose to study an important task, Zero-Shot Composed Image Retrieval (ZS-CIR), whose goal is to build a CIR model without requiring labeled triplets for training. To this end, we propose a novel method, called Pic2Word, that requires only w"},"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":"2302.03084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T19:40:04Z","cross_cats_sorted":[],"title_canon_sha256":"247402bb427d56bb747bc672c02318db4559d01359c3ca9259fed1f577a77331","abstract_canon_sha256":"01a7e6982abfa8373dcae6f4d8a5258399f40d4e2be616cabec87b025beacd29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:29.953850Z","signature_b64":"5cDcQdgVluh0Eq01yDOmTc6s36Msy7jeDJURswEqrMW8ZHksFm0BD1t/mnk9KZ9xTnQWdLVbGmRk9EzIMKdiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f9f8b486d8589ad75690ce4ebb7eb14f94e5071165924db4dd0da381b6d54b7","last_reissued_at":"2026-07-05T06:10:29.953430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:29.953430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen-Yu Lee, Chun-Liang Li, Kate Saenko, Kihyuk Sohn, Kuniaki Saito, Tomas Pfister, Xiang Zhang","submitted_at":"2023-02-06T19:40:04Z","abstract_excerpt":"In Composed Image Retrieval (CIR), a user combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text specification, and the target image. Labeling such triplets is expensive and hinders broad applicability of CIR. In this work, we propose to study an important task, Zero-Shot Composed Image Retrieval (ZS-CIR), whose goal is to build a CIR model without requiring labeled triplets for training. To this end, we propose a novel method, called Pic2Word, that requires only w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03084","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/2302.03084/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":"2302.03084","created_at":"2026-07-05T06:10:29.953487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03084v2","created_at":"2026-07-05T06:10:29.953487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03084","created_at":"2026-07-05T06:10:29.953487+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6PYWSDNQWE2","created_at":"2026-07-05T06:10:29.953487+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6PYWSDNQWE225LJ","created_at":"2026-07-05T06:10:29.953487+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6PYWSDN","created_at":"2026-07-05T06:10:29.953487+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/B6PYWSDNQWE225LJBTSOXN7LCT","json":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT.json","graph_json":"https://pith.science/api/pith-number/B6PYWSDNQWE225LJBTSOXN7LCT/graph.json","events_json":"https://pith.science/api/pith-number/B6PYWSDNQWE225LJBTSOXN7LCT/events.json","paper":"https://pith.science/paper/B6PYWSDN"},"agent_actions":{"view_html":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT","download_json":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT.json","view_paper":"https://pith.science/paper/B6PYWSDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03084&json=true","fetch_graph":"https://pith.science/api/pith-number/B6PYWSDNQWE225LJBTSOXN7LCT/graph.json","fetch_events":"https://pith.science/api/pith-number/B6PYWSDNQWE225LJBTSOXN7LCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT/action/storage_attestation","attest_author":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT/action/author_attestation","sign_citation":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT/action/citation_signature","submit_replication":"https://pith.science/pith/B6PYWSDNQWE225LJBTSOXN7LCT/action/replication_record"}},"created_at":"2026-07-05T06:10:29.953487+00:00","updated_at":"2026-07-05T06:10:29.953487+00:00"}