{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NY24W544TPCVY6YYZG7XPORI5D","short_pith_number":"pith:NY24W544","schema_version":"1.0","canonical_sha256":"6e35cb779c9bc55c7b18c9bf77ba28e8dfa2a13913b007e4ff08cdc532c99f2e","source":{"kind":"arxiv","id":"2509.00177","version":1},"attestation_state":"computed","paper":{"title":"Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Faizan Farooq Khan, Giorgos Tolias, Mohamed Elhoseiny, Vladan Stojni\\'c, Zakaria Laskar","submitted_at":"2025-08-29T18:24:38Z","abstract_excerpt":"This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant regions in the representation space, limiting retrieval performance. To bridge this modality gap, we propose a two-step approach. First, we transform the text query into a visual query using a generative diffusion model. Then, we estimate image-to-image similarity with a vision model. Additionally, we introduce an aggregation network that combines multiple gene"},"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":"2509.00177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T18:24:38Z","cross_cats_sorted":[],"title_canon_sha256":"5aed59971dd259ff97988567f411bc1a7303ead66ed5e872741655f9299659be","abstract_canon_sha256":"388c5092ceca5ff7ba18cf0038a42945e9d303f09ead4986a20aeaf244ea9d8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:10.782576Z","signature_b64":"nj4oxVmFkfshQ/bmMNlbeXAAN4M1Ie6kuswMPS48J3OmOJ50hfJ8arvqyIeLRXjUqyJw6+NVtgzo6vRkXcnLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e35cb779c9bc55c7b18c9bf77ba28e8dfa2a13913b007e4ff08cdc532c99f2e","last_reissued_at":"2026-07-05T12:02:10.782085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:10.782085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Faizan Farooq Khan, Giorgos Tolias, Mohamed Elhoseiny, Vladan Stojni\\'c, Zakaria Laskar","submitted_at":"2025-08-29T18:24:38Z","abstract_excerpt":"This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant regions in the representation space, limiting retrieval performance. To bridge this modality gap, we propose a two-step approach. First, we transform the text query into a visual query using a generative diffusion model. Then, we estimate image-to-image similarity with a vision model. Additionally, we introduce an aggregation network that combines multiple gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00177","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/2509.00177/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":"2509.00177","created_at":"2026-07-05T12:02:10.782142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00177v1","created_at":"2026-07-05T12:02:10.782142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00177","created_at":"2026-07-05T12:02:10.782142+00:00"},{"alias_kind":"pith_short_12","alias_value":"NY24W544TPCV","created_at":"2026-07-05T12:02:10.782142+00:00"},{"alias_kind":"pith_short_16","alias_value":"NY24W544TPCVY6YY","created_at":"2026-07-05T12:02:10.782142+00:00"},{"alias_kind":"pith_short_8","alias_value":"NY24W544","created_at":"2026-07-05T12:02:10.782142+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/NY24W544TPCVY6YYZG7XPORI5D","json":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D.json","graph_json":"https://pith.science/api/pith-number/NY24W544TPCVY6YYZG7XPORI5D/graph.json","events_json":"https://pith.science/api/pith-number/NY24W544TPCVY6YYZG7XPORI5D/events.json","paper":"https://pith.science/paper/NY24W544"},"agent_actions":{"view_html":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D","download_json":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D.json","view_paper":"https://pith.science/paper/NY24W544","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00177&json=true","fetch_graph":"https://pith.science/api/pith-number/NY24W544TPCVY6YYZG7XPORI5D/graph.json","fetch_events":"https://pith.science/api/pith-number/NY24W544TPCVY6YYZG7XPORI5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D/action/storage_attestation","attest_author":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D/action/author_attestation","sign_citation":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D/action/citation_signature","submit_replication":"https://pith.science/pith/NY24W544TPCVY6YYZG7XPORI5D/action/replication_record"}},"created_at":"2026-07-05T12:02:10.782142+00:00","updated_at":"2026-07-05T12:02:10.782142+00:00"}