{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ","short_pith_number":"pith:6ZWJS2ZC","schema_version":"1.0","canonical_sha256":"f66c996b22ceafe0a06978a2a1bb2f841c7681091a16d446c5b6d1f3aa55b66f","source":{"kind":"arxiv","id":"2502.12532","version":3},"attestation_state":"computed","paper":{"title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chen Gao, Jincai Huang, Kai Xu, Yatai Ji, Yingfeng Chen, Yong Li, Yong Zhao, Yue Hu, Zhengqiu Zhu, Zhiheng Zheng","submitted_at":"2025-02-18T04:36:15Z","abstract_excerpt":"Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings-spanning environment, action, and perception-largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces. To support this task, we present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks across six categories, grounded in a realistic 3D urban simulator. Moreover, we propose Planner-Manager-Actor (PMA), a novel agent tailored"},"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":"2502.12532","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T04:36:15Z","cross_cats_sorted":[],"title_canon_sha256":"760d15239607e04b6a76682de641e163e29140d978ffa195382200659b1a7597","abstract_canon_sha256":"6a6b50fd23ba1727f9f11e1da878ef28d10c8d6b382d2f1e593cc54942514542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:20.658699Z","signature_b64":"uLSSnrH3pV1AUmX1lcIUnNbp5AgYxTP47UtoKzbyoi+MB5GRKxC73peh2yvURXY89ugJuUs/YwIt3JJB1H9RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f66c996b22ceafe0a06978a2a1bb2f841c7681091a16d446c5b6d1f3aa55b66f","last_reissued_at":"2026-07-05T11:07:20.658175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:20.658175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chen Gao, Jincai Huang, Kai Xu, Yatai Ji, Yingfeng Chen, Yong Li, Yong Zhao, Yue Hu, Zhengqiu Zhu, Zhiheng Zheng","submitted_at":"2025-02-18T04:36:15Z","abstract_excerpt":"Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings-spanning environment, action, and perception-largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces. To support this task, we present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks across six categories, grounded in a realistic 3D urban simulator. Moreover, we propose Planner-Manager-Actor (PMA), a novel agent tailored"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12532","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/2502.12532/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":"2502.12532","created_at":"2026-07-05T11:07:20.658248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12532v3","created_at":"2026-07-05T11:07:20.658248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12532","created_at":"2026-07-05T11:07:20.658248+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZWJS2ZCZ2X6","created_at":"2026-07-05T11:07:20.658248+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZWJS2ZCZ2X6BIDJ","created_at":"2026-07-05T11:07:20.658248+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZWJS2ZC","created_at":"2026-07-05T11:07:20.658248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30404","citing_title":"HUMEMBR: Learning Human Routines for Predictive Embodied Navigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09583","citing_title":"AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12676","citing_title":"BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08639","citing_title":"Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ","json":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ.json","graph_json":"https://pith.science/api/pith-number/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/graph.json","events_json":"https://pith.science/api/pith-number/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/events.json","paper":"https://pith.science/paper/6ZWJS2ZC"},"agent_actions":{"view_html":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ","download_json":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ.json","view_paper":"https://pith.science/paper/6ZWJS2ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12532&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/action/storage_attestation","attest_author":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/action/author_attestation","sign_citation":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/action/citation_signature","submit_replication":"https://pith.science/pith/6ZWJS2ZCZ2X6BIDJPCRKDOZPQQ/action/replication_record"}},"created_at":"2026-07-05T11:07:20.658248+00:00","updated_at":"2026-07-05T11:07:20.658248+00:00"}