{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KEOFAUGJ6CKHYKATBTPW7ZXOZR","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":"85c8f1a13232a1c16f178c46dfe1e169dc68585318ef65fd967afac602424c38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T12:21:57Z","title_canon_sha256":"32eeeb2cce3924b2a1d62b8b7c3c7c105857d173319f55c48480c65e3f899f46"},"schema_version":"1.0","source":{"id":"2508.21565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21565","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21565v1","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21565","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"pith_short_12","alias_value":"KEOFAUGJ6CKH","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"pith_short_16","alias_value":"KEOFAUGJ6CKHYKAT","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"pith_short_8","alias_value":"KEOFAUGJ","created_at":"2026-07-05T12:01:36Z"}],"graph_snapshots":[{"event_id":"sha256:0cfef9b9853728b46db25f9719ceb25676998233e297721d80ab35d0eb51578b","target":"graph","created_at":"2026-07-05T12:01:36Z","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/2508.21565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban domain remains underexplored. To address this gap, we conduct a comparative study of three off-the-shelf VLMs-BLIP-2, InstructBLIP, and LLaVA-1.5-evaluating both zero-shot performance and the effects of fine-tuning with a synthetic VQA dataset specific to urban scenes. We construct such dataset from segmentation, depth, and object detection predictions of st","authors_text":"Juneyoung Ro, Namwoo Kim, Yoonjin Yoon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T12:21:57Z","title":"How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21565","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:e92f3acce44c1410f76a163ea356fde35c34c96569ed4b13b5375836593004ab","target":"record","created_at":"2026-07-05T12:01:36Z","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":"85c8f1a13232a1c16f178c46dfe1e169dc68585318ef65fd967afac602424c38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T12:21:57Z","title_canon_sha256":"32eeeb2cce3924b2a1d62b8b7c3c7c105857d173319f55c48480c65e3f899f46"},"schema_version":"1.0","source":{"id":"2508.21565","kind":"arxiv","version":1}},"canonical_sha256":"511c5050c9f0947c28130cdf6fe6eecc49fc3690ce9dc31997a03c4fe0fcbb9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"511c5050c9f0947c28130cdf6fe6eecc49fc3690ce9dc31997a03c4fe0fcbb9c","first_computed_at":"2026-07-05T12:01:36.919482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:36.919482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TnVHzuGcVYC5YOaQXlmDnaswDewRsCxqoz0ollnx30r/Nzi8DqYGeuhP0qSTGQ9PRvBpogv0kixzXK73OSS9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:36.919965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e92f3acce44c1410f76a163ea356fde35c34c96569ed4b13b5375836593004ab","sha256:0cfef9b9853728b46db25f9719ceb25676998233e297721d80ab35d0eb51578b"],"state_sha256":"9f58ff55db92382b4cbd57e0a814002333857f334dbc2973e3400ba0c649e110"}