{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3UACZRFFVWGCL3ZMIWQBYQK2EU","short_pith_number":"pith:3UACZRFF","schema_version":"1.0","canonical_sha256":"dd002cc4a5ad8c25ef2c45a01c415a250d52f93f7c4640e655b483e58899cbbc","source":{"kind":"arxiv","id":"2409.04918","version":4},"attestation_state":"computed","paper":{"title":"Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huei-Fang Yang, Ren-Di Wu, Yu-Yen Lin","submitted_at":"2024-09-07T21:52:58Z","abstract_excerpt":"Composed image retrieval (CIR), which formulates the query as a combination of a reference image and modified text, has emerged as a new form of image search due to its enhanced ability to capture user intent. However, training a CIR model in a supervised manner typically requires labor-intensive collection of (reference image, text modifier, target image) triplets. While existing zero-shot CIR (ZS-CIR) methods eliminate the need for training on specific downstream datasets, they still require additional pretraining on large-scale image datasets. In this paper, we introduce a training-free app"},"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":"2409.04918","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T21:52:58Z","cross_cats_sorted":[],"title_canon_sha256":"3872a6b04e525f02116192314953863b87be4fd79c9a172e590081f05beca2da","abstract_canon_sha256":"182ecc5c3ac6280bb25f552b4daee6de8da45c1c97d808dd93783435302a55d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:11.638842Z","signature_b64":"HS3um1VFMixpb9+AM4R6UMh4A3gCsUCdq2gzGlnugLyhFcQE9zVaNtZ2KkJ78cZKCs3jVf+Khkoud9OY7/cUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd002cc4a5ad8c25ef2c45a01c415a250d52f93f7c4640e655b483e58899cbbc","last_reissued_at":"2026-07-05T10:53:11.638392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:11.638392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huei-Fang Yang, Ren-Di Wu, Yu-Yen Lin","submitted_at":"2024-09-07T21:52:58Z","abstract_excerpt":"Composed image retrieval (CIR), which formulates the query as a combination of a reference image and modified text, has emerged as a new form of image search due to its enhanced ability to capture user intent. However, training a CIR model in a supervised manner typically requires labor-intensive collection of (reference image, text modifier, target image) triplets. While existing zero-shot CIR (ZS-CIR) methods eliminate the need for training on specific downstream datasets, they still require additional pretraining on large-scale image datasets. In this paper, we introduce a training-free app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04918","kind":"arxiv","version":4},"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/2409.04918/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":"2409.04918","created_at":"2026-07-05T10:53:11.638448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04918v4","created_at":"2026-07-05T10:53:11.638448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04918","created_at":"2026-07-05T10:53:11.638448+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UACZRFFVWGC","created_at":"2026-07-05T10:53:11.638448+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UACZRFFVWGCL3ZM","created_at":"2026-07-05T10:53:11.638448+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UACZRFF","created_at":"2026-07-05T10:53:11.638448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12294","citing_title":"Bridging the Modality Gap in Forensic Image Retrieval","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU","json":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU.json","graph_json":"https://pith.science/api/pith-number/3UACZRFFVWGCL3ZMIWQBYQK2EU/graph.json","events_json":"https://pith.science/api/pith-number/3UACZRFFVWGCL3ZMIWQBYQK2EU/events.json","paper":"https://pith.science/paper/3UACZRFF"},"agent_actions":{"view_html":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU","download_json":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU.json","view_paper":"https://pith.science/paper/3UACZRFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04918&json=true","fetch_graph":"https://pith.science/api/pith-number/3UACZRFFVWGCL3ZMIWQBYQK2EU/graph.json","fetch_events":"https://pith.science/api/pith-number/3UACZRFFVWGCL3ZMIWQBYQK2EU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU/action/storage_attestation","attest_author":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU/action/author_attestation","sign_citation":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU/action/citation_signature","submit_replication":"https://pith.science/pith/3UACZRFFVWGCL3ZMIWQBYQK2EU/action/replication_record"}},"created_at":"2026-07-05T10:53:11.638448+00:00","updated_at":"2026-07-05T10:53:11.638448+00:00"}