{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IMJ27EZBNCRAKULOJVIHDKPMBS","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":"7a1a1c86744574fa44a48225d4a6c1ae7c2edb62c0fde18de5736ed32c7787e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T14:06:28Z","title_canon_sha256":"08525f0043e4f7de7a6762f53b02f986a002e1dc63ca72333fdf9ac7e6e5c2c6"},"schema_version":"1.0","source":{"id":"2508.10667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10667","created_at":"2026-07-05T11:54:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10667v1","created_at":"2026-07-05T11:54:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10667","created_at":"2026-07-05T11:54:00Z"},{"alias_kind":"pith_short_12","alias_value":"IMJ27EZBNCRA","created_at":"2026-07-05T11:54:00Z"},{"alias_kind":"pith_short_16","alias_value":"IMJ27EZBNCRAKULO","created_at":"2026-07-05T11:54:00Z"},{"alias_kind":"pith_short_8","alias_value":"IMJ27EZB","created_at":"2026-07-05T11:54:00Z"}],"graph_snapshots":[{"event_id":"sha256:8a4e93360071c6e4b3197391dd2a02cc9e7a406bf8f178ced5fe8f54e9aa7b43","target":"graph","created_at":"2026-07-05T11:54:00Z","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/2508.10667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large visual language models (LVLMs) have demonstrated impressive performance in coarse-grained geo-localization at the country or city level, but they struggle with fine-grained street-level localization within urban areas. In this paper, we explore integrating city-wide address localization capabilities into LVLMs, facilitating flexible address-related question answering using street-view images. A key challenge is that the street-view visual question-and-answer (VQA) data provides only microscopic visual cues, leading to subpar performance in fine-tuned models. To tackle this issue, we inco","authors_text":"Bin Fan, Chenghao Zhang, Gaofeng Meng, Jieping Ye, Lubin Fan, Shiming Xiang, Shixiong Xu, Yuan Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T14:06:28Z","title":"AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10667","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":"sha256:142525c6d277d15352e2502f30c1e7a2cd2920cbf2f7b2dcb5dd26cb96e9fd41","target":"record","created_at":"2026-07-05T11:54:00Z","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":"7a1a1c86744574fa44a48225d4a6c1ae7c2edb62c0fde18de5736ed32c7787e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T14:06:28Z","title_canon_sha256":"08525f0043e4f7de7a6762f53b02f986a002e1dc63ca72333fdf9ac7e6e5c2c6"},"schema_version":"1.0","source":{"id":"2508.10667","kind":"arxiv","version":1}},"canonical_sha256":"4313af932168a205516e4d5071a9ec0c815cb917a5bd90872bcd5fb6952c382f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4313af932168a205516e4d5071a9ec0c815cb917a5bd90872bcd5fb6952c382f","first_computed_at":"2026-07-05T11:54:00.576476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:00.576476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FOGl2CqJBlj8dcI0x8PeJX8j/m4R1eR1Mb6we7xKWAipHrAfNgJMY5OuEh9Mv/Hh6fseevL3ST8V9mNZ0qggAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:00.576948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:142525c6d277d15352e2502f30c1e7a2cd2920cbf2f7b2dcb5dd26cb96e9fd41","sha256:8a4e93360071c6e4b3197391dd2a02cc9e7a406bf8f178ced5fe8f54e9aa7b43"],"state_sha256":"6406e3060f94e54f462787451a7960caceaf71f856e3187a0da523fa3cf0f2dc"}