{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KE6S7DZTVQRXT6HW3FERQXCFUC","short_pith_number":"pith:KE6S7DZT","schema_version":"1.0","canonical_sha256":"513d2f8f33ac2379f8f6d949185c45a0a4e566f8f4f3d842e0ffec916ba2d889","source":{"kind":"arxiv","id":"2508.18971","version":1},"attestation_state":"computed","paper":{"title":"Can we make NeRF-based visual localization privacy-preserving?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gabriela Csurka, Martin Humenberger, Maxime Pietrantoni, Torsten Sattler","submitted_at":"2025-08-26T12:17:00Z","abstract_excerpt":"Visual localization (VL) is the task of estimating the camera pose in a known scene. VL methods, a.o., can be distinguished based on how they represent the scene, e.g., explicitly through a (sparse) point cloud or a collection of images or implicitly through the weights of a neural network. Recently, NeRF-based methods have become popular for VL. While NeRFs offer high-quality novel view synthesis, they inadvertently encode fine scene details, raising privacy concerns when deployed in cloud-based localization services as sensitive information could be recovered. In this paper, we tackle this c"},"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":"2508.18971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T12:17:00Z","cross_cats_sorted":[],"title_canon_sha256":"ed148b4cc188e3a8932fe0b89b7b23caa50ed4fa7e9987bac0a6a9fb646be3db","abstract_canon_sha256":"71b506a46e2952da718ab4e60a0c485ca0b000e14f24f202ba1df4e36c30398e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:34.775122Z","signature_b64":"6SirlxyYU5HabhWYiSKDlwKZxQTaUFRXrmyAXFdwCjCUDS22C8iC5cURxY1lezu028a0C9GGlzRRXjaei862Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"513d2f8f33ac2379f8f6d949185c45a0a4e566f8f4f3d842e0ffec916ba2d889","last_reissued_at":"2026-07-05T11:59:34.774650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:34.774650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can we make NeRF-based visual localization privacy-preserving?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gabriela Csurka, Martin Humenberger, Maxime Pietrantoni, Torsten Sattler","submitted_at":"2025-08-26T12:17:00Z","abstract_excerpt":"Visual localization (VL) is the task of estimating the camera pose in a known scene. VL methods, a.o., can be distinguished based on how they represent the scene, e.g., explicitly through a (sparse) point cloud or a collection of images or implicitly through the weights of a neural network. Recently, NeRF-based methods have become popular for VL. While NeRFs offer high-quality novel view synthesis, they inadvertently encode fine scene details, raising privacy concerns when deployed in cloud-based localization services as sensitive information could be recovered. In this paper, we tackle this c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18971","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/2508.18971/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":"2508.18971","created_at":"2026-07-05T11:59:34.774711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18971v1","created_at":"2026-07-05T11:59:34.774711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18971","created_at":"2026-07-05T11:59:34.774711+00:00"},{"alias_kind":"pith_short_12","alias_value":"KE6S7DZTVQRX","created_at":"2026-07-05T11:59:34.774711+00:00"},{"alias_kind":"pith_short_16","alias_value":"KE6S7DZTVQRXT6HW","created_at":"2026-07-05T11:59:34.774711+00:00"},{"alias_kind":"pith_short_8","alias_value":"KE6S7DZT","created_at":"2026-07-05T11:59:34.774711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02486","citing_title":"GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31164","citing_title":"Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC","json":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC.json","graph_json":"https://pith.science/api/pith-number/KE6S7DZTVQRXT6HW3FERQXCFUC/graph.json","events_json":"https://pith.science/api/pith-number/KE6S7DZTVQRXT6HW3FERQXCFUC/events.json","paper":"https://pith.science/paper/KE6S7DZT"},"agent_actions":{"view_html":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC","download_json":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC.json","view_paper":"https://pith.science/paper/KE6S7DZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18971&json=true","fetch_graph":"https://pith.science/api/pith-number/KE6S7DZTVQRXT6HW3FERQXCFUC/graph.json","fetch_events":"https://pith.science/api/pith-number/KE6S7DZTVQRXT6HW3FERQXCFUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC/action/storage_attestation","attest_author":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC/action/author_attestation","sign_citation":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC/action/citation_signature","submit_replication":"https://pith.science/pith/KE6S7DZTVQRXT6HW3FERQXCFUC/action/replication_record"}},"created_at":"2026-07-05T11:59:34.774711+00:00","updated_at":"2026-07-05T11:59:34.774711+00:00"}