{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TEXOGRNNI5LIWNSVNLYYGYNG72","short_pith_number":"pith:TEXOGRNN","schema_version":"1.0","canonical_sha256":"992ee345ad47568b36556af18361a6fe93d871377d57170f400e8ea837b7a865","source":{"kind":"arxiv","id":"2311.14656","version":3},"attestation_state":"computed","paper":{"title":"Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jonathan Roberts, Kai Han, Rehan Sheikh, Samuel Albanie, Timo L\\\"uddecke","submitted_at":"2023-11-24T18:46:02Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown remarkable capabilities across a broad range of tasks but their knowledge and abilities in the geographic and geospatial domains are yet to be explored, despite potential wide-ranging benefits to navigation, environmental research, urban development, and disaster response. We conduct a series of experiments exploring various vision capabilities of MLLMs within these domains, particularly focusing on the frontier model GPT-4V, and benchmark its performance against open-source counterparts. Our methodology involves challenging these models with"},"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":"2311.14656","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-24T18:46:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b08e8b675cd07cb537f269f86b1e6f96386a102f8ff9d7c36de31f96ba095007","abstract_canon_sha256":"ed405f25807627007932854bbd82133541376083866c4ab1373398044d1f848e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:58.531542Z","signature_b64":"4REiWs7NqUm80uoTM0CouckxLWQyljpsd5ch3E4U/LjpvTsZQ7qY/jpUrhtStUtBHIfjRKFGpNlfsaRF2hd6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"992ee345ad47568b36556af18361a6fe93d871377d57170f400e8ea837b7a865","last_reissued_at":"2026-07-05T07:33:58.531079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:58.531079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jonathan Roberts, Kai Han, Rehan Sheikh, Samuel Albanie, Timo L\\\"uddecke","submitted_at":"2023-11-24T18:46:02Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown remarkable capabilities across a broad range of tasks but their knowledge and abilities in the geographic and geospatial domains are yet to be explored, despite potential wide-ranging benefits to navigation, environmental research, urban development, and disaster response. We conduct a series of experiments exploring various vision capabilities of MLLMs within these domains, particularly focusing on the frontier model GPT-4V, and benchmark its performance against open-source counterparts. Our methodology involves challenging these models with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14656","kind":"arxiv","version":3},"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/2311.14656/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":"2311.14656","created_at":"2026-07-05T07:33:58.531141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14656v3","created_at":"2026-07-05T07:33:58.531141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14656","created_at":"2026-07-05T07:33:58.531141+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEXOGRNNI5LI","created_at":"2026-07-05T07:33:58.531141+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEXOGRNNI5LIWNSV","created_at":"2026-07-05T07:33:58.531141+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEXOGRNN","created_at":"2026-07-05T07:33:58.531141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05744","citing_title":"PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16248","citing_title":"Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72","json":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72.json","graph_json":"https://pith.science/api/pith-number/TEXOGRNNI5LIWNSVNLYYGYNG72/graph.json","events_json":"https://pith.science/api/pith-number/TEXOGRNNI5LIWNSVNLYYGYNG72/events.json","paper":"https://pith.science/paper/TEXOGRNN"},"agent_actions":{"view_html":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72","download_json":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72.json","view_paper":"https://pith.science/paper/TEXOGRNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14656&json=true","fetch_graph":"https://pith.science/api/pith-number/TEXOGRNNI5LIWNSVNLYYGYNG72/graph.json","fetch_events":"https://pith.science/api/pith-number/TEXOGRNNI5LIWNSVNLYYGYNG72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72/action/storage_attestation","attest_author":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72/action/author_attestation","sign_citation":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72/action/citation_signature","submit_replication":"https://pith.science/pith/TEXOGRNNI5LIWNSVNLYYGYNG72/action/replication_record"}},"created_at":"2026-07-05T07:33:58.531141+00:00","updated_at":"2026-07-05T07:33:58.531141+00:00"}