{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQAENLDUP6B4M6KMKXXOALKBLW","short_pith_number":"pith:ZQAENLDU","schema_version":"1.0","canonical_sha256":"cc0046ac747f83c6794c55eee02d415da200e51a5ff080d8603c5dc2f905924d","source":{"kind":"arxiv","id":"2507.04706","version":1},"attestation_state":"computed","paper":{"title":"UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengtao Jian, Hui Ma, Kai Yang, Shengjie Zhao, Xiaozhou Ye, Ye Ouyang, Zelin Zhu","submitted_at":"2025-07-07T06:57:34Z","abstract_excerpt":"Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we introduce UrbanMind, a tool-enhanced retrieval-augmented generation (RAG) framework designed to facilitate UGI. Central to UrbanMind is a novel architecture based on Continual Retrieval-Augmented MoE-based LLM (C-RAG-LLM), which dynamically incorporates domain-specific knowledge and evolving urban data to support long-term adaptability. The architecture of C-RAG-LLM aligns naturally with a multilevel optimization framew"},"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":"2507.04706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T06:57:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2622d9112570b6fe2a665f8c0b3151f3064984ccf1ca190cfabfb1f8cb8377de","abstract_canon_sha256":"d0506c97e2c853667e1be198cd0ade72008ee0521a1d82a35a6e2900b87a4f91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:52.498047Z","signature_b64":"ofWJC0ZG3zG6tPb1ljKVYxu89nCuq/MjWiCdGi0KZNAodrwVkQ4zXkJQDB8FYBesmWJRHAe1YKkGUtxK3CNhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc0046ac747f83c6794c55eee02d415da200e51a5ff080d8603c5dc2f905924d","last_reissued_at":"2026-07-05T11:32:52.497551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:52.497551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengtao Jian, Hui Ma, Kai Yang, Shengjie Zhao, Xiaozhou Ye, Ye Ouyang, Zelin Zhu","submitted_at":"2025-07-07T06:57:34Z","abstract_excerpt":"Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we introduce UrbanMind, a tool-enhanced retrieval-augmented generation (RAG) framework designed to facilitate UGI. Central to UrbanMind is a novel architecture based on Continual Retrieval-Augmented MoE-based LLM (C-RAG-LLM), which dynamically incorporates domain-specific knowledge and evolving urban data to support long-term adaptability. The architecture of C-RAG-LLM aligns naturally with a multilevel optimization framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04706","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/2507.04706/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":"2507.04706","created_at":"2026-07-05T11:32:52.497609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04706v1","created_at":"2026-07-05T11:32:52.497609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04706","created_at":"2026-07-05T11:32:52.497609+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQAENLDUP6B4","created_at":"2026-07-05T11:32:52.497609+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQAENLDUP6B4M6KM","created_at":"2026-07-05T11:32:52.497609+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQAENLDU","created_at":"2026-07-05T11:32:52.497609+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/ZQAENLDUP6B4M6KMKXXOALKBLW","json":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW.json","graph_json":"https://pith.science/api/pith-number/ZQAENLDUP6B4M6KMKXXOALKBLW/graph.json","events_json":"https://pith.science/api/pith-number/ZQAENLDUP6B4M6KMKXXOALKBLW/events.json","paper":"https://pith.science/paper/ZQAENLDU"},"agent_actions":{"view_html":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW","download_json":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW.json","view_paper":"https://pith.science/paper/ZQAENLDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04706&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQAENLDUP6B4M6KMKXXOALKBLW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQAENLDUP6B4M6KMKXXOALKBLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW/action/storage_attestation","attest_author":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW/action/author_attestation","sign_citation":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW/action/citation_signature","submit_replication":"https://pith.science/pith/ZQAENLDUP6B4M6KMKXXOALKBLW/action/replication_record"}},"created_at":"2026-07-05T11:32:52.497609+00:00","updated_at":"2026-07-05T11:32:52.497609+00:00"}