{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5OYH6QAMWR4UGYIGNJKDGQLTZQ","short_pith_number":"pith:5OYH6QAM","schema_version":"1.0","canonical_sha256":"ebb07f400cb4794361066a54334173cc0e9e41a0fec16b145f8da469202eb667","source":{"kind":"arxiv","id":"2507.12795","version":1},"attestation_state":"computed","paper":{"title":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changqun Xia, Penglei Sun, Qiang Wang, Tiefeng Li, Xiang Liu, Xiangru Zhu, Xiaowen Chu, Yang Yang, Yaoxian Song, Yue Liu","submitted_at":"2025-07-17T05:21:21Z","abstract_excerpt":"Scene understanding enables intelligent agents to interpret and comprehend their environment. While existing large vision-language models (LVLMs) for scene understanding have primarily focused on indoor household tasks, they face two significant limitations when applied to outdoor large-scale scene understanding. First, outdoor scenarios typically encompass larger-scale environments observed through various sensors from multiple viewpoints (e.g., bird view and terrestrial view), while existing indoor LVLMs mainly analyze single visual modalities within building-scale contexts from humanoid vie"},"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":"2507.12795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T05:21:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88fc0d3beadeb41305983ef3b850b46114bfed9407e3e6cd9c70e8483d46128e","abstract_canon_sha256":"333e2971e7c3aeb13066d596e54cb2c8b6c810fcd370d82ca354e544db1520e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:39.341556Z","signature_b64":"9EwkBzPn8I975PBB7DYqpcFcHN4uYDM+FqtbPPHQDx5YM3Emi6SfZnRh1WxZ2rsCwymT6II8Wl8QI0cIavl+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebb07f400cb4794361066a54334173cc0e9e41a0fec16b145f8da469202eb667","last_reissued_at":"2026-07-05T11:38:39.340844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:39.340844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changqun Xia, Penglei Sun, Qiang Wang, Tiefeng Li, Xiang Liu, Xiangru Zhu, Xiaowen Chu, Yang Yang, Yaoxian Song, Yue Liu","submitted_at":"2025-07-17T05:21:21Z","abstract_excerpt":"Scene understanding enables intelligent agents to interpret and comprehend their environment. While existing large vision-language models (LVLMs) for scene understanding have primarily focused on indoor household tasks, they face two significant limitations when applied to outdoor large-scale scene understanding. First, outdoor scenarios typically encompass larger-scale environments observed through various sensors from multiple viewpoints (e.g., bird view and terrestrial view), while existing indoor LVLMs mainly analyze single visual modalities within building-scale contexts from humanoid vie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12795","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/2507.12795/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":"2507.12795","created_at":"2026-07-05T11:38:39.340922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12795v1","created_at":"2026-07-05T11:38:39.340922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12795","created_at":"2026-07-05T11:38:39.340922+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OYH6QAMWR4U","created_at":"2026-07-05T11:38:39.340922+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OYH6QAMWR4UGYIG","created_at":"2026-07-05T11:38:39.340922+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OYH6QAM","created_at":"2026-07-05T11:38:39.340922+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/5OYH6QAMWR4UGYIGNJKDGQLTZQ","json":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ.json","graph_json":"https://pith.science/api/pith-number/5OYH6QAMWR4UGYIGNJKDGQLTZQ/graph.json","events_json":"https://pith.science/api/pith-number/5OYH6QAMWR4UGYIGNJKDGQLTZQ/events.json","paper":"https://pith.science/paper/5OYH6QAM"},"agent_actions":{"view_html":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ","download_json":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ.json","view_paper":"https://pith.science/paper/5OYH6QAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12795&json=true","fetch_graph":"https://pith.science/api/pith-number/5OYH6QAMWR4UGYIGNJKDGQLTZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5OYH6QAMWR4UGYIGNJKDGQLTZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ/action/storage_attestation","attest_author":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ/action/author_attestation","sign_citation":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ/action/citation_signature","submit_replication":"https://pith.science/pith/5OYH6QAMWR4UGYIGNJKDGQLTZQ/action/replication_record"}},"created_at":"2026-07-05T11:38:39.340922+00:00","updated_at":"2026-07-05T11:38:39.340922+00:00"}