{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JLWCMKM5BRGQELCVKKT5DXGPVD","short_pith_number":"pith:JLWCMKM5","schema_version":"1.0","canonical_sha256":"4aec26299d0c4d022c5552a7d1dccfa8ec95d5ad4b3ced28e7300077e33d5e62","source":{"kind":"arxiv","id":"2306.00424","version":1},"attestation_state":"computed","paper":{"title":"End-to-end Knowledge Retrieval with Multi-modal Queries","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Man Luo, Tejas Gokhale, Yezhou Yang, Zhiyuan Fang","submitted_at":"2023-06-01T08:04:12Z","abstract_excerpt":"We investigate knowledge retrieval with multi-modal queries, i.e. queries containing information split across image and text inputs, a challenging task that differs from previous work on cross-modal retrieval. We curate a new dataset called ReMuQ for benchmarking progress on this task. ReMuQ requires a system to retrieve knowledge from a large corpus by integrating contents from both text and image queries. We introduce a retriever model ``ReViz'' that can directly process input text and images to retrieve relevant knowledge in an end-to-end fashion without being dependent on intermediate modu"},"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":"2306.00424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-01T08:04:12Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"05bdb9fd5aacc2887fce93dfa53634801af15f934ef4da2536fe435c60c6ef62","abstract_canon_sha256":"9d5b3257c11c9c0f279dca6cd21472f858e9bbd8d6a1a76ec7b70bdb11fe040f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:26.240492Z","signature_b64":"L4u58suRQ6TYAnsi7/N98HxpsvwltHNIVjmjxN1wozk2W0oVre5qF+fkxKjpMdpO/0G7lxfDBbxr22f03sEkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aec26299d0c4d022c5552a7d1dccfa8ec95d5ad4b3ced28e7300077e33d5e62","last_reissued_at":"2026-07-05T06:16:26.239998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:26.239998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Knowledge Retrieval with Multi-modal Queries","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Man Luo, Tejas Gokhale, Yezhou Yang, Zhiyuan Fang","submitted_at":"2023-06-01T08:04:12Z","abstract_excerpt":"We investigate knowledge retrieval with multi-modal queries, i.e. queries containing information split across image and text inputs, a challenging task that differs from previous work on cross-modal retrieval. We curate a new dataset called ReMuQ for benchmarking progress on this task. ReMuQ requires a system to retrieve knowledge from a large corpus by integrating contents from both text and image queries. We introduce a retriever model ``ReViz'' that can directly process input text and images to retrieve relevant knowledge in an end-to-end fashion without being dependent on intermediate modu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00424","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/2306.00424/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":"2306.00424","created_at":"2026-07-05T06:16:26.240058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00424v1","created_at":"2026-07-05T06:16:26.240058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00424","created_at":"2026-07-05T06:16:26.240058+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLWCMKM5BRGQ","created_at":"2026-07-05T06:16:26.240058+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLWCMKM5BRGQELCV","created_at":"2026-07-05T06:16:26.240058+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLWCMKM5","created_at":"2026-07-05T06:16:26.240058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07907","citing_title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2509.00798","citing_title":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD","json":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD.json","graph_json":"https://pith.science/api/pith-number/JLWCMKM5BRGQELCVKKT5DXGPVD/graph.json","events_json":"https://pith.science/api/pith-number/JLWCMKM5BRGQELCVKKT5DXGPVD/events.json","paper":"https://pith.science/paper/JLWCMKM5"},"agent_actions":{"view_html":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD","download_json":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD.json","view_paper":"https://pith.science/paper/JLWCMKM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00424&json=true","fetch_graph":"https://pith.science/api/pith-number/JLWCMKM5BRGQELCVKKT5DXGPVD/graph.json","fetch_events":"https://pith.science/api/pith-number/JLWCMKM5BRGQELCVKKT5DXGPVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD/action/storage_attestation","attest_author":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD/action/author_attestation","sign_citation":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD/action/citation_signature","submit_replication":"https://pith.science/pith/JLWCMKM5BRGQELCVKKT5DXGPVD/action/replication_record"}},"created_at":"2026-07-05T06:16:26.240058+00:00","updated_at":"2026-07-05T06:16:26.240058+00:00"}