{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XBJL52BCQELNFKBEEMESE63KAD","short_pith_number":"pith:XBJL52BC","schema_version":"1.0","canonical_sha256":"b852bee8228116d2a8242309227b6a00e3cef154240d28acac78e530293aade5","source":{"kind":"arxiv","id":"2404.18873","version":1},"attestation_state":"computed","paper":{"title":"OpenStreetView-5M: The Many Roads to Global Visual Geolocation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Charles Raude, Constantin Aronssohn, Elliot Vincent, Guillaume Astruc, Hongyu Zhou, Ioannis Siglidis, Lintao XU, Loic Landrieu, Nacim Bouia, Nicolas Dufour, Romain Loiseau, Stephanie Fu, Van Nguyen Nguyen","submitted_at":"2024-04-29T17:06:44Z","abstract_excerpt":"Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms. Yet, the absence of standard, large-scale, open-access datasets with reliably localizable images has limited its potential. To address this issue, we introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images, covering 225 countries and territories. In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of le"},"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":"2404.18873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-29T17:06:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4672b89d5691737a75204558421813bec692834559ec4116c747f91744fd385","abstract_canon_sha256":"222ec4b71375442709f2ca4f5c28ac1de10e8b4d79f57b4e80e2f4a433a9082e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:21.909100Z","signature_b64":"SMkrYvq9lunzrn0QPUPDmGL45jwxHIcvznKirr6RCvVZqegYikRkYmXjHY8dKmL+2bmdFpfd0dm8c+ehC+sJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b852bee8228116d2a8242309227b6a00e3cef154240d28acac78e530293aade5","last_reissued_at":"2026-07-05T08:13:21.908613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:21.908613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenStreetView-5M: The Many Roads to Global Visual Geolocation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Charles Raude, Constantin Aronssohn, Elliot Vincent, Guillaume Astruc, Hongyu Zhou, Ioannis Siglidis, Lintao XU, Loic Landrieu, Nacim Bouia, Nicolas Dufour, Romain Loiseau, Stephanie Fu, Van Nguyen Nguyen","submitted_at":"2024-04-29T17:06:44Z","abstract_excerpt":"Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms. Yet, the absence of standard, large-scale, open-access datasets with reliably localizable images has limited its potential. To address this issue, we introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images, covering 225 countries and territories. In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18873","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/2404.18873/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":"2404.18873","created_at":"2026-07-05T08:13:21.908671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18873v1","created_at":"2026-07-05T08:13:21.908671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18873","created_at":"2026-07-05T08:13:21.908671+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBJL52BCQELN","created_at":"2026-07-05T08:13:21.908671+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBJL52BCQELNFKBE","created_at":"2026-07-05T08:13:21.908671+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBJL52BC","created_at":"2026-07-05T08:13:21.908671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01341","citing_title":"Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD","json":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD.json","graph_json":"https://pith.science/api/pith-number/XBJL52BCQELNFKBEEMESE63KAD/graph.json","events_json":"https://pith.science/api/pith-number/XBJL52BCQELNFKBEEMESE63KAD/events.json","paper":"https://pith.science/paper/XBJL52BC"},"agent_actions":{"view_html":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD","download_json":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD.json","view_paper":"https://pith.science/paper/XBJL52BC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18873&json=true","fetch_graph":"https://pith.science/api/pith-number/XBJL52BCQELNFKBEEMESE63KAD/graph.json","fetch_events":"https://pith.science/api/pith-number/XBJL52BCQELNFKBEEMESE63KAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD/action/storage_attestation","attest_author":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD/action/author_attestation","sign_citation":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD/action/citation_signature","submit_replication":"https://pith.science/pith/XBJL52BCQELNFKBEEMESE63KAD/action/replication_record"}},"created_at":"2026-07-05T08:13:21.908671+00:00","updated_at":"2026-07-05T08:13:21.908671+00:00"}