{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FOZAVMSDTJJE5N3FCDZ336V7ES","short_pith_number":"pith:FOZAVMSD","schema_version":"1.0","canonical_sha256":"2bb20ab2439a524eb76510f3bdfabf248d5610487c5724d89a7a4ee8428bec67","source":{"kind":"arxiv","id":"2406.04292","version":1},"attestation_state":"computed","paper":{"title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Bo Zhao, Junjie Zhou, Shitao Xiao, Yongping Xiong, Zheng Liu","submitted_at":"2024-06-06T17:37:47Z","abstract_excerpt":"Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP, the current methods are severely limited in representing the text-only and image-only data. In this work, we present a new embedding model VISTA for universal multi-modal retrieval. Our work brings forth threefold technical contributions. Firstly, we introduce a flexible architecture which extends a powerful text encoder with the image understanding capability"},"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":"2406.04292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-06T17:37:47Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"7e51c0f03079a0d74e58b0d5fdbd7a5e5d58c3f9ad4cc9e60ad61fda3bc29743","abstract_canon_sha256":"7238d12ffc9bf3b93f580ff97cfbcf4506e255c681d04f08e0c4c55e7c0217e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:29.153124Z","signature_b64":"wxx+Yt3Snonj3Mf8ECIhMZtFJOUMCsTPZIC1gW6yzqD9yagEuhZhjPmvS4FfYx2Eg/Gm5bhXXOHc2uuO4pxNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bb20ab2439a524eb76510f3bdfabf248d5610487c5724d89a7a4ee8428bec67","last_reissued_at":"2026-07-05T08:28:29.152689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:29.152689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Bo Zhao, Junjie Zhou, Shitao Xiao, Yongping Xiong, Zheng Liu","submitted_at":"2024-06-06T17:37:47Z","abstract_excerpt":"Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP, the current methods are severely limited in representing the text-only and image-only data. In this work, we present a new embedding model VISTA for universal multi-modal retrieval. Our work brings forth threefold technical contributions. Firstly, we introduce a flexible architecture which extends a powerful text encoder with the image understanding capability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04292","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/2406.04292/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":"2406.04292","created_at":"2026-07-05T08:28:29.152747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04292v1","created_at":"2026-07-05T08:28:29.152747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04292","created_at":"2026-07-05T08:28:29.152747+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOZAVMSDTJJE","created_at":"2026-07-05T08:28:29.152747+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOZAVMSDTJJE5N3F","created_at":"2026-07-05T08:28:29.152747+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOZAVMSD","created_at":"2026-07-05T08:28:29.152747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19584","citing_title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24530","citing_title":"Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2407.12580","citing_title":"E5-V: Universal Embeddings with Multimodal Large Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13511","citing_title":"Adapting MLLMs for Nuanced Video Retrieval","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21262","citing_title":"CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27600","citing_title":"Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES","json":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES.json","graph_json":"https://pith.science/api/pith-number/FOZAVMSDTJJE5N3FCDZ336V7ES/graph.json","events_json":"https://pith.science/api/pith-number/FOZAVMSDTJJE5N3FCDZ336V7ES/events.json","paper":"https://pith.science/paper/FOZAVMSD"},"agent_actions":{"view_html":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES","download_json":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES.json","view_paper":"https://pith.science/paper/FOZAVMSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04292&json=true","fetch_graph":"https://pith.science/api/pith-number/FOZAVMSDTJJE5N3FCDZ336V7ES/graph.json","fetch_events":"https://pith.science/api/pith-number/FOZAVMSDTJJE5N3FCDZ336V7ES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES/action/storage_attestation","attest_author":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES/action/author_attestation","sign_citation":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES/action/citation_signature","submit_replication":"https://pith.science/pith/FOZAVMSDTJJE5N3FCDZ336V7ES/action/replication_record"}},"created_at":"2026-07-05T08:28:29.152747+00:00","updated_at":"2026-07-05T08:28:29.152747+00:00"}