{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TPAMRTPAX3TR2GPNP4IQPFF2TL","short_pith_number":"pith:TPAMRTPA","schema_version":"1.0","canonical_sha256":"9bc0c8cde0bee71d19ed7f110794ba9ad85668a593e5eecde7273aed175e7924","source":{"kind":"arxiv","id":"2311.17136","version":1},"attestation_state":"computed","paper":{"title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Alan Ritter, Cong Wei, Ge Zhang, Haonan Chen, Hexiang Hu, Jie Fu, Wenhu Chen, Yang Chen","submitted_at":"2023-11-28T18:55:52Z","abstract_excerpt":"Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or finding a similar photo with a query image. To approach such different information-seeking demands, we introduce UniIR, a unified instruction-guided multimodal retriever capable of handling eight distinct retrieval tasks across modalities. UniIR, a single retrieval system jointly trained on ten diverse multimodal-IR datasets, interprets user instructions to ex"},"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":"2311.17136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"61ccc20f6ec63e61751602cef972aedb4b83a3543d3d90d82c71fb36c0aaf3d5","abstract_canon_sha256":"e22cdfee719aed4b2fe96f05e35f47f95f3b7d95f4a21fb4973b435b4873802b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:58.008814Z","signature_b64":"wSsAWMF9EOSuIZBnXypJy5vHOZxY4nq5ZrZPTlAMD1YOxHyn0G0jehv57/AbiD5TIjinAZLAM5j/KrEoUp2mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bc0c8cde0bee71d19ed7f110794ba9ad85668a593e5eecde7273aed175e7924","last_reissued_at":"2026-07-05T07:17:58.008299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:58.008299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Alan Ritter, Cong Wei, Ge Zhang, Haonan Chen, Hexiang Hu, Jie Fu, Wenhu Chen, Yang Chen","submitted_at":"2023-11-28T18:55:52Z","abstract_excerpt":"Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or finding a similar photo with a query image. To approach such different information-seeking demands, we introduce UniIR, a unified instruction-guided multimodal retriever capable of handling eight distinct retrieval tasks across modalities. UniIR, a single retrieval system jointly trained on ten diverse multimodal-IR datasets, interprets user instructions to ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17136","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/2311.17136/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":"2311.17136","created_at":"2026-07-05T07:17:58.008370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17136v1","created_at":"2026-07-05T07:17:58.008370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17136","created_at":"2026-07-05T07:17:58.008370+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPAMRTPAX3TR","created_at":"2026-07-05T07:17:58.008370+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPAMRTPAX3TR2GPN","created_at":"2026-07-05T07:17:58.008370+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPAMRTPA","created_at":"2026-07-05T07:17:58.008370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24938","citing_title":"Your Embedding Model is SMARTer Than You Think","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05160","citing_title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2407.12580","citing_title":"E5-V: Universal Embeddings with Multimodal Large Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2410.10594","citing_title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00104","citing_title":"R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23321","citing_title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL","json":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL.json","graph_json":"https://pith.science/api/pith-number/TPAMRTPAX3TR2GPNP4IQPFF2TL/graph.json","events_json":"https://pith.science/api/pith-number/TPAMRTPAX3TR2GPNP4IQPFF2TL/events.json","paper":"https://pith.science/paper/TPAMRTPA"},"agent_actions":{"view_html":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL","download_json":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL.json","view_paper":"https://pith.science/paper/TPAMRTPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17136&json=true","fetch_graph":"https://pith.science/api/pith-number/TPAMRTPAX3TR2GPNP4IQPFF2TL/graph.json","fetch_events":"https://pith.science/api/pith-number/TPAMRTPAX3TR2GPNP4IQPFF2TL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL/action/storage_attestation","attest_author":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL/action/author_attestation","sign_citation":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL/action/citation_signature","submit_replication":"https://pith.science/pith/TPAMRTPAX3TR2GPNP4IQPFF2TL/action/replication_record"}},"created_at":"2026-07-05T07:17:58.008370+00:00","updated_at":"2026-07-05T07:17:58.008370+00:00"}