{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YYZTJNSR24LRSTQNZ27RE2BCJT","short_pith_number":"pith:YYZTJNSR","schema_version":"1.0","canonical_sha256":"c63334b651d717194e0dcebf1268224cec623ac8b466f0eb0f4d3105685bd6e6","source":{"kind":"arxiv","id":"2506.05087","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Multimodal Framework for Human-Centered Street Assessment: Integrating Visual-Language Models for Perceptual Urban Diagnostics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haotian Lan","submitted_at":"2025-06-05T14:34:04Z","abstract_excerpt":"While objective street metrics derived from imagery or GIS have become standard in urban analytics, they remain insufficient to capture subjective perceptions essential to inclusive urban design. This study introduces a novel Multimodal Street Evaluation Framework (MSEF) that fuses a vision transformer (VisualGLM-6B) with a large language model (GPT-4), enabling interpretable dual-output assessment of streetscapes. Leveraging over 15,000 annotated street-view images from Harbin, China, we fine-tune the framework using LoRA and P-Tuning v2 for parameter-efficient adaptation. The model achieves "},"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":"2506.05087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:34:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4df3b5741e21d0105cb02f022e0f9e3c228dc1a7a56919524c0dd4c7c7beb2bc","abstract_canon_sha256":"454da80736f99185d1171248c584b89c2d3d85901430645252a96c1de9ddfb87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:42.015023Z","signature_b64":"SVLRwhgGZb3IJBiBNX8FNNzKsD+ltsa3u3yVJeDpIlX46GzM9BypoLSYm7bWfJE8BViXkkT8L8SzxUzgrUoGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c63334b651d717194e0dcebf1268224cec623ac8b466f0eb0f4d3105685bd6e6","last_reissued_at":"2026-07-05T11:16:42.014509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:42.014509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Multimodal Framework for Human-Centered Street Assessment: Integrating Visual-Language Models for Perceptual Urban Diagnostics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haotian Lan","submitted_at":"2025-06-05T14:34:04Z","abstract_excerpt":"While objective street metrics derived from imagery or GIS have become standard in urban analytics, they remain insufficient to capture subjective perceptions essential to inclusive urban design. This study introduces a novel Multimodal Street Evaluation Framework (MSEF) that fuses a vision transformer (VisualGLM-6B) with a large language model (GPT-4), enabling interpretable dual-output assessment of streetscapes. Leveraging over 15,000 annotated street-view images from Harbin, China, we fine-tune the framework using LoRA and P-Tuning v2 for parameter-efficient adaptation. The model achieves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05087","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/2506.05087/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":"2506.05087","created_at":"2026-07-05T11:16:42.014584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05087v1","created_at":"2026-07-05T11:16:42.014584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05087","created_at":"2026-07-05T11:16:42.014584+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYZTJNSR24LR","created_at":"2026-07-05T11:16:42.014584+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYZTJNSR24LRSTQN","created_at":"2026-07-05T11:16:42.014584+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYZTJNSR","created_at":"2026-07-05T11:16:42.014584+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/YYZTJNSR24LRSTQNZ27RE2BCJT","json":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT.json","graph_json":"https://pith.science/api/pith-number/YYZTJNSR24LRSTQNZ27RE2BCJT/graph.json","events_json":"https://pith.science/api/pith-number/YYZTJNSR24LRSTQNZ27RE2BCJT/events.json","paper":"https://pith.science/paper/YYZTJNSR"},"agent_actions":{"view_html":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT","download_json":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT.json","view_paper":"https://pith.science/paper/YYZTJNSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05087&json=true","fetch_graph":"https://pith.science/api/pith-number/YYZTJNSR24LRSTQNZ27RE2BCJT/graph.json","fetch_events":"https://pith.science/api/pith-number/YYZTJNSR24LRSTQNZ27RE2BCJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/action/storage_attestation","attest_author":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/action/author_attestation","sign_citation":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/action/citation_signature","submit_replication":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/action/replication_record"}},"created_at":"2026-07-05T11:16:42.014584+00:00","updated_at":"2026-07-05T11:16:42.014584+00:00"}