{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UCLPA2SIX7SXMQVQLH7AYFMRKB","short_pith_number":"pith:UCLPA2SI","schema_version":"1.0","canonical_sha256":"a096f06a48bfe57642b059fe0c15915054f3bce953be49316cbcea0d030bef60","source":{"kind":"arxiv","id":"2605.31251","version":1},"attestation_state":"computed","paper":{"title":"ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guoxin Zhang, Haoran Luo, Kaiwen Xue, Kaoyan Lu, Tao Wei, Yifan Zhu, Yu Feng, Zhonghong Ou","submitted_at":"2026-05-29T12:49:17Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation. We introduce ERGeoBench, a diagnostic benchmark for vision-driven embodied geo-localization. ERGeoBench evaluates models under three progressive settings -- single-view, panorama-view, and embodied-view -- where agents may actively acquire observations through sequential changes in yaw, pitch, and zoom. The benchmark contains 2,207 globally distributed street-view panoramas and measures four complementary capabi"},"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":"2605.31251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T12:49:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0920eccd17779558b586f0543ca88beb3d0a97566887af0810c5ab0360c03c61","abstract_canon_sha256":"6b305654b4ce1e85dc99ed4f3d217791b93f9fa6c8c2b58d268352a5ad6b5134"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:06.711771Z","signature_b64":"XJqyY4NhnRlBIwAekghcHw2CnZFpc9P3OgIQj7v6NhV7rLjAJq6yuNAZjUMQ483Djpvfd3lJQurYuODewSi4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a096f06a48bfe57642b059fe0c15915054f3bce953be49316cbcea0d030bef60","last_reissued_at":"2026-06-01T01:04:06.710701Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:06.710701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guoxin Zhang, Haoran Luo, Kaiwen Xue, Kaoyan Lu, Tao Wei, Yifan Zhu, Yu Feng, Zhonghong Ou","submitted_at":"2026-05-29T12:49:17Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation. We introduce ERGeoBench, a diagnostic benchmark for vision-driven embodied geo-localization. ERGeoBench evaluates models under three progressive settings -- single-view, panorama-view, and embodied-view -- where agents may actively acquire observations through sequential changes in yaw, pitch, and zoom. The benchmark contains 2,207 globally distributed street-view panoramas and measures four complementary capabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31251","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/2605.31251/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":"2605.31251","created_at":"2026-06-01T01:04:06.710887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31251v1","created_at":"2026-06-01T01:04:06.710887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31251","created_at":"2026-06-01T01:04:06.710887+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCLPA2SIX7SX","created_at":"2026-06-01T01:04:06.710887+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCLPA2SIX7SXMQVQ","created_at":"2026-06-01T01:04:06.710887+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCLPA2SI","created_at":"2026-06-01T01:04:06.710887+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/UCLPA2SIX7SXMQVQLH7AYFMRKB","json":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB.json","graph_json":"https://pith.science/api/pith-number/UCLPA2SIX7SXMQVQLH7AYFMRKB/graph.json","events_json":"https://pith.science/api/pith-number/UCLPA2SIX7SXMQVQLH7AYFMRKB/events.json","paper":"https://pith.science/paper/UCLPA2SI"},"agent_actions":{"view_html":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB","download_json":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB.json","view_paper":"https://pith.science/paper/UCLPA2SI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31251&json=true","fetch_graph":"https://pith.science/api/pith-number/UCLPA2SIX7SXMQVQLH7AYFMRKB/graph.json","fetch_events":"https://pith.science/api/pith-number/UCLPA2SIX7SXMQVQLH7AYFMRKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB/action/storage_attestation","attest_author":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB/action/author_attestation","sign_citation":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB/action/citation_signature","submit_replication":"https://pith.science/pith/UCLPA2SIX7SXMQVQLH7AYFMRKB/action/replication_record"}},"created_at":"2026-06-01T01:04:06.710887+00:00","updated_at":"2026-06-01T01:04:06.710887+00:00"}