{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6ZANICCFGPCMJJWR7NALAI4QMI","short_pith_number":"pith:6ZANICCF","schema_version":"1.0","canonical_sha256":"f640d4084533c4c4a6d1fb40b023906239ff9af003313262ed3047e42b680327","source":{"kind":"arxiv","id":"2606.22543","version":1},"attestation_state":"computed","paper":{"title":"MAPS: Multi-Anchor Projection Similarity for Joint Vision-Language Geo-Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayuan Li, Pengcheng Shi, Qingwu Hu, Shaocheng Yan, Siyuan Tan, Yutong Hu","submitted_at":"2026-06-21T15:01:53Z","abstract_excerpt":"Humans localize places by integrating perceptual cues from vision with semantic reasoning from language, forming a scene understanding that is both intuitive and structured. Although existing geo-localization models have made substantial progress in cross-view and cross-modal settings, they are largely built upon point-to-point alignment, which is insufficient for joint vision-language queries. In such queries, visual and textual cues do not simply act as independent references, but jointly define a semantic subspace for locating the target. In this paper, we formulate vision-language geo-loca"},"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":"2606.22543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T15:01:53Z","cross_cats_sorted":[],"title_canon_sha256":"43015703a494cb795bdf7fabbe522f4fd7d8a81416a6ef1f7e6d9247ad730293","abstract_canon_sha256":"82826cb73b6e6bcbc26e2673bf858574b70a67a90ce5c602e38ce12035b2118f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:41.180185Z","signature_b64":"hhN6txUgIhXw/H4c5b1meOys0CMQr06WA2LfVZ6eIdbvu+oig2hdoBfOgMnYeKY48J9mruHjXzLxAsB5DIFmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f640d4084533c4c4a6d1fb40b023906239ff9af003313262ed3047e42b680327","last_reissued_at":"2026-06-23T02:13:41.179791Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:41.179791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAPS: Multi-Anchor Projection Similarity for Joint Vision-Language Geo-Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayuan Li, Pengcheng Shi, Qingwu Hu, Shaocheng Yan, Siyuan Tan, Yutong Hu","submitted_at":"2026-06-21T15:01:53Z","abstract_excerpt":"Humans localize places by integrating perceptual cues from vision with semantic reasoning from language, forming a scene understanding that is both intuitive and structured. Although existing geo-localization models have made substantial progress in cross-view and cross-modal settings, they are largely built upon point-to-point alignment, which is insufficient for joint vision-language queries. In such queries, visual and textual cues do not simply act as independent references, but jointly define a semantic subspace for locating the target. In this paper, we formulate vision-language geo-loca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22543","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/2606.22543/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":"2606.22543","created_at":"2026-06-23T02:13:41.179857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22543v1","created_at":"2026-06-23T02:13:41.179857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22543","created_at":"2026-06-23T02:13:41.179857+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZANICCFGPCM","created_at":"2026-06-23T02:13:41.179857+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZANICCFGPCMJJWR","created_at":"2026-06-23T02:13:41.179857+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZANICCF","created_at":"2026-06-23T02:13:41.179857+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/6ZANICCFGPCMJJWR7NALAI4QMI","json":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI.json","graph_json":"https://pith.science/api/pith-number/6ZANICCFGPCMJJWR7NALAI4QMI/graph.json","events_json":"https://pith.science/api/pith-number/6ZANICCFGPCMJJWR7NALAI4QMI/events.json","paper":"https://pith.science/paper/6ZANICCF"},"agent_actions":{"view_html":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI","download_json":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI.json","view_paper":"https://pith.science/paper/6ZANICCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22543&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZANICCFGPCMJJWR7NALAI4QMI/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZANICCFGPCMJJWR7NALAI4QMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI/action/storage_attestation","attest_author":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI/action/author_attestation","sign_citation":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI/action/citation_signature","submit_replication":"https://pith.science/pith/6ZANICCFGPCMJJWR7NALAI4QMI/action/replication_record"}},"created_at":"2026-06-23T02:13:41.179857+00:00","updated_at":"2026-06-23T02:13:41.179857+00:00"}