{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NY24W544TPCVY6YYZG7XPORI5D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"388c5092ceca5ff7ba18cf0038a42945e9d303f09ead4986a20aeaf244ea9d8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T18:24:38Z","title_canon_sha256":"5aed59971dd259ff97988567f411bc1a7303ead66ed5e872741655f9299659be"},"schema_version":"1.0","source":{"id":"2509.00177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00177","created_at":"2026-07-05T12:02:10Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00177v1","created_at":"2026-07-05T12:02:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00177","created_at":"2026-07-05T12:02:10Z"},{"alias_kind":"pith_short_12","alias_value":"NY24W544TPCV","created_at":"2026-07-05T12:02:10Z"},{"alias_kind":"pith_short_16","alias_value":"NY24W544TPCVY6YY","created_at":"2026-07-05T12:02:10Z"},{"alias_kind":"pith_short_8","alias_value":"NY24W544","created_at":"2026-07-05T12:02:10Z"}],"graph_snapshots":[{"event_id":"sha256:c4e902ecfaa62446d28c2920b5bae1620a7b5df132d76f916f6c53019e6509f4","target":"graph","created_at":"2026-07-05T12:02:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.00177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Faizan Farooq Khan, Giorgos Tolias, Mohamed Elhoseiny, Vladan Stojni\\'c, Zakaria Laskar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T18:24:38Z","title":"Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00177","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e0e162b8d79f4fdb04df4f255a25257099781ac34afa2b19a488f87e8639be9a","target":"record","created_at":"2026-07-05T12:02:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"388c5092ceca5ff7ba18cf0038a42945e9d303f09ead4986a20aeaf244ea9d8d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T18:24:38Z","title_canon_sha256":"5aed59971dd259ff97988567f411bc1a7303ead66ed5e872741655f9299659be"},"schema_version":"1.0","source":{"id":"2509.00177","kind":"arxiv","version":1}},"canonical_sha256":"6e35cb779c9bc55c7b18c9bf77ba28e8dfa2a13913b007e4ff08cdc532c99f2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e35cb779c9bc55c7b18c9bf77ba28e8dfa2a13913b007e4ff08cdc532c99f2e","first_computed_at":"2026-07-05T12:02:10.782085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:10.782085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nj4oxVmFkfshQ/bmMNlbeXAAN4M1Ie6kuswMPS48J3OmOJ50hfJ8arvqyIeLRXjUqyJw6+NVtgzo6vRkXcnLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:10.782576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0e162b8d79f4fdb04df4f255a25257099781ac34afa2b19a488f87e8639be9a","sha256:c4e902ecfaa62446d28c2920b5bae1620a7b5df132d76f916f6c53019e6509f4"],"state_sha256":"2db12802a53ba76fe8295cac3a32836f58b4384c5fbe7a5f7d3293a62ff48fd6"}