{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OZR2SKS4HKHTVLP4VMQ3U5GFHO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a7a782e4ac75b2b655e422bcd40d96ad9ea3ea3de463ddda845503984405d2b4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T13:04:27Z","title_canon_sha256":"321666503a0676c878e34dad6c6eb65db69748af97c983992f24ecac5a6d6300"},"schema_version":"1.0","source":{"id":"2506.23219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23219","created_at":"2026-07-05T11:29:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23219v1","created_at":"2026-07-05T11:29:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23219","created_at":"2026-07-05T11:29:18Z"},{"alias_kind":"pith_short_12","alias_value":"OZR2SKS4HKHT","created_at":"2026-07-05T11:29:18Z"},{"alias_kind":"pith_short_16","alias_value":"OZR2SKS4HKHTVLP4","created_at":"2026-07-05T11:29:18Z"},{"alias_kind":"pith_short_8","alias_value":"OZR2SKS4","created_at":"2026-07-05T11:29:18Z"}],"graph_snapshots":[{"event_id":"sha256:15b102917bba6ab69b48a45854f55e4b3e866f5b12c66ababa7e124ead1c9efc","target":"graph","created_at":"2026-07-05T11:29:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.23219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Urban research involves a wide range of scenarios and tasks that require the understanding of multi-modal data. Current methods often focus on specific data types and lack a unified framework in urban field for processing them comprehensively. The recent success of multi-modal large language models (MLLMs) presents a promising opportunity to overcome this limitation. In this paper, we introduce $\\textit{UrbanLLaVA}$, a multi-modal large language model designed to process these four types of data simultaneously and achieve strong performance across diverse urban tasks compared with general MLLM","authors_text":"Jie Feng, Shengyuan Wang, Tianhui Liu, Yanxin Xi, Yong Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T13:04:27Z","title":"UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23219","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f0c441a543f4d7b23fc81a0cdcd91630342ab566011c14813e36a8e6a4de170b","target":"record","created_at":"2026-07-05T11:29:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a7a782e4ac75b2b655e422bcd40d96ad9ea3ea3de463ddda845503984405d2b4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T13:04:27Z","title_canon_sha256":"321666503a0676c878e34dad6c6eb65db69748af97c983992f24ecac5a6d6300"},"schema_version":"1.0","source":{"id":"2506.23219","kind":"arxiv","version":1}},"canonical_sha256":"7663a92a5c3a8f3aadfcab21ba74c53b8384cbacf5d2cc0dc350bab01ffa1603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7663a92a5c3a8f3aadfcab21ba74c53b8384cbacf5d2cc0dc350bab01ffa1603","first_computed_at":"2026-07-05T11:29:18.060705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:18.060705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j7DX3fJw4eLotyMvbFyXQuZKeCCohl8SEdxG86boarnxhBLqmau1NsSye7gMh3KMD7zCbUdxz7O8TFx7FC99Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:18.061197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0c441a543f4d7b23fc81a0cdcd91630342ab566011c14813e36a8e6a4de170b","sha256:15b102917bba6ab69b48a45854f55e4b3e866f5b12c66ababa7e124ead1c9efc"],"state_sha256":"a2913a6dfece0b773861c9ac15d7bc2249611e183cd0e6c465a9bec647345d3d"}