{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KJPR5X3TGUVGLMNH63GS6V4QGP","short_pith_number":"pith:KJPR5X3T","schema_version":"1.0","canonical_sha256":"525f1edf73352a65b1a7f6cd2f579033c836be7ced703dd50514f1c0d5fd32d7","source":{"kind":"arxiv","id":"2505.13731","version":4},"attestation_state":"computed","paper":{"title":"GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pengyue Jia, Seongheon Park, Sharon Li, Song Gao, Xiangyu Zhao","submitted_at":"2025-05-19T21:04:46Z","abstract_excerpt":"Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the vast diversity in visual content across regions. While recent approaches adopt a two-stage pipeline of retrieving candidates and selecting the best match, they typically rely on simplistic similarity heuristics and point-wise supervision, failing to model spatial relationships among candidates. In this paper, we propose GeoRanker, a distance-aware ranking framework that leverages large vision-language models to jointly encode query-candidate intera"},"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":"2505.13731","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T21:04:46Z","cross_cats_sorted":[],"title_canon_sha256":"1188c71c6224b6bfe3c8bc2aeba532c681f549c8493f4c46cbaa7bc0a802f2a0","abstract_canon_sha256":"61732c3272d2877317b192967151beab3ddbdd40bc3b1ab036f208066b322535"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:44.575609Z","signature_b64":"gZdpNBRjCMRPF3Q9ykFZE7x08KAOgPcAxvl6We/Mp72q8nG8WPn9q3BW5hFp318d5RBBMTCCldkaIQhZPtpCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"525f1edf73352a65b1a7f6cd2f579033c836be7ced703dd50514f1c0d5fd32d7","last_reissued_at":"2026-06-25T01:17:44.575105Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:44.575105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pengyue Jia, Seongheon Park, Sharon Li, Song Gao, Xiangyu Zhao","submitted_at":"2025-05-19T21:04:46Z","abstract_excerpt":"Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the vast diversity in visual content across regions. While recent approaches adopt a two-stage pipeline of retrieving candidates and selecting the best match, they typically rely on simplistic similarity heuristics and point-wise supervision, failing to model spatial relationships among candidates. In this paper, we propose GeoRanker, a distance-aware ranking framework that leverages large vision-language models to jointly encode query-candidate intera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13731","kind":"arxiv","version":4},"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/2505.13731/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":"2505.13731","created_at":"2026-06-25T01:17:44.575162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13731v4","created_at":"2026-06-25T01:17:44.575162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13731","created_at":"2026-06-25T01:17:44.575162+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJPR5X3TGUVG","created_at":"2026-06-25T01:17:44.575162+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJPR5X3TGUVGLMNH","created_at":"2026-06-25T01:17:44.575162+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJPR5X3T","created_at":"2026-06-25T01:17:44.575162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.08303","citing_title":"GeoGNN: Time Series Geo-Localization using Two-Tower Graph Neural Networks","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09025","citing_title":"Skill-Conditioned Visual Geolocation for Vision-Language Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12159","citing_title":"VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09025","citing_title":"Skill-Conditioned Visual Geolocation for Vision-Language Models","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP","json":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP.json","graph_json":"https://pith.science/api/pith-number/KJPR5X3TGUVGLMNH63GS6V4QGP/graph.json","events_json":"https://pith.science/api/pith-number/KJPR5X3TGUVGLMNH63GS6V4QGP/events.json","paper":"https://pith.science/paper/KJPR5X3T"},"agent_actions":{"view_html":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP","download_json":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP.json","view_paper":"https://pith.science/paper/KJPR5X3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13731&json=true","fetch_graph":"https://pith.science/api/pith-number/KJPR5X3TGUVGLMNH63GS6V4QGP/graph.json","fetch_events":"https://pith.science/api/pith-number/KJPR5X3TGUVGLMNH63GS6V4QGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP/action/storage_attestation","attest_author":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP/action/author_attestation","sign_citation":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP/action/citation_signature","submit_replication":"https://pith.science/pith/KJPR5X3TGUVGLMNH63GS6V4QGP/action/replication_record"}},"created_at":"2026-06-25T01:17:44.575162+00:00","updated_at":"2026-06-25T01:17:44.575162+00:00"}