{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TPAMRTPAX3TR2GPNP4IQPFF2TL","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":"e22cdfee719aed4b2fe96f05e35f47f95f3b7d95f4a21fb4973b435b4873802b","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:52Z","title_canon_sha256":"61ccc20f6ec63e61751602cef972aedb4b83a3543d3d90d82c71fb36c0aaf3d5"},"schema_version":"1.0","source":{"id":"2311.17136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17136","created_at":"2026-07-05T07:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17136v1","created_at":"2026-07-05T07:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17136","created_at":"2026-07-05T07:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"TPAMRTPAX3TR","created_at":"2026-07-05T07:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"TPAMRTPAX3TR2GPN","created_at":"2026-07-05T07:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"TPAMRTPA","created_at":"2026-07-05T07:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:5ca5669c0ac448c9e3fd219e167455ae49d4801e9f82e988db7f22475847b438","target":"graph","created_at":"2026-07-05T07:17:58Z","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/2311.17136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alan Ritter, Cong Wei, Ge Zhang, Haonan Chen, Hexiang Hu, Jie Fu, Wenhu Chen, Yang Chen","cross_cats":["cs.AI","cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:52Z","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17136","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:e3559097db0d34a07e13b2437caf76718aee785268483a243e21681eb9e5ea74","target":"record","created_at":"2026-07-05T07:17:58Z","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":"e22cdfee719aed4b2fe96f05e35f47f95f3b7d95f4a21fb4973b435b4873802b","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:55:52Z","title_canon_sha256":"61ccc20f6ec63e61751602cef972aedb4b83a3543d3d90d82c71fb36c0aaf3d5"},"schema_version":"1.0","source":{"id":"2311.17136","kind":"arxiv","version":1}},"canonical_sha256":"9bc0c8cde0bee71d19ed7f110794ba9ad85668a593e5eecde7273aed175e7924","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bc0c8cde0bee71d19ed7f110794ba9ad85668a593e5eecde7273aed175e7924","first_computed_at":"2026-07-05T07:17:58.008299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:58.008299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wSsAWMF9EOSuIZBnXypJy5vHOZxY4nq5ZrZPTlAMD1YOxHyn0G0jehv57/AbiD5TIjinAZLAM5j/KrEoUp2mCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:58.008814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3559097db0d34a07e13b2437caf76718aee785268483a243e21681eb9e5ea74","sha256:5ca5669c0ac448c9e3fd219e167455ae49d4801e9f82e988db7f22475847b438"],"state_sha256":"0f4ed1be2e0060c952f38a61626aeffd5b702cdb02f18ec46d239faa41b293af"}