{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NCFUDZZKL3X3TZVLMQ5FEHZF6J","short_pith_number":"pith:NCFUDZZK","schema_version":"1.0","canonical_sha256":"688b41e72a5eefb9e6ab643a521f25f24dfb2ecb1df1b473b693534816005513","source":{"kind":"arxiv","id":"2302.11154","version":2},"attestation_state":"computed","paper":{"title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hexiang Hu, Kenton Lee, Kristina Toutanova, Mandar Joshi, Ming-Wei Chang, Urvashi Khandelwal, Yang Chen, Yi Luan","submitted_at":"2023-02-22T05:31:26Z","abstract_excerpt":"Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong generalization on various visual domains and tasks. However, existing image classification benchmarks often evaluate recognition on a specific domain (e.g., outdoor images) or a specific task (e.g., classifying plant species), which falls short of evaluating whether pre-trained foundational models are universal visual recognizers. To address this, we formally present the task of Open-domain Visual Entity recognitioN (OVEN), where a model need to link an image onto a Wikipedia entity with respect to a text query. W"},"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":"2302.11154","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-22T05:31:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"773b835e47a1f0f569fd728af25d1805263ce53365573821024e8eaf385b5c1f","abstract_canon_sha256":"316c78520610dae9f8ee9a132e820b864e5d60fce4d335875e51f21b8a855c84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:07.221735Z","signature_b64":"mMbHNVmjAFFmt/ZQlE3NKSZltCtmiw1rdjnLoha9d7E8Q3dmQUdXLpy33q+i6WS++cOslrc1IgljPiy8puHnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"688b41e72a5eefb9e6ab643a521f25f24dfb2ecb1df1b473b693534816005513","last_reissued_at":"2026-07-05T05:45:07.221262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:07.221262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hexiang Hu, Kenton Lee, Kristina Toutanova, Mandar Joshi, Ming-Wei Chang, Urvashi Khandelwal, Yang Chen, Yi Luan","submitted_at":"2023-02-22T05:31:26Z","abstract_excerpt":"Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong generalization on various visual domains and tasks. However, existing image classification benchmarks often evaluate recognition on a specific domain (e.g., outdoor images) or a specific task (e.g., classifying plant species), which falls short of evaluating whether pre-trained foundational models are universal visual recognizers. To address this, we formally present the task of Open-domain Visual Entity recognitioN (OVEN), where a model need to link an image onto a Wikipedia entity with respect to a text query. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11154","kind":"arxiv","version":2},"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/2302.11154/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":"2302.11154","created_at":"2026-07-05T05:45:07.221322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11154v2","created_at":"2026-07-05T05:45:07.221322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11154","created_at":"2026-07-05T05:45:07.221322+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCFUDZZKL3X3","created_at":"2026-07-05T05:45:07.221322+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCFUDZZKL3X3TZVL","created_at":"2026-07-05T05:45:07.221322+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCFUDZZK","created_at":"2026-07-05T05:45:07.221322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04240","citing_title":"Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2305.18565","citing_title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J","json":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J.json","graph_json":"https://pith.science/api/pith-number/NCFUDZZKL3X3TZVLMQ5FEHZF6J/graph.json","events_json":"https://pith.science/api/pith-number/NCFUDZZKL3X3TZVLMQ5FEHZF6J/events.json","paper":"https://pith.science/paper/NCFUDZZK"},"agent_actions":{"view_html":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J","download_json":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J.json","view_paper":"https://pith.science/paper/NCFUDZZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11154&json=true","fetch_graph":"https://pith.science/api/pith-number/NCFUDZZKL3X3TZVLMQ5FEHZF6J/graph.json","fetch_events":"https://pith.science/api/pith-number/NCFUDZZKL3X3TZVLMQ5FEHZF6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J/action/storage_attestation","attest_author":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J/action/author_attestation","sign_citation":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J/action/citation_signature","submit_replication":"https://pith.science/pith/NCFUDZZKL3X3TZVLMQ5FEHZF6J/action/replication_record"}},"created_at":"2026-07-05T05:45:07.221322+00:00","updated_at":"2026-07-05T05:45:07.221322+00:00"}