{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CPSVVGWYIEQUWMSO2Q34SK2BKF","short_pith_number":"pith:CPSVVGWY","schema_version":"1.0","canonical_sha256":"13e55a9ad841214b324ed437c92b41516bd39dff7664a56924f059cfa311116f","source":{"kind":"arxiv","id":"2608.03826","version":1},"attestation_state":"computed","paper":{"title":"Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Jiapeng Li, Junjie Zhou, Yong Li, Yu Liu","submitted_at":"2026-08-04T15:36:17Z","abstract_excerpt":"Geospatial and urban applications increasingly require models to compare heterogeneous evidence across street-view imagery, remote-sensing observations, text descriptions, region proposals, and temporal change cues. However, existing multimodal embedding models and benchmarks are still largely designed and evaluated around general-purpose image-text matching, leaving unclear whether unified embedding space can support heterogeneous geospatial tasks involving spatial relationships, fine-grained semantics, and temporal changes. To address this gap, we make three key contributions. First, we intr"},"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":"2608.03826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T15:36:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cf21737ada96692bf42587976a814d04f9f0f2ae487955b2d2f3859be53c0bc","abstract_canon_sha256":"76ecc05a962e15a2ec386c78659e1a4cdc11727470946360652d36dca9654ce4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:12.797817Z","signature_b64":"jp2dyCF3KSdAo/+QCE8lN6TpA5vp5x+Iaj1XclG8CJisExsYZ7Gr15wctw7Cy+vQE9hyS6FUUobrJzjdOSlYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e55a9ad841214b324ed437c92b41516bd39dff7664a56924f059cfa311116f","last_reissued_at":"2026-08-05T01:37:12.795851Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:12.795851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Jiapeng Li, Junjie Zhou, Yong Li, Yu Liu","submitted_at":"2026-08-04T15:36:17Z","abstract_excerpt":"Geospatial and urban applications increasingly require models to compare heterogeneous evidence across street-view imagery, remote-sensing observations, text descriptions, region proposals, and temporal change cues. However, existing multimodal embedding models and benchmarks are still largely designed and evaluated around general-purpose image-text matching, leaving unclear whether unified embedding space can support heterogeneous geospatial tasks involving spatial relationships, fine-grained semantics, and temporal changes. To address this gap, we make three key contributions. First, we intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03826","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/2608.03826/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":"2608.03826","created_at":"2026-08-05T01:37:12.796539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03826v1","created_at":"2026-08-05T01:37:12.796539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03826","created_at":"2026-08-05T01:37:12.796539+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPSVVGWYIEQU","created_at":"2026-08-05T01:37:12.796539+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPSVVGWYIEQUWMSO","created_at":"2026-08-05T01:37:12.796539+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPSVVGWY","created_at":"2026-08-05T01:37:12.796539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF","json":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF.json","graph_json":"https://pith.science/api/pith-number/CPSVVGWYIEQUWMSO2Q34SK2BKF/graph.json","events_json":"https://pith.science/api/pith-number/CPSVVGWYIEQUWMSO2Q34SK2BKF/events.json","paper":"https://pith.science/paper/CPSVVGWY"},"agent_actions":{"view_html":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF","download_json":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF.json","view_paper":"https://pith.science/paper/CPSVVGWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03826&json=true","fetch_graph":"https://pith.science/api/pith-number/CPSVVGWYIEQUWMSO2Q34SK2BKF/graph.json","fetch_events":"https://pith.science/api/pith-number/CPSVVGWYIEQUWMSO2Q34SK2BKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF/action/storage_attestation","attest_author":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF/action/author_attestation","sign_citation":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF/action/citation_signature","submit_replication":"https://pith.science/pith/CPSVVGWYIEQUWMSO2Q34SK2BKF/action/replication_record"}},"created_at":"2026-08-05T01:37:12.796539+00:00","updated_at":"2026-08-05T01:37:12.796539+00:00"}