{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FZNEJFF6ILS5SYCNQ5XCGUTCEW","short_pith_number":"pith:FZNEJFF6","schema_version":"1.0","canonical_sha256":"2e5a4494be42e5d9604d876e23526225bfdcf42361f48f48cc524c985e651e6d","source":{"kind":"arxiv","id":"2506.06602","version":1},"attestation_state":"computed","paper":{"title":"Zero Shot Composed Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gautama Shastry Bulusu Venkata, Santhosh Kakarla","submitted_at":"2025-06-07T00:38:43Z","abstract_excerpt":"Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text with separate pretrained vision-language encoders, reaches only 20-25\\% Recall@10 on the FashionIQ benchmark. We improve this by fine-tuning BLIP-2 with a lightweight Q-Former that fuses visual and textual features into a single embedding, raising Recall@10 to 45.6\\% (shirt), 40.1\\% (dress), and 50.4\\% (top-tee) and increasing the average Recall@50 to 67.6\\%. 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":"2506.06602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-07T00:38:43Z","cross_cats_sorted":[],"title_canon_sha256":"a8f860befdb9853d599d3654548a9758af571a202dd783cc9cb2eac9284a740b","abstract_canon_sha256":"90b562056c30684dbfb00631fc1fc0948c13e9d839a0d2388c8eca75391acd53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:52.683599Z","signature_b64":"qiDjVDs1YYf4P/nfpAycRqmJRqsZdmzaILLHYeBfeMaJZVfQ6Xl3NlOf2OBOJrhkI2NtBrV1gQhrPJChcCyoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e5a4494be42e5d9604d876e23526225bfdcf42361f48f48cc524c985e651e6d","last_reissued_at":"2026-07-05T11:17:52.683124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:52.683124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero Shot Composed Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gautama Shastry Bulusu Venkata, Santhosh Kakarla","submitted_at":"2025-06-07T00:38:43Z","abstract_excerpt":"Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text with separate pretrained vision-language encoders, reaches only 20-25\\% Recall@10 on the FashionIQ benchmark. We improve this by fine-tuning BLIP-2 with a lightweight Q-Former that fuses visual and textual features into a single embedding, raising Recall@10 to 45.6\\% (shirt), 40.1\\% (dress), and 50.4\\% (top-tee) and increasing the average Recall@50 to 67.6\\%. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06602","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/2506.06602/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":"2506.06602","created_at":"2026-07-05T11:17:52.683181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06602v1","created_at":"2026-07-05T11:17:52.683181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06602","created_at":"2026-07-05T11:17:52.683181+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZNEJFF6ILS5","created_at":"2026-07-05T11:17:52.683181+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZNEJFF6ILS5SYCN","created_at":"2026-07-05T11:17:52.683181+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZNEJFF6","created_at":"2026-07-05T11:17:52.683181+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/FZNEJFF6ILS5SYCNQ5XCGUTCEW","json":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW.json","graph_json":"https://pith.science/api/pith-number/FZNEJFF6ILS5SYCNQ5XCGUTCEW/graph.json","events_json":"https://pith.science/api/pith-number/FZNEJFF6ILS5SYCNQ5XCGUTCEW/events.json","paper":"https://pith.science/paper/FZNEJFF6"},"agent_actions":{"view_html":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW","download_json":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW.json","view_paper":"https://pith.science/paper/FZNEJFF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06602&json=true","fetch_graph":"https://pith.science/api/pith-number/FZNEJFF6ILS5SYCNQ5XCGUTCEW/graph.json","fetch_events":"https://pith.science/api/pith-number/FZNEJFF6ILS5SYCNQ5XCGUTCEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW/action/storage_attestation","attest_author":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW/action/author_attestation","sign_citation":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW/action/citation_signature","submit_replication":"https://pith.science/pith/FZNEJFF6ILS5SYCNQ5XCGUTCEW/action/replication_record"}},"created_at":"2026-07-05T11:17:52.683181+00:00","updated_at":"2026-07-05T11:17:52.683181+00:00"}