{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JLWCMKM5BRGQELCVKKT5DXGPVD","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":"9d5b3257c11c9c0f279dca6cd21472f858e9bbd8d6a1a76ec7b70bdb11fe040f","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-01T08:04:12Z","title_canon_sha256":"05bdb9fd5aacc2887fce93dfa53634801af15f934ef4da2536fe435c60c6ef62"},"schema_version":"1.0","source":{"id":"2306.00424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00424","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00424v1","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00424","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_12","alias_value":"JLWCMKM5BRGQ","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_16","alias_value":"JLWCMKM5BRGQELCV","created_at":"2026-07-05T06:16:26Z"},{"alias_kind":"pith_short_8","alias_value":"JLWCMKM5","created_at":"2026-07-05T06:16:26Z"}],"graph_snapshots":[{"event_id":"sha256:c3d61d5b60094addd6542da512dd9c341efb49c0646805216548fa92c7e887a4","target":"graph","created_at":"2026-07-05T06:16:26Z","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/2306.00424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chitta Baral, Man Luo, Tejas Gokhale, Yezhou Yang, Zhiyuan Fang","cross_cats":["cs.CV","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-01T08:04:12Z","title":"End-to-end Knowledge Retrieval with Multi-modal Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00424","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:f488fe3667ade86895307c1946de81e98d9c8f3246301c6fb56ba769b11147c0","target":"record","created_at":"2026-07-05T06:16:26Z","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":"9d5b3257c11c9c0f279dca6cd21472f858e9bbd8d6a1a76ec7b70bdb11fe040f","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-01T08:04:12Z","title_canon_sha256":"05bdb9fd5aacc2887fce93dfa53634801af15f934ef4da2536fe435c60c6ef62"},"schema_version":"1.0","source":{"id":"2306.00424","kind":"arxiv","version":1}},"canonical_sha256":"4aec26299d0c4d022c5552a7d1dccfa8ec95d5ad4b3ced28e7300077e33d5e62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aec26299d0c4d022c5552a7d1dccfa8ec95d5ad4b3ced28e7300077e33d5e62","first_computed_at":"2026-07-05T06:16:26.239998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:26.239998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L4u58suRQ6TYAnsi7/N98HxpsvwltHNIVjmjxN1wozk2W0oVre5qF+fkxKjpMdpO/0G7lxfDBbxr22f03sEkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:26.240492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f488fe3667ade86895307c1946de81e98d9c8f3246301c6fb56ba769b11147c0","sha256:c3d61d5b60094addd6542da512dd9c341efb49c0646805216548fa92c7e887a4"],"state_sha256":"d8b352625956527d035e34b78ce420aab989cb48da48cec7e98a8ceca7b16610"}