{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HI2M62Y24QUWABLIO7CLX4YBY7","short_pith_number":"pith:HI2M62Y2","schema_version":"1.0","canonical_sha256":"3a34cf6b1ae42960056877c4bbf301c7ff998c089eb3564b360ce5c1a05f3aa0","source":{"kind":"arxiv","id":"2403.02041","version":2},"attestation_state":"computed","paper":{"title":"A Generative Approach for Wikipedia-Scale Visual Entity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Alireza Fathi, Cordelia Schmid, Mathilde Caron","submitted_at":"2024-03-04T13:47:30Z","abstract_excerpt":"In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. One way of approaching a problem of such scale is using dual-encoder models (eg CLIP), where all the entity names and query images are embedded into a unified space, paving the way for an approximate k-NN search. Alternatively, it is also possible to re-purpose a captioning model to directly generate the entity names for a given image. In contrast, we introduce a novel Generative Entity Recognition (GER) framework, which giv"},"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":"2403.02041","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T13:47:30Z","cross_cats_sorted":[],"title_canon_sha256":"3f9b7c1df8b89443c939c00e2a228ca74816b91b74795fac48297923da155b6f","abstract_canon_sha256":"6a52df01cc6a6d2574939930abba05aef82ab14cd2c5f1290eac91b25b93b4e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:05.514391Z","signature_b64":"YYO0hv8AHhsKBC/0WQdE8r9yDbJi1Yx1E+22l+UwAU65emMnuygdyPJKBKIH4g1iEivY5+HKvstcNpynMpsCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a34cf6b1ae42960056877c4bbf301c7ff998c089eb3564b360ce5c1a05f3aa0","last_reissued_at":"2026-07-05T07:59:05.513893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:05.513893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generative Approach for Wikipedia-Scale Visual Entity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Alireza Fathi, Cordelia Schmid, Mathilde Caron","submitted_at":"2024-03-04T13:47:30Z","abstract_excerpt":"In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. One way of approaching a problem of such scale is using dual-encoder models (eg CLIP), where all the entity names and query images are embedded into a unified space, paving the way for an approximate k-NN search. Alternatively, it is also possible to re-purpose a captioning model to directly generate the entity names for a given image. In contrast, we introduce a novel Generative Entity Recognition (GER) framework, which giv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02041","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/2403.02041/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":"2403.02041","created_at":"2026-07-05T07:59:05.513949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02041v2","created_at":"2026-07-05T07:59:05.513949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02041","created_at":"2026-07-05T07:59:05.513949+00:00"},{"alias_kind":"pith_short_12","alias_value":"HI2M62Y24QUW","created_at":"2026-07-05T07:59:05.513949+00:00"},{"alias_kind":"pith_short_16","alias_value":"HI2M62Y24QUWABLI","created_at":"2026-07-05T07:59:05.513949+00:00"},{"alias_kind":"pith_short_8","alias_value":"HI2M62Y2","created_at":"2026-07-05T07:59:05.513949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13614","citing_title":"Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7","json":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7.json","graph_json":"https://pith.science/api/pith-number/HI2M62Y24QUWABLIO7CLX4YBY7/graph.json","events_json":"https://pith.science/api/pith-number/HI2M62Y24QUWABLIO7CLX4YBY7/events.json","paper":"https://pith.science/paper/HI2M62Y2"},"agent_actions":{"view_html":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7","download_json":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7.json","view_paper":"https://pith.science/paper/HI2M62Y2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02041&json=true","fetch_graph":"https://pith.science/api/pith-number/HI2M62Y24QUWABLIO7CLX4YBY7/graph.json","fetch_events":"https://pith.science/api/pith-number/HI2M62Y24QUWABLIO7CLX4YBY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7/action/storage_attestation","attest_author":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7/action/author_attestation","sign_citation":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7/action/citation_signature","submit_replication":"https://pith.science/pith/HI2M62Y24QUWABLIO7CLX4YBY7/action/replication_record"}},"created_at":"2026-07-05T07:59:05.513949+00:00","updated_at":"2026-07-05T07:59:05.513949+00:00"}