{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IQU7FBGGJMWQPK5DPAQU3MSNAL","short_pith_number":"pith:IQU7FBGG","schema_version":"1.0","canonical_sha256":"4429f284c64b2d07aba378214db24d02dc493d200ebd4b7aa2e000dc31f873f3","source":{"kind":"arxiv","id":"2501.00316","version":2},"attestation_state":"computed","paper":{"title":"MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mahir Labib Dihan, Md Almash Alam, Md Hasebul Hasan, Md Rizwan Parvez, MD Tanvir Hassan, Md Tanvir Parvez, Mohammed Eunus Ali, Muhammad Aamir Cheema","submitted_at":"2024-12-31T07:20:32Z","abstract_excerpt":"Recent advancements in foundation models have improved autonomous tool usage and reasoning, but their capabilities in map-based reasoning remain underexplored. To address this, we introduce MapEval, a benchmark designed to assess foundation models across three distinct tasks - textual, API-based, and visual reasoning - through 700 multiple-choice questions spanning 180 cities and 54 countries, covering spatial relationships, navigation, travel planning, and real-world map interactions. Unlike prior benchmarks that focus on simple location queries, MapEval requires models to handle long-context"},"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":"2501.00316","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T07:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"d888e53ead8d12a21367536cca1e4543a3c902afd21abd17f760bb53a6f94bf4","abstract_canon_sha256":"1987799e4b187221d1fa63557be50ba0eda29cbc5e2559b28697000ee58e0054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:53.777943Z","signature_b64":"LTwQ0sVlzXOmwJf2X54pHL+7XBRKiBBSBcLH0X3bMjVReXg4SHJlpjcSihJLw0i/oHZR6ROuQ+rhnguRciNoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4429f284c64b2d07aba378214db24d02dc493d200ebd4b7aa2e000dc31f873f3","last_reissued_at":"2026-07-05T11:16:53.777447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:53.777447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mahir Labib Dihan, Md Almash Alam, Md Hasebul Hasan, Md Rizwan Parvez, MD Tanvir Hassan, Md Tanvir Parvez, Mohammed Eunus Ali, Muhammad Aamir Cheema","submitted_at":"2024-12-31T07:20:32Z","abstract_excerpt":"Recent advancements in foundation models have improved autonomous tool usage and reasoning, but their capabilities in map-based reasoning remain underexplored. To address this, we introduce MapEval, a benchmark designed to assess foundation models across three distinct tasks - textual, API-based, and visual reasoning - through 700 multiple-choice questions spanning 180 cities and 54 countries, covering spatial relationships, navigation, travel planning, and real-world map interactions. Unlike prior benchmarks that focus on simple location queries, MapEval requires models to handle long-context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00316","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/2501.00316/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":"2501.00316","created_at":"2026-07-05T11:16:53.777506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00316v2","created_at":"2026-07-05T11:16:53.777506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00316","created_at":"2026-07-05T11:16:53.777506+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQU7FBGGJMWQ","created_at":"2026-07-05T11:16:53.777506+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQU7FBGGJMWQPK5D","created_at":"2026-07-05T11:16:53.777506+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQU7FBGG","created_at":"2026-07-05T11:16:53.777506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2408.10872","citing_title":"V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL","json":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL.json","graph_json":"https://pith.science/api/pith-number/IQU7FBGGJMWQPK5DPAQU3MSNAL/graph.json","events_json":"https://pith.science/api/pith-number/IQU7FBGGJMWQPK5DPAQU3MSNAL/events.json","paper":"https://pith.science/paper/IQU7FBGG"},"agent_actions":{"view_html":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL","download_json":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL.json","view_paper":"https://pith.science/paper/IQU7FBGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00316&json=true","fetch_graph":"https://pith.science/api/pith-number/IQU7FBGGJMWQPK5DPAQU3MSNAL/graph.json","fetch_events":"https://pith.science/api/pith-number/IQU7FBGGJMWQPK5DPAQU3MSNAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL/action/storage_attestation","attest_author":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL/action/author_attestation","sign_citation":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL/action/citation_signature","submit_replication":"https://pith.science/pith/IQU7FBGGJMWQPK5DPAQU3MSNAL/action/replication_record"}},"created_at":"2026-07-05T11:16:53.777506+00:00","updated_at":"2026-07-05T11:16:53.777506+00:00"}