{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VSOPB4B2U4CBIEZSYYHXJ4NIRT","short_pith_number":"pith:VSOPB4B2","schema_version":"1.0","canonical_sha256":"ac9cf0f03aa704141332c60f74f1a88ccf705b34d52de1a6baed8afdec59d042","source":{"kind":"arxiv","id":"2411.16752","version":2},"attestation_state":"computed","paper":{"title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Ma, Yi Yang, You Li","submitted_at":"2024-11-24T05:27:21Z","abstract_excerpt":"The Zero-shot Composed Image Retrieval (ZSCIR) requires retrieving images that match the query image and the relative captions. Current methods focus on projecting the query image into the text feature space, subsequently combining them with features of query texts for retrieval. However, retrieving images only with the text features cannot guarantee detailed alignment due to the natural gap between images and text. In this paper, we introduce Imagined Proxy for CIR (IP-CIR), a training-free method that creates a proxy image aligned with the query image and text description, enhancing query re"},"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":"2411.16752","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T05:27:21Z","cross_cats_sorted":[],"title_canon_sha256":"34e462250478c15b05c5038b9dd298e68c56f10661097e8fdf61b2156ff09830","abstract_canon_sha256":"59c6daa67d641c510e71c72320a679edf0564c51cd1383b8f07bb609e822dea8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:33.548957Z","signature_b64":"4Q7yhIzsXNfH4i5E04w6PJlaFo9x8Brwlb5O8OTWZAu5t3adO1egEKm9JwGlAJzs8/8hV0sHMqVGpWOiHR30Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac9cf0f03aa704141332c60f74f1a88ccf705b34d52de1a6baed8afdec59d042","last_reissued_at":"2026-07-05T09:42:33.548447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:33.548447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Ma, Yi Yang, You Li","submitted_at":"2024-11-24T05:27:21Z","abstract_excerpt":"The Zero-shot Composed Image Retrieval (ZSCIR) requires retrieving images that match the query image and the relative captions. Current methods focus on projecting the query image into the text feature space, subsequently combining them with features of query texts for retrieval. However, retrieving images only with the text features cannot guarantee detailed alignment due to the natural gap between images and text. In this paper, we introduce Imagined Proxy for CIR (IP-CIR), a training-free method that creates a proxy image aligned with the query image and text description, enhancing query re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16752","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/2411.16752/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":"2411.16752","created_at":"2026-07-05T09:42:33.548512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16752v2","created_at":"2026-07-05T09:42:33.548512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16752","created_at":"2026-07-05T09:42:33.548512+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSOPB4B2U4CB","created_at":"2026-07-05T09:42:33.548512+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSOPB4B2U4CBIEZS","created_at":"2026-07-05T09:42:33.548512+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSOPB4B2","created_at":"2026-07-05T09:42:33.548512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12819","citing_title":"MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT","json":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT.json","graph_json":"https://pith.science/api/pith-number/VSOPB4B2U4CBIEZSYYHXJ4NIRT/graph.json","events_json":"https://pith.science/api/pith-number/VSOPB4B2U4CBIEZSYYHXJ4NIRT/events.json","paper":"https://pith.science/paper/VSOPB4B2"},"agent_actions":{"view_html":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT","download_json":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT.json","view_paper":"https://pith.science/paper/VSOPB4B2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16752&json=true","fetch_graph":"https://pith.science/api/pith-number/VSOPB4B2U4CBIEZSYYHXJ4NIRT/graph.json","fetch_events":"https://pith.science/api/pith-number/VSOPB4B2U4CBIEZSYYHXJ4NIRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT/action/storage_attestation","attest_author":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT/action/author_attestation","sign_citation":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT/action/citation_signature","submit_replication":"https://pith.science/pith/VSOPB4B2U4CBIEZSYYHXJ4NIRT/action/replication_record"}},"created_at":"2026-07-05T09:42:33.548512+00:00","updated_at":"2026-07-05T09:42:33.548512+00:00"}