{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GGDOLSILM3245YKTWPV4V3S6CG","short_pith_number":"pith:GGDOLSIL","schema_version":"1.0","canonical_sha256":"3186e5c90b66f5cee153b3ebcaee5e11904586c1fd24894e8880f3860d94c183","source":{"kind":"arxiv","id":"2509.01910","version":2},"attestation_state":"computed","paper":{"title":"Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ce Hou, Fan Zhang, Furong Jia, Lanxin Liu, Xinyan Liu, Yu Liu","submitted_at":"2025-09-02T03:07:26Z","abstract_excerpt":"Worldwide geo-localization involves determining the exact geographic location of images captured globally, typically guided by geographic cues such as climate, landmarks, and architectural styles. Despite advancements in geo-localization models like GeoCLIP, which leverages images and location alignment via contrastive learning for accurate predictions, the interpretability of these models remains insufficiently explored. Current concept-based interpretability methods fail to align effectively with Geo-alignment image-location embedding objectives, resulting in suboptimal interpretability and "},"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":"2509.01910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T03:07:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbc647b638d5f7353dce563032422d830bf356f5ef34fa9a2c6daac3e86cc0ff","abstract_canon_sha256":"cc1ba20089514f64b6c373a4532b8d9f6f8d9a0769d1a767522f2f369f998f2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:21.166731Z","signature_b64":"Vmh/9mFxnWjO1NeIQmz2BX+YpLAgzn0w7F/gukrYyxSfU0GijXncvns6qKIa6o+LfoLyvo4IvaQ6D2xSZ/6kDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3186e5c90b66f5cee153b3ebcaee5e11904586c1fd24894e8880f3860d94c183","last_reissued_at":"2026-07-05T12:05:21.166206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:21.166206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ce Hou, Fan Zhang, Furong Jia, Lanxin Liu, Xinyan Liu, Yu Liu","submitted_at":"2025-09-02T03:07:26Z","abstract_excerpt":"Worldwide geo-localization involves determining the exact geographic location of images captured globally, typically guided by geographic cues such as climate, landmarks, and architectural styles. Despite advancements in geo-localization models like GeoCLIP, which leverages images and location alignment via contrastive learning for accurate predictions, the interpretability of these models remains insufficiently explored. Current concept-based interpretability methods fail to align effectively with Geo-alignment image-location embedding objectives, resulting in suboptimal interpretability and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01910","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/2509.01910/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":"2509.01910","created_at":"2026-07-05T12:05:21.166281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01910v2","created_at":"2026-07-05T12:05:21.166281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01910","created_at":"2026-07-05T12:05:21.166281+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGDOLSILM324","created_at":"2026-07-05T12:05:21.166281+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGDOLSILM3245YKT","created_at":"2026-07-05T12:05:21.166281+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGDOLSIL","created_at":"2026-07-05T12:05:21.166281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07292","citing_title":"CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24997","citing_title":"What's in an Earth Embedding? An Explainability Analysis of Location Encoders","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG","json":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG.json","graph_json":"https://pith.science/api/pith-number/GGDOLSILM3245YKTWPV4V3S6CG/graph.json","events_json":"https://pith.science/api/pith-number/GGDOLSILM3245YKTWPV4V3S6CG/events.json","paper":"https://pith.science/paper/GGDOLSIL"},"agent_actions":{"view_html":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG","download_json":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG.json","view_paper":"https://pith.science/paper/GGDOLSIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01910&json=true","fetch_graph":"https://pith.science/api/pith-number/GGDOLSILM3245YKTWPV4V3S6CG/graph.json","fetch_events":"https://pith.science/api/pith-number/GGDOLSILM3245YKTWPV4V3S6CG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG/action/storage_attestation","attest_author":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG/action/author_attestation","sign_citation":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG/action/citation_signature","submit_replication":"https://pith.science/pith/GGDOLSILM3245YKTWPV4V3S6CG/action/replication_record"}},"created_at":"2026-07-05T12:05:21.166281+00:00","updated_at":"2026-07-05T12:05:21.166281+00:00"}