{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YYZTJNSR24LRSTQNZ27RE2BCJT","short_pith_number":"pith:YYZTJNSR","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"},"canonical_sha256":"c63334b651d717194e0dcebf1268224cec623ac8b466f0eb0f4d3105685bd6e6","source":{"kind":"arxiv","id":"2506.05087","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05087","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05087v1","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05087","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"pith_short_12","alias_value":"YYZTJNSR24LR","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"pith_short_16","alias_value":"YYZTJNSR24LRSTQN","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"pith_short_8","alias_value":"YYZTJNSR","created_at":"2026-07-05T11:16:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YYZTJNSR24LRSTQNZ27RE2BCJT","target":"record","payload":{"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"},"canonical_sha256":"c63334b651d717194e0dcebf1268224cec623ac8b466f0eb0f4d3105685bd6e6","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"},"source_kind":"arxiv","source_id":"2506.05087","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KezYbJ6FrpqLNuqO5pseAzkYBONlM7TpIMZd1ePz9mwyq+5NjCkcBVmrPBDeRw5L7ulqjV3u+JKBENdWuhBrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:09:30.371060Z"},"content_sha256":"d5748708514b9ad476f2bfcdf43ee84b2a5ee814dd46c8f39d74bbefa0d7b856","schema_version":"1.0","event_id":"sha256:d5748708514b9ad476f2bfcdf43ee84b2a5ee814dd46c8f39d74bbefa0d7b856"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YYZTJNSR24LRSTQNZ27RE2BCJT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nm/BHbKfiFDrwXjj+lkEFMXKjoXYsN1i/8Skbo8C75mGm8Hk7UPBtty8q3mwE4F8EzXeZ4nF8Ep7xg0H87IBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:09:30.371552Z"},"content_sha256":"e29f6aa25ac77d5ca5c7bbecf06eadcde1f07e168f4e6d2486e1e32937e3d3a6","schema_version":"1.0","event_id":"sha256:e29f6aa25ac77d5ca5c7bbecf06eadcde1f07e168f4e6d2486e1e32937e3d3a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/bundle.json","state_url":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:09:30Z","links":{"resolver":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT","bundle":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/bundle.json","state":"https://pith.science/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYZTJNSR24LRSTQNZ27RE2BCJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YYZTJNSR24LRSTQNZ27RE2BCJT","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":"454da80736f99185d1171248c584b89c2d3d85901430645252a96c1de9ddfb87","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:34:04Z","title_canon_sha256":"4df3b5741e21d0105cb02f022e0f9e3c228dc1a7a56919524c0dd4c7c7beb2bc"},"schema_version":"1.0","source":{"id":"2506.05087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05087","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05087v1","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05087","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"pith_short_12","alias_value":"YYZTJNSR24LR","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"pith_short_16","alias_value":"YYZTJNSR24LRSTQN","created_at":"2026-07-05T11:16:42Z"},{"alias_kind":"pith_short_8","alias_value":"YYZTJNSR","created_at":"2026-07-05T11:16:42Z"}],"graph_snapshots":[{"event_id":"sha256:e29f6aa25ac77d5ca5c7bbecf06eadcde1f07e168f4e6d2486e1e32937e3d3a6","target":"graph","created_at":"2026-07-05T11:16:42Z","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/2506.05087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Haotian Lan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:34:04Z","title":"Interpretable Multimodal Framework for Human-Centered Street Assessment: Integrating Visual-Language Models for Perceptual Urban Diagnostics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05087","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:d5748708514b9ad476f2bfcdf43ee84b2a5ee814dd46c8f39d74bbefa0d7b856","target":"record","created_at":"2026-07-05T11:16:42Z","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":"454da80736f99185d1171248c584b89c2d3d85901430645252a96c1de9ddfb87","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T14:34:04Z","title_canon_sha256":"4df3b5741e21d0105cb02f022e0f9e3c228dc1a7a56919524c0dd4c7c7beb2bc"},"schema_version":"1.0","source":{"id":"2506.05087","kind":"arxiv","version":1}},"canonical_sha256":"c63334b651d717194e0dcebf1268224cec623ac8b466f0eb0f4d3105685bd6e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c63334b651d717194e0dcebf1268224cec623ac8b466f0eb0f4d3105685bd6e6","first_computed_at":"2026-07-05T11:16:42.014509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:42.014509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SVLRwhgGZb3IJBiBNX8FNNzKsD+ltsa3u3yVJeDpIlX46GzM9BypoLSYm7bWfJE8BViXkkT8L8SzxUzgrUoGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:42.015023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5748708514b9ad476f2bfcdf43ee84b2a5ee814dd46c8f39d74bbefa0d7b856","sha256:e29f6aa25ac77d5ca5c7bbecf06eadcde1f07e168f4e6d2486e1e32937e3d3a6"],"state_sha256":"3f5cadcaf570cd4b6aaa157aad859b39d2b99d8a24df097f04687eea2b26aebd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OC4t5HPwtd02iJleUVbcXxdjoBjew3DCfDRGHxzmf9ciALyEUokLCHQ81Q9arkhSs0N3g6ZyczzBbUSdhkkEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:09:30.375002Z","bundle_sha256":"20a7f0fd05b02759e19cb7a10886522a66127f278b36cd4bcf61f020ab532f7f"}}