{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VY4Y3ZFW5QO3R6URBLMLKGG7RA","short_pith_number":"pith:VY4Y3ZFW","schema_version":"1.0","canonical_sha256":"ae398de4b6ec1db8fa910ad8b518df882026f1a1c0c0af857119b5e8e3c52576","source":{"kind":"arxiv","id":"2403.16831","version":3},"attestation_state":"computed","paper":{"title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kun Wang, Qingsong Wen, Siru Zhong, Wei Chen, Xixuan Hao, Yibo Yan, Yuxuan Liang","submitted_at":"2024-03-25T14:57:18Z","abstract_excerpt":"Urban socioeconomic indicator prediction aims to infer various metrics related to sustainable development in diverse urban landscapes using data-driven methods. However, prevalent pretrained models, particularly those reliant on satellite imagery, face dual challenges. Firstly, concentrating solely on macro-level patterns from satellite data may introduce bias, lacking nuanced details at micro levels, such as architectural details at a place. Secondly, the text generated by the precursor work UrbanCLIP, which fully utilizes the extensive knowledge of LLMs, frequently exhibits issues such as ha"},"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":"2403.16831","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T14:57:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5603114947046708061f8c9d5268c59867f9788062a715042fd62395ef3997f9","abstract_canon_sha256":"754800af9a4e4f5e599868c7d2d2682fe9a39af68cb61524a65721f232cdb3c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:41.661689Z","signature_b64":"tBeEjqhqznRFv8BP/IGPgJ1YDs0QI0wZkJRug5RGLU/7fOJ0b4UaMhr3jzdvYq6zbNh4qA/UyK4JvupcBvdkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae398de4b6ec1db8fa910ad8b518df882026f1a1c0c0af857119b5e8e3c52576","last_reissued_at":"2026-07-05T10:03:41.661159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:41.661159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kun Wang, Qingsong Wen, Siru Zhong, Wei Chen, Xixuan Hao, Yibo Yan, Yuxuan Liang","submitted_at":"2024-03-25T14:57:18Z","abstract_excerpt":"Urban socioeconomic indicator prediction aims to infer various metrics related to sustainable development in diverse urban landscapes using data-driven methods. However, prevalent pretrained models, particularly those reliant on satellite imagery, face dual challenges. Firstly, concentrating solely on macro-level patterns from satellite data may introduce bias, lacking nuanced details at micro levels, such as architectural details at a place. Secondly, the text generated by the precursor work UrbanCLIP, which fully utilizes the extensive knowledge of LLMs, frequently exhibits issues such as ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16831","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/2403.16831/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":"2403.16831","created_at":"2026-07-05T10:03:41.661227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16831v3","created_at":"2026-07-05T10:03:41.661227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16831","created_at":"2026-07-05T10:03:41.661227+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY4Y3ZFW5QO3","created_at":"2026-07-05T10:03:41.661227+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY4Y3ZFW5QO3R6UR","created_at":"2026-07-05T10:03:41.661227+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY4Y3ZFW","created_at":"2026-07-05T10:03:41.661227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04509","citing_title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA","json":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA.json","graph_json":"https://pith.science/api/pith-number/VY4Y3ZFW5QO3R6URBLMLKGG7RA/graph.json","events_json":"https://pith.science/api/pith-number/VY4Y3ZFW5QO3R6URBLMLKGG7RA/events.json","paper":"https://pith.science/paper/VY4Y3ZFW"},"agent_actions":{"view_html":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA","download_json":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA.json","view_paper":"https://pith.science/paper/VY4Y3ZFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16831&json=true","fetch_graph":"https://pith.science/api/pith-number/VY4Y3ZFW5QO3R6URBLMLKGG7RA/graph.json","fetch_events":"https://pith.science/api/pith-number/VY4Y3ZFW5QO3R6URBLMLKGG7RA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA/action/storage_attestation","attest_author":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA/action/author_attestation","sign_citation":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA/action/citation_signature","submit_replication":"https://pith.science/pith/VY4Y3ZFW5QO3R6URBLMLKGG7RA/action/replication_record"}},"created_at":"2026-07-05T10:03:41.661227+00:00","updated_at":"2026-07-05T10:03:41.661227+00:00"}