{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CZTPKA6U5SUWBVHHEY3AY2EAXY","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":"82f5ca7c6ffb96b7123e73c0aee5618eb03af9d2562d8fe0056a73f45bde0357","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T03:31:30Z","title_canon_sha256":"4ba1572ab95a61de93df371da7d868970207422cc029fc598f5783be032678db"},"schema_version":"1.0","source":{"id":"2408.11312","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11312","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11312v3","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11312","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"CZTPKA6U5SUW","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"pith_short_16","alias_value":"CZTPKA6U5SUWBVHH","created_at":"2026-07-05T09:20:47Z"},{"alias_kind":"pith_short_8","alias_value":"CZTPKA6U","created_at":"2026-07-05T09:20:47Z"}],"graph_snapshots":[{"event_id":"sha256:42fffce987ff0eb6d3807ee1352abc6841fb9dce05b68a16517963bc98f9ef19","target":"graph","created_at":"2026-07-05T09:20:47Z","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/2408.11312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual geo-localization demands in-depth knowledge and advanced reasoning skills to associate images with precise real-world geographic locations. Existing image database retrieval methods are limited by the impracticality of storing sufficient visual records of global landmarks. Recently, Large Vision-Language Models (LVLMs) have demonstrated the capability of geo-localization through Visual Question Answering (VQA), enabling a solution that does not require external geo-tagged image records. However, the performance of a single LVLM is still limited by its intrinsic knowledge and reasoning c","authors_text":"Chen Zhu, Hengshu Zhu, Xiangyu Zhao, Xiao Han","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T03:31:30Z","title":"Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11312","kind":"arxiv","version":3},"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:bf2dd19081a1bc93455121d15492a3e9e23bffd35edd67cae293501dd487a0aa","target":"record","created_at":"2026-07-05T09:20:47Z","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":"82f5ca7c6ffb96b7123e73c0aee5618eb03af9d2562d8fe0056a73f45bde0357","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T03:31:30Z","title_canon_sha256":"4ba1572ab95a61de93df371da7d868970207422cc029fc598f5783be032678db"},"schema_version":"1.0","source":{"id":"2408.11312","kind":"arxiv","version":3}},"canonical_sha256":"1666f503d4eca960d4e726360c6880be2c32d204635943987faa8de6dc6688fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1666f503d4eca960d4e726360c6880be2c32d204635943987faa8de6dc6688fd","first_computed_at":"2026-07-05T09:20:47.111454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:47.111454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9M+zSSrsEAvC3je/3x+cvmDSkuUlkRyZ2jy46a1Tg8AYZnneANRiYK1/+vOhBSiL1s8Hd19RGuG2OwZtsNB+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:47.111969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11312","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf2dd19081a1bc93455121d15492a3e9e23bffd35edd67cae293501dd487a0aa","sha256:42fffce987ff0eb6d3807ee1352abc6841fb9dce05b68a16517963bc98f9ef19"],"state_sha256":"64e230c326baa5189455ff9349e30fbad0c5c5a37fd66eb2467cfa4506f5541e"}