{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IMJ27EZBNCRAKULOJVIHDKPMBS","short_pith_number":"pith:IMJ27EZB","schema_version":"1.0","canonical_sha256":"4313af932168a205516e4d5071a9ec0c815cb917a5bd90872bcd5fb6952c382f","source":{"kind":"arxiv","id":"2508.10667","version":1},"attestation_state":"computed","paper":{"title":"AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Fan, Chenghao Zhang, Gaofeng Meng, Jieping Ye, Lubin Fan, Shiming Xiang, Shixiong Xu, Yuan Zhou","submitted_at":"2025-08-14T14:06:28Z","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"},"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":"2508.10667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T14:06:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08525f0043e4f7de7a6762f53b02f986a002e1dc63ca72333fdf9ac7e6e5c2c6","abstract_canon_sha256":"7a1a1c86744574fa44a48225d4a6c1ae7c2edb62c0fde18de5736ed32c7787e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:00.576948Z","signature_b64":"FOGl2CqJBlj8dcI0x8PeJX8j/m4R1eR1Mb6we7xKWAipHrAfNgJMY5OuEh9Mv/Hh6fseevL3ST8V9mNZ0qggAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4313af932168a205516e4d5071a9ec0c815cb917a5bd90872bcd5fb6952c382f","last_reissued_at":"2026-07-05T11:54:00.576476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:00.576476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Fan, Chenghao Zhang, Gaofeng Meng, Jieping Ye, Lubin Fan, Shiming Xiang, Shixiong Xu, Yuan Zhou","submitted_at":"2025-08-14T14:06:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10667","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/2508.10667/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":"2508.10667","created_at":"2026-07-05T11:54:00.576534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10667v1","created_at":"2026-07-05T11:54:00.576534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10667","created_at":"2026-07-05T11:54:00.576534+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMJ27EZBNCRA","created_at":"2026-07-05T11:54:00.576534+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMJ27EZBNCRAKULO","created_at":"2026-07-05T11:54:00.576534+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMJ27EZB","created_at":"2026-07-05T11:54:00.576534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07292","citing_title":"CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS","json":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS.json","graph_json":"https://pith.science/api/pith-number/IMJ27EZBNCRAKULOJVIHDKPMBS/graph.json","events_json":"https://pith.science/api/pith-number/IMJ27EZBNCRAKULOJVIHDKPMBS/events.json","paper":"https://pith.science/paper/IMJ27EZB"},"agent_actions":{"view_html":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS","download_json":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS.json","view_paper":"https://pith.science/paper/IMJ27EZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10667&json=true","fetch_graph":"https://pith.science/api/pith-number/IMJ27EZBNCRAKULOJVIHDKPMBS/graph.json","fetch_events":"https://pith.science/api/pith-number/IMJ27EZBNCRAKULOJVIHDKPMBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS/action/storage_attestation","attest_author":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS/action/author_attestation","sign_citation":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS/action/citation_signature","submit_replication":"https://pith.science/pith/IMJ27EZBNCRAKULOJVIHDKPMBS/action/replication_record"}},"created_at":"2026-07-05T11:54:00.576534+00:00","updated_at":"2026-07-05T11:54:00.576534+00:00"}