{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NK7BLAV2TV7LUJ52EAU3OMVW2X","short_pith_number":"pith:NK7BLAV2","schema_version":"1.0","canonical_sha256":"6abe1582ba9d7eba27ba2029b732b6d5e1072435d986163f3a2137a9b96bcdeb","source":{"kind":"arxiv","id":"2412.12079","version":1},"attestation_state":"computed","paper":{"title":"UniLoc: Towards Universal Place Recognition Using Any Single Modality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, Hu Cao, Jo\\~ao F. Henriques, Letian Shi, Yan Xia, Yun-Jin Li, Zhendong Li","submitted_at":"2024-12-16T18:48:58Z","abstract_excerpt":"To date, most place recognition methods focus on single-modality retrieval. While they perform well in specific environments, cross-modal methods offer greater flexibility by allowing seamless switching between map and query sources. It also promises to reduce computation requirements by having a unified model, and achieving greater sample efficiency by sharing parameters. In this work, we develop a universal solution to place recognition, UniLoc, that works with any single query modality (natural language, image, or point cloud). UniLoc leverages recent advances in large-scale contrastive lea"},"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":"2412.12079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T18:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"d39b65dcd2d2469a33fd5d9d779a71b19fb6bd10f7c6d14ca212ba26d410f508","abstract_canon_sha256":"4ace7cafb22c7b4a3a751ba27597630913dddfbaafb457550eb7d4c330f94101"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:56.319835Z","signature_b64":"GNPBTVZNBYmsW2D9i0PKCPGH/mcTTozzUQBIPoXUfyCAeNMOqvluvWg1RXtJJNcnubKfscyyJ4TuBBzBEwU/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6abe1582ba9d7eba27ba2029b732b6d5e1072435d986163f3a2137a9b96bcdeb","last_reissued_at":"2026-07-05T09:49:56.319288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:56.319288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniLoc: Towards Universal Place Recognition Using Any Single Modality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, Hu Cao, Jo\\~ao F. Henriques, Letian Shi, Yan Xia, Yun-Jin Li, Zhendong Li","submitted_at":"2024-12-16T18:48:58Z","abstract_excerpt":"To date, most place recognition methods focus on single-modality retrieval. While they perform well in specific environments, cross-modal methods offer greater flexibility by allowing seamless switching between map and query sources. It also promises to reduce computation requirements by having a unified model, and achieving greater sample efficiency by sharing parameters. In this work, we develop a universal solution to place recognition, UniLoc, that works with any single query modality (natural language, image, or point cloud). UniLoc leverages recent advances in large-scale contrastive lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12079","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/2412.12079/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":"2412.12079","created_at":"2026-07-05T09:49:56.319361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12079v1","created_at":"2026-07-05T09:49:56.319361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12079","created_at":"2026-07-05T09:49:56.319361+00:00"},{"alias_kind":"pith_short_12","alias_value":"NK7BLAV2TV7L","created_at":"2026-07-05T09:49:56.319361+00:00"},{"alias_kind":"pith_short_16","alias_value":"NK7BLAV2TV7LUJ52","created_at":"2026-07-05T09:49:56.319361+00:00"},{"alias_kind":"pith_short_8","alias_value":"NK7BLAV2","created_at":"2026-07-05T09:49:56.319361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09418","citing_title":"MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognition","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X","json":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X.json","graph_json":"https://pith.science/api/pith-number/NK7BLAV2TV7LUJ52EAU3OMVW2X/graph.json","events_json":"https://pith.science/api/pith-number/NK7BLAV2TV7LUJ52EAU3OMVW2X/events.json","paper":"https://pith.science/paper/NK7BLAV2"},"agent_actions":{"view_html":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X","download_json":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X.json","view_paper":"https://pith.science/paper/NK7BLAV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12079&json=true","fetch_graph":"https://pith.science/api/pith-number/NK7BLAV2TV7LUJ52EAU3OMVW2X/graph.json","fetch_events":"https://pith.science/api/pith-number/NK7BLAV2TV7LUJ52EAU3OMVW2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X/action/storage_attestation","attest_author":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X/action/author_attestation","sign_citation":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X/action/citation_signature","submit_replication":"https://pith.science/pith/NK7BLAV2TV7LUJ52EAU3OMVW2X/action/replication_record"}},"created_at":"2026-07-05T09:49:56.319361+00:00","updated_at":"2026-07-05T09:49:56.319361+00:00"}