{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MVSVAY6Q2TM72CJG4HPUFASLVJ","short_pith_number":"pith:MVSVAY6Q","schema_version":"1.0","canonical_sha256":"65655063d0d4d9fd0926e1df42824baa7103569da5d1653c05f801ed8e7273e8","source":{"kind":"arxiv","id":"2302.00275","version":1},"attestation_state":"computed","paper":{"title":"Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lukas Haas, Michal Skreta, Silas Alberti","submitted_at":"2023-02-01T06:44:07Z","abstract_excerpt":"Image geolocalization is the challenging task of predicting the geographic coordinates of origin for a given photo. It is an unsolved problem relying on the ability to combine visual clues with general knowledge about the world to make accurate predictions across geographies. We present $\\href{https://huggingface.co/geolocal/StreetCLIP}{\\text{StreetCLIP}}$, a robust, publicly available foundation model not only achieving state-of-the-art performance on multiple open-domain image geolocalization benchmarks but also doing so in a zero-shot setting, outperforming supervised models trained on more"},"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":"2302.00275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-01T06:44:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f6ef8b22c4465a0321464db48972f8dd33e87119b4f031fe14960e4cce5f8e6","abstract_canon_sha256":"50dda0b3fac68f9e49da13f19f7bca41ac2eb4c5b02ad61eb49202bfb22bd865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:01.529979Z","signature_b64":"+3yrham2TvI+a1HYDWIERExD3YvGQ50BsNXCfIMPxCU/SS3coZxl4CHgtNKxcFZCTjXZWkv8t3i3UsfU3lhaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65655063d0d4d9fd0926e1df42824baa7103569da5d1653c05f801ed8e7273e8","last_reissued_at":"2026-07-05T05:38:01.529582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:01.529582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lukas Haas, Michal Skreta, Silas Alberti","submitted_at":"2023-02-01T06:44:07Z","abstract_excerpt":"Image geolocalization is the challenging task of predicting the geographic coordinates of origin for a given photo. It is an unsolved problem relying on the ability to combine visual clues with general knowledge about the world to make accurate predictions across geographies. We present $\\href{https://huggingface.co/geolocal/StreetCLIP}{\\text{StreetCLIP}}$, a robust, publicly available foundation model not only achieving state-of-the-art performance on multiple open-domain image geolocalization benchmarks but also doing so in a zero-shot setting, outperforming supervised models trained on more"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00275","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/2302.00275/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":"2302.00275","created_at":"2026-07-05T05:38:01.529641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00275v1","created_at":"2026-07-05T05:38:01.529641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00275","created_at":"2026-07-05T05:38:01.529641+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVSVAY6Q2TM7","created_at":"2026-07-05T05:38:01.529641+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVSVAY6Q2TM72CJG","created_at":"2026-07-05T05:38:01.529641+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVSVAY6Q","created_at":"2026-07-05T05:38:01.529641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08126","citing_title":"One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17492","citing_title":"MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09025","citing_title":"Skill-Conditioned Visual Geolocation for Vision-Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12159","citing_title":"VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09025","citing_title":"Skill-Conditioned Visual Geolocation for Vision-Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ","json":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ.json","graph_json":"https://pith.science/api/pith-number/MVSVAY6Q2TM72CJG4HPUFASLVJ/graph.json","events_json":"https://pith.science/api/pith-number/MVSVAY6Q2TM72CJG4HPUFASLVJ/events.json","paper":"https://pith.science/paper/MVSVAY6Q"},"agent_actions":{"view_html":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ","download_json":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ.json","view_paper":"https://pith.science/paper/MVSVAY6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00275&json=true","fetch_graph":"https://pith.science/api/pith-number/MVSVAY6Q2TM72CJG4HPUFASLVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MVSVAY6Q2TM72CJG4HPUFASLVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ/action/storage_attestation","attest_author":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ/action/author_attestation","sign_citation":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ/action/citation_signature","submit_replication":"https://pith.science/pith/MVSVAY6Q2TM72CJG4HPUFASLVJ/action/replication_record"}},"created_at":"2026-07-05T05:38:01.529641+00:00","updated_at":"2026-07-05T05:38:01.529641+00:00"}