{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:II2427KEXDTKFYLWU4N4Q5P22L","short_pith_number":"pith:II2427KE","schema_version":"1.0","canonical_sha256":"4235cd7d44b8e6a2e176a71bc875fad2f74dafba4dd1684e3af9a5eeb9fd105c","source":{"kind":"arxiv","id":"2605.26381","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Building Inspection via Perceiver IO Fusion of Satellite and Street-Level Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Martin R. Oswald, Niels Sombekke, Rob G.J. Wijnhoven","submitted_at":"2026-05-25T23:01:05Z","abstract_excerpt":"We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial patch tokens from a shared DINOv2 backbone. The design naturally handles a variable number of street-level views per building without padding or fixed-size pooling, and jointly predicts multi-label roof element and roof material classes. We construct a large-scale dataset of 32,135 buildings (61,672 segments) spanning ten countries, pairing satellite images with up to eight street-level views per segment and evaluating four masking strategies "},"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":"2605.26381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T23:01:05Z","cross_cats_sorted":[],"title_canon_sha256":"047c9682c9eb613761cb615b102a14b9b7f55686be15ce57aa743c76cf2253bf","abstract_canon_sha256":"e4f0bbb41664cf2dfc63d99e6e31ab9286b0e98ea44313d7ea37f670b30f8677"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:15.133599Z","signature_b64":"5dfhq7wsCF5GQcGbKuLBVXQHNPxxFLFi2wokH3P+UJTvE+Ewui3z2oWpWuNEaJeqlGBiJs2oyLp+dnYZKLoBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4235cd7d44b8e6a2e176a71bc875fad2f74dafba4dd1684e3af9a5eeb9fd105c","last_reissued_at":"2026-05-27T01:05:15.132852Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:15.132852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Building Inspection via Perceiver IO Fusion of Satellite and Street-Level Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Martin R. Oswald, Niels Sombekke, Rob G.J. Wijnhoven","submitted_at":"2026-05-25T23:01:05Z","abstract_excerpt":"We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial patch tokens from a shared DINOv2 backbone. The design naturally handles a variable number of street-level views per building without padding or fixed-size pooling, and jointly predicts multi-label roof element and roof material classes. We construct a large-scale dataset of 32,135 buildings (61,672 segments) spanning ten countries, pairing satellite images with up to eight street-level views per segment and evaluating four masking strategies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26381","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/2605.26381/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":"2605.26381","created_at":"2026-05-27T01:05:15.132977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26381v1","created_at":"2026-05-27T01:05:15.132977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26381","created_at":"2026-05-27T01:05:15.132977+00:00"},{"alias_kind":"pith_short_12","alias_value":"II2427KEXDTK","created_at":"2026-05-27T01:05:15.132977+00:00"},{"alias_kind":"pith_short_16","alias_value":"II2427KEXDTKFYLW","created_at":"2026-05-27T01:05:15.132977+00:00"},{"alias_kind":"pith_short_8","alias_value":"II2427KE","created_at":"2026-05-27T01:05:15.132977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L","json":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L.json","graph_json":"https://pith.science/api/pith-number/II2427KEXDTKFYLWU4N4Q5P22L/graph.json","events_json":"https://pith.science/api/pith-number/II2427KEXDTKFYLWU4N4Q5P22L/events.json","paper":"https://pith.science/paper/II2427KE"},"agent_actions":{"view_html":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L","download_json":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L.json","view_paper":"https://pith.science/paper/II2427KE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26381&json=true","fetch_graph":"https://pith.science/api/pith-number/II2427KEXDTKFYLWU4N4Q5P22L/graph.json","fetch_events":"https://pith.science/api/pith-number/II2427KEXDTKFYLWU4N4Q5P22L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L/action/storage_attestation","attest_author":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L/action/author_attestation","sign_citation":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L/action/citation_signature","submit_replication":"https://pith.science/pith/II2427KEXDTKFYLWU4N4Q5P22L/action/replication_record"}},"created_at":"2026-05-27T01:05:15.132977+00:00","updated_at":"2026-05-27T01:05:15.132977+00:00"}