{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G3PS23H4UF4VO6D7VTXOPWFRIT","short_pith_number":"pith:G3PS23H4","schema_version":"1.0","canonical_sha256":"36df2d6cfca17957787faceee7d8b144fe2c1bd9bc426140324d594bcaa2701d","source":{"kind":"arxiv","id":"2506.02291","version":1},"attestation_state":"computed","paper":{"title":"Entity Image and Mixed-Modal Image Retrieval Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Cristian-Ioan Blaga, Enrique Alfonseca, Imed Zitouni, Krishna Srinivasan, Paul Suganthan, Peter Dornbach, Sahil Dua, Tom Duerig, Zhe Dong","submitted_at":"2025-06-02T22:04:06Z","abstract_excerpt":"Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a novel benchmark to rigorously evaluate image retrieval that demands deep cross-modal contextual understanding. We present two new datasets: the Entity Image Dataset (EI), providing canonical images for Wikipedia entities, and the Mixed-Modal Image Retrieval Dataset (MMIR), derived from the WIT dataset. The MMIR benchmark features two challenging query types requiring models to ground textual descriptions in the context"},"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":"2506.02291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T22:04:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7565746f039aecb19e016aece69c956969d6ff4fea894e4ab1a42b231e71de38","abstract_canon_sha256":"554de499c8ad798c2005c9808536a249e4ffefc262efaacb5c5ab523671600aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:35.829410Z","signature_b64":"rpwI3nXl7vc8WIbc+eP+Jf+wZ2vF3v5BObkCMMtBLNM8uA7E2BT1kDMXu4CB5exweBvbwSeHB7n7Yrqm8aufDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36df2d6cfca17957787faceee7d8b144fe2c1bd9bc426140324d594bcaa2701d","last_reissued_at":"2026-07-05T11:14:35.828924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:35.828924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity Image and Mixed-Modal Image Retrieval Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Cristian-Ioan Blaga, Enrique Alfonseca, Imed Zitouni, Krishna Srinivasan, Paul Suganthan, Peter Dornbach, Sahil Dua, Tom Duerig, Zhe Dong","submitted_at":"2025-06-02T22:04:06Z","abstract_excerpt":"Despite advances in multimodal learning, challenging benchmarks for mixed-modal image retrieval that combines visual and textual information are lacking. This paper introduces a novel benchmark to rigorously evaluate image retrieval that demands deep cross-modal contextual understanding. We present two new datasets: the Entity Image Dataset (EI), providing canonical images for Wikipedia entities, and the Mixed-Modal Image Retrieval Dataset (MMIR), derived from the WIT dataset. The MMIR benchmark features two challenging query types requiring models to ground textual descriptions in the context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02291","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/2506.02291/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":"2506.02291","created_at":"2026-07-05T11:14:35.828984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02291v1","created_at":"2026-07-05T11:14:35.828984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02291","created_at":"2026-07-05T11:14:35.828984+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3PS23H4UF4V","created_at":"2026-07-05T11:14:35.828984+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3PS23H4UF4VO6D7","created_at":"2026-07-05T11:14:35.828984+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3PS23H4","created_at":"2026-07-05T11:14:35.828984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT","json":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT.json","graph_json":"https://pith.science/api/pith-number/G3PS23H4UF4VO6D7VTXOPWFRIT/graph.json","events_json":"https://pith.science/api/pith-number/G3PS23H4UF4VO6D7VTXOPWFRIT/events.json","paper":"https://pith.science/paper/G3PS23H4"},"agent_actions":{"view_html":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT","download_json":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT.json","view_paper":"https://pith.science/paper/G3PS23H4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02291&json=true","fetch_graph":"https://pith.science/api/pith-number/G3PS23H4UF4VO6D7VTXOPWFRIT/graph.json","fetch_events":"https://pith.science/api/pith-number/G3PS23H4UF4VO6D7VTXOPWFRIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT/action/storage_attestation","attest_author":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT/action/author_attestation","sign_citation":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT/action/citation_signature","submit_replication":"https://pith.science/pith/G3PS23H4UF4VO6D7VTXOPWFRIT/action/replication_record"}},"created_at":"2026-07-05T11:14:35.828984+00:00","updated_at":"2026-07-05T11:14:35.828984+00:00"}