{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZN7WDERCLDIQKKLDHBMP6XLWFP","short_pith_number":"pith:ZN7WDERC","schema_version":"1.0","canonical_sha256":"cb7f61922258d10529633858ff5d762bf4f16d1d2bb19c1ddbeaf86eeaba6c41","source":{"kind":"arxiv","id":"2608.07411","version":1},"attestation_state":"computed","paper":{"title":"GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jose G Moreno, Karim Radouane, Lynda Tamine, Rodrigo Ferreira Rodrigues","submitted_at":"2026-08-07T16:58:04Z","abstract_excerpt":"In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities. In this paper, we present \\benchName, a comprehensive benchmark for probing LLMs on geo-related tasks. We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains, and evaluate a set of LLMs on geo-spatial and temporal understanding using our benchmark. Our results show that reasoning and size have a strong impact on overall performance. GeoBenchLLM is publ"},"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":"2608.07411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T16:58:04Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"5c759b471dc626b5d2c9534431c059a0cf10a5d36b6e22ca3f08d1972b0d3451","abstract_canon_sha256":"dab2b5271da02d83cca25e7fc0f3261b295470751523f24b1d6f3a21e51b2c52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:17.999210Z","signature_b64":"THUhJqx3oNsKepznsv15LSVzTFOe35sEHQ/IhVxFwapzp6FbzHlDoODXfz5+gyi1i11PsSZl6dynnu6CeTq1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb7f61922258d10529633858ff5d762bf4f16d1d2bb19c1ddbeaf86eeaba6c41","last_reissued_at":"2026-08-10T01:15:17.996756Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:17.996756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jose G Moreno, Karim Radouane, Lynda Tamine, Rodrigo Ferreira Rodrigues","submitted_at":"2026-08-07T16:58:04Z","abstract_excerpt":"In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities. In this paper, we present \\benchName, a comprehensive benchmark for probing LLMs on geo-related tasks. We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains, and evaluate a set of LLMs on geo-spatial and temporal understanding using our benchmark. Our results show that reasoning and size have a strong impact on overall performance. GeoBenchLLM is publ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07411","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/2608.07411/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":"2608.07411","created_at":"2026-08-10T01:15:17.997684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07411v1","created_at":"2026-08-10T01:15:17.997684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07411","created_at":"2026-08-10T01:15:17.997684+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZN7WDERCLDIQ","created_at":"2026-08-10T01:15:17.997684+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZN7WDERCLDIQKKLD","created_at":"2026-08-10T01:15:17.997684+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZN7WDERC","created_at":"2026-08-10T01:15:17.997684+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/ZN7WDERCLDIQKKLDHBMP6XLWFP","json":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP.json","graph_json":"https://pith.science/api/pith-number/ZN7WDERCLDIQKKLDHBMP6XLWFP/graph.json","events_json":"https://pith.science/api/pith-number/ZN7WDERCLDIQKKLDHBMP6XLWFP/events.json","paper":"https://pith.science/paper/ZN7WDERC"},"agent_actions":{"view_html":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP","download_json":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP.json","view_paper":"https://pith.science/paper/ZN7WDERC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07411&json=true","fetch_graph":"https://pith.science/api/pith-number/ZN7WDERCLDIQKKLDHBMP6XLWFP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZN7WDERCLDIQKKLDHBMP6XLWFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP/action/storage_attestation","attest_author":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP/action/author_attestation","sign_citation":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP/action/citation_signature","submit_replication":"https://pith.science/pith/ZN7WDERCLDIQKKLDHBMP6XLWFP/action/replication_record"}},"created_at":"2026-08-10T01:15:17.997684+00:00","updated_at":"2026-08-10T01:15:17.997684+00:00"}