{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZTY6PAS3Q3YG3T24OXJC6YN6HT","short_pith_number":"pith:ZTY6PAS3","schema_version":"1.0","canonical_sha256":"ccf1e7825b86f06dcf5c75d22f61be3cd071df0a530b8b11568017766e7d3e82","source":{"kind":"arxiv","id":"2605.14239","version":1},"attestation_state":"computed","paper":{"title":"Implicit spatial-frequency fusion of hyperspectral and lidar data via kolmogorov-arnold networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Kolmogorov-Arnold Networks with learnable splines and LiDAR-guided modules improve hyperspectral-LiDAR fusion accuracy.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Zia, Guanyiman Fu, Jing Wang, Judy X. Yang, Jun Zhou, Zekun Long","submitted_at":"2026-05-14T01:12:12Z","abstract_excerpt":"Hyperspectral image (HSI) classification is challenging in complex scenes due to spectral ambiguity, spatial heterogeneity, and the strong coupling between material properties and geometric structures. Although LiDAR provides complementary elevation information, most HSI-LiDAR fusion methods rely on CNNs or MLPs with fixed activation functions and linear weights. These methods struggle to model structural discontinuities in LiDAR data, intricate spectral features of HSI, and their interactions. In addition, fusion of the two modalities in both spatial and frequency domains with LiDAR guidance "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T01:12:12Z","cross_cats_sorted":[],"title_canon_sha256":"00221b883e97e99c3105b83daf0a3ed54afb107765ba771a55b5d83e0ee46666","abstract_canon_sha256":"67dfed2ba60f99d116c59032acddd63a1384a48a878ac67c03c92dcfa2d1a941"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.668334Z","signature_b64":"hVF8HoK5Y8a+2oBgh8jABVKsB9+KceVaDf9oJPxpQTH99wc/34ahXUT0c3VoslQ7lZfWrJkyKVd8x2PyWfAiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccf1e7825b86f06dcf5c75d22f61be3cd071df0a530b8b11568017766e7d3e82","last_reissued_at":"2026-05-17T23:39:10.667876Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.667876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit spatial-frequency fusion of hyperspectral and lidar data via kolmogorov-arnold networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Kolmogorov-Arnold Networks with learnable splines and LiDAR-guided modules improve hyperspectral-LiDAR fusion accuracy.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Zia, Guanyiman Fu, Jing Wang, Judy X. Yang, Jun Zhou, Zekun Long","submitted_at":"2026-05-14T01:12:12Z","abstract_excerpt":"Hyperspectral image (HSI) classification is challenging in complex scenes due to spectral ambiguity, spatial heterogeneity, and the strong coupling between material properties and geometric structures. Although LiDAR provides complementary elevation information, most HSI-LiDAR fusion methods rely on CNNs or MLPs with fixed activation functions and linear weights. These methods struggle to model structural discontinuities in LiDAR data, intricate spectral features of HSI, and their interactions. In addition, fusion of the two modalities in both spatial and frequency domains with LiDAR guidance "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the Houston 2013 and MUUFL benchmarks demonstrate that IFGNet consistently outperforms existing fusion methods in overall accuracy, average accuracy, and Cohen's Kappa, while maintaining an efficient architecture.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the learnable spline functions inside the KAN layers, together with the LiDAR-guided implicit aggregation modules, are the primary drivers of the observed accuracy gains rather than differences in training protocol, data augmentation, or hyper-parameter tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"IFGNet replaces fixed activations with KAN splines and adds LiDAR-guided implicit aggregation in spatial and frequency domains, reporting higher overall accuracy, average accuracy, and Kappa than prior fusion methods on the Houston 2013 and MUUFL benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Kolmogorov-Arnold Networks with learnable splines and LiDAR-guided modules improve hyperspectral-LiDAR fusion accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8bac473c5dc27a188504e82a38b6257cf573ec503e7ebe47f8d12480c08cf50d"},"source":{"id":"2605.14239","kind":"arxiv","version":1},"verdict":{"id":"96e85a08-042e-426e-9fe7-bce796a328ce","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:36:23.953307Z","strongest_claim":"Experiments on the Houston 2013 and MUUFL benchmarks demonstrate that IFGNet consistently outperforms existing fusion methods in overall accuracy, average accuracy, and Cohen's Kappa, while maintaining an efficient architecture.","one_line_summary":"IFGNet replaces fixed activations with KAN splines and adds LiDAR-guided implicit aggregation in spatial and frequency domains, reporting higher overall accuracy, average accuracy, and Kappa than prior fusion methods on the Houston 2013 and MUUFL benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the learnable spline functions inside the KAN layers, together with the LiDAR-guided implicit aggregation modules, are the primary drivers of the observed accuracy gains rather than differences in training protocol, data augmentation, or hyper-parameter tuning.","pith_extraction_headline":"Kolmogorov-Arnold Networks with learnable splines and LiDAR-guided modules improve hyperspectral-LiDAR fusion accuracy."},"references":{"count":23,"sample":[{"doi":"","year":2005,"title":"Clas- sification of hyperspectral data from urban areas based on extended morphological profiles,","work_id":"03225d1f-24b2-4d93-b7a1-45173d26b8c3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"A novel deep learning framework by combination of subspace- based feature extraction and convolutional neural net- works for hyperspectral images classification,","work_id":"f2d76e12-3e87-454a-b7bd-15da14fbb53f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Deep learning for land use and land cover classification based on hyperspectral and multispectral earth observation data: A review,","work_id":"7723d047-b664-4a33-ae2b-9f5ddc8993a9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Hyperspectral image analysis. a tutorial,","work_id":"2fff3b0b-e7ae-4d2e-aaa9-978c4b7ba2da","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Deep learning for hyperspectral image classification: An overview,","work_id":"9c519d26-6f76-400a-a9df-c0581ce5e303","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"ccf5214903e2460cd1d8ee63bffba078b3bc246004545b730173d4aa853a4322","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":"2605.14239","created_at":"2026-05-17T23:39:10.667937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14239v1","created_at":"2026-05-17T23:39:10.667937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14239","created_at":"2026-05-17T23:39:10.667937+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTY6PAS3Q3YG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTY6PAS3Q3YG3T24","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTY6PAS3","created_at":"2026-05-18T12:33:37.589309+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/ZTY6PAS3Q3YG3T24OXJC6YN6HT","json":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT.json","graph_json":"https://pith.science/api/pith-number/ZTY6PAS3Q3YG3T24OXJC6YN6HT/graph.json","events_json":"https://pith.science/api/pith-number/ZTY6PAS3Q3YG3T24OXJC6YN6HT/events.json","paper":"https://pith.science/paper/ZTY6PAS3"},"agent_actions":{"view_html":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT","download_json":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT.json","view_paper":"https://pith.science/paper/ZTY6PAS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14239&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTY6PAS3Q3YG3T24OXJC6YN6HT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTY6PAS3Q3YG3T24OXJC6YN6HT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT/action/storage_attestation","attest_author":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT/action/author_attestation","sign_citation":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT/action/citation_signature","submit_replication":"https://pith.science/pith/ZTY6PAS3Q3YG3T24OXJC6YN6HT/action/replication_record"}},"created_at":"2026-05-17T23:39:10.667937+00:00","updated_at":"2026-05-17T23:39:10.667937+00:00"}