{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UX2BEFXE662WV7XGPKKBMMSE5Z","short_pith_number":"pith:UX2BEFXE","schema_version":"1.0","canonical_sha256":"a5f41216e4f7b56afee67a94163244ee4960ca8fe7959fa17d3dd6c49f9e5cf2","source":{"kind":"arxiv","id":"2512.21078","version":3},"attestation_state":"computed","paper":{"title":"UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danwei Wang, Hesheng Wang, Hongming Shen, Javier Civera, Shuhao Zhai, Tianchen Deng, Xun Chen, Ziming Li","submitted_at":"2025-12-24T09:55:16Z","abstract_excerpt":"Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to generalize across diverse environments. In this work we introduce UniPR-3D, the first VPR architecture that effectively integrates information from multiple views. UniPR-3D builds on a VGGT backbone capable of encoding multi-view 3D representations, which we adapt by designing feature aggregators and fine-tune for the place recognition task. To construct our descr"},"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":"2512.21078","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T09:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"a510e2245a5913583bfcd9537799253e05be15c35cde661f9d972d7d8e205291","abstract_canon_sha256":"903df64451426e20ae9e05c238ce500bebdd76080df70ea1cfd2affdb42edb83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:06.393093Z","signature_b64":"6PeYg+sl9p4eR0evVp60a2QFMH3+XsXOcdNGZiSdttd6tWfPe2GnHerudSsynruTyU3RhHx/aHZwojPD1QGVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5f41216e4f7b56afee67a94163244ee4960ca8fe7959fa17d3dd6c49f9e5cf2","last_reissued_at":"2026-06-30T02:18:06.392381Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:06.392381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danwei Wang, Hesheng Wang, Hongming Shen, Javier Civera, Shuhao Zhai, Tianchen Deng, Xun Chen, Ziming Li","submitted_at":"2025-12-24T09:55:16Z","abstract_excerpt":"Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to generalize across diverse environments. In this work we introduce UniPR-3D, the first VPR architecture that effectively integrates information from multiple views. UniPR-3D builds on a VGGT backbone capable of encoding multi-view 3D representations, which we adapt by designing feature aggregators and fine-tune for the place recognition task. To construct our descr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.21078","kind":"arxiv","version":3},"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/2512.21078/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":"2512.21078","created_at":"2026-06-30T02:18:06.392469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.21078v3","created_at":"2026-06-30T02:18:06.392469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.21078","created_at":"2026-06-30T02:18:06.392469+00:00"},{"alias_kind":"pith_short_12","alias_value":"UX2BEFXE662W","created_at":"2026-06-30T02:18:06.392469+00:00"},{"alias_kind":"pith_short_16","alias_value":"UX2BEFXE662WV7XG","created_at":"2026-06-30T02:18:06.392469+00:00"},{"alias_kind":"pith_short_8","alias_value":"UX2BEFXE","created_at":"2026-06-30T02:18:06.392469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.16911","citing_title":"VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14795","citing_title":"Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z","json":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z.json","graph_json":"https://pith.science/api/pith-number/UX2BEFXE662WV7XGPKKBMMSE5Z/graph.json","events_json":"https://pith.science/api/pith-number/UX2BEFXE662WV7XGPKKBMMSE5Z/events.json","paper":"https://pith.science/paper/UX2BEFXE"},"agent_actions":{"view_html":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z","download_json":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z.json","view_paper":"https://pith.science/paper/UX2BEFXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.21078&json=true","fetch_graph":"https://pith.science/api/pith-number/UX2BEFXE662WV7XGPKKBMMSE5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/UX2BEFXE662WV7XGPKKBMMSE5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z/action/storage_attestation","attest_author":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z/action/author_attestation","sign_citation":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z/action/citation_signature","submit_replication":"https://pith.science/pith/UX2BEFXE662WV7XGPKKBMMSE5Z/action/replication_record"}},"created_at":"2026-06-30T02:18:06.392469+00:00","updated_at":"2026-06-30T02:18:06.392469+00:00"}