{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KEOFAUGJ6CKHYKATBTPW7ZXOZR","short_pith_number":"pith:KEOFAUGJ","canonical_record":{"source":{"id":"2508.21565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T12:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"32eeeb2cce3924b2a1d62b8b7c3c7c105857d173319f55c48480c65e3f899f46","abstract_canon_sha256":"85c8f1a13232a1c16f178c46dfe1e169dc68585318ef65fd967afac602424c38"},"schema_version":"1.0"},"canonical_sha256":"511c5050c9f0947c28130cdf6fe6eecc49fc3690ce9dc31997a03c4fe0fcbb9c","source":{"kind":"arxiv","id":"2508.21565","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KEOFAUGJ6CKHYKATBTPW7ZXOZR","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T12:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"32eeeb2cce3924b2a1d62b8b7c3c7c105857d173319f55c48480c65e3f899f46","abstract_canon_sha256":"85c8f1a13232a1c16f178c46dfe1e169dc68585318ef65fd967afac602424c38"},"schema_version":"1.0"},"canonical_sha256":"511c5050c9f0947c28130cdf6fe6eecc49fc3690ce9dc31997a03c4fe0fcbb9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:36.919965Z","signature_b64":"TnVHzuGcVYC5YOaQXlmDnaswDewRsCxqoz0ollnx30r/Nzi8DqYGeuhP0qSTGQ9PRvBpogv0kixzXK73OSS9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"511c5050c9f0947c28130cdf6fe6eecc49fc3690ce9dc31997a03c4fe0fcbb9c","last_reissued_at":"2026-07-05T12:01:36.919482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:36.919482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21565","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":"2026-07-05T12:01:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0yBfZQi01cdVkjXApuq63Drwn2eQ3O5iKluEnTO/b6drBKIcGl8V/fgacNJ8ND+bmiyhdgKJhpLQ/JK1wqCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:13:53.057927Z"},"content_sha256":"e92f3acce44c1410f76a163ea356fde35c34c96569ed4b13b5375836593004ab","schema_version":"1.0","event_id":"sha256:e92f3acce44c1410f76a163ea356fde35c34c96569ed4b13b5375836593004ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KEOFAUGJ6CKHYKATBTPW7ZXOZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juneyoung Ro, Namwoo Kim, Yoonjin Yoon","submitted_at":"2025-08-29T12:21:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21565","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/2508.21565/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":"2026-07-05T12:01:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBr1cjBMDveUt/DDat0Qk0j5qu9Y58A9QjQRI8iDcJaM0UpIAchczK7cYitgCvWEqvTyQ5RJ65+bnNjPuKU/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:13:53.058823Z"},"content_sha256":"0cfef9b9853728b46db25f9719ceb25676998233e297721d80ab35d0eb51578b","schema_version":"1.0","event_id":"sha256:0cfef9b9853728b46db25f9719ceb25676998233e297721d80ab35d0eb51578b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KEOFAUGJ6CKHYKATBTPW7ZXOZR/bundle.json","state_url":"https://pith.science/pith/KEOFAUGJ6CKHYKATBTPW7ZXOZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KEOFAUGJ6CKHYKATBTPW7ZXOZR/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":"2026-08-18T21:13:53Z","links":{"resolver":"https://pith.science/pith/KEOFAUGJ6CKHYKATBTPW7ZXOZR","bundle":"https://pith.science/pith/KEOFAUGJ6CKHYKATBTPW7ZXOZR/bundle.json","state":"https://pith.science/pith/KEOFAUGJ6CKHYKATBTPW7ZXOZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KEOFAUGJ6CKHYKATBTPW7ZXOZR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ESqAHci7lSb504iso69H5HDkGtOrG2bazZyB2DoZirQ2ZWoHXbX/WW07l38FxBlRsJldmuPnFkMB8EW272UgBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:13:53.063145Z","bundle_sha256":"411d3612605f772f3569af5942a45f29eb35fbf1a8148205dff85612232c45eb"}}