{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MDHM4CNNW36TNV3YAAYKL7ZQ4A","short_pith_number":"pith:MDHM4CNN","schema_version":"1.0","canonical_sha256":"60cece09adb6fd36d7780030a5ff30e01edce490adb614796562eb5419c631ea","source":{"kind":"arxiv","id":"2605.16768","version":1},"attestation_state":"computed","paper":{"title":"Axial-Relation Guided Fusion State Space Model for Optical-Elevation Sensing Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ARG-Mamba fuses optical and elevation features along axial relations within a state space model to improve remote sensing segmentation accuracy.","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Feng Gao, Junyu Dong, Qian Du, Yanhai Gan, Zhilin Jin","submitted_at":"2026-05-16T02:42:54Z","abstract_excerpt":"Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependen"},"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":true},"canonical_record":{"source":{"id":"2605.16768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T02:42:54Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"e1aa8f9f281ad7293a33508405542aceb392dd54399bc778965eb0cdbdc47708","abstract_canon_sha256":"546a259ca469f2aa3409c5a120aab231c890243fcccc4541d9694d3953308e99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:20.938457Z","signature_b64":"WWLGD0kuPYHBp4jjlsMLtD6nSjBonW7pcmjECEghTyBXBG4LU0MtYXAotnLBf1I8Q8BJaKpCpcQkaPhKRKseBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60cece09adb6fd36d7780030a5ff30e01edce490adb614796562eb5419c631ea","last_reissued_at":"2026-05-20T00:03:20.937477Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:20.937477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Axial-Relation Guided Fusion State Space Model for Optical-Elevation Sensing Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ARG-Mamba fuses optical and elevation features along axial relations within a state space model to improve remote sensing segmentation accuracy.","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Feng Gao, Junyu Dong, Qian Du, Yanhai Gan, Zhilin Jin","submitted_at":"2026-05-16T02:42:54Z","abstract_excerpt":"Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency on the ISPRS Vaihingen and Potsdam datasets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that explicitly modeling global cross-modal correlations along horizontal and vertical axes via the Axial-Relation Guided Fusion Module yields superior feature fusion compared with existing cross-modal methods, as described in the module design.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ARG-Mamba combines a multi-scale state space module and an axial-relation guided fusion module to outperform prior methods on optical-elevation semantic segmentation for remote sensing.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ARG-Mamba fuses optical and elevation features along axial relations within a state space model to improve remote sensing segmentation accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4f2b4dcf10b55af4e615e775d1a0d40e5acc917bff30d98073da446d366f6ea5"},"source":{"id":"2605.16768","kind":"arxiv","version":1},"verdict":{"id":"dcef637d-bfba-4844-a14c-cc590b2d5889","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:11:11.145762Z","strongest_claim":"ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency on the ISPRS Vaihingen and Potsdam datasets.","one_line_summary":"ARG-Mamba combines a multi-scale state space module and an axial-relation guided fusion module to outperform prior methods on optical-elevation semantic segmentation for remote sensing.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that explicitly modeling global cross-modal correlations along horizontal and vertical axes via the Axial-Relation Guided Fusion Module yields superior feature fusion compared with existing cross-modal methods, as described in the module design.","pith_extraction_headline":"ARG-Mamba fuses optical and elevation features along axial relations within a state space model to improve remote sensing segmentation accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16768/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.356537Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:21:23.895819Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.312857Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.446546Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"eeec59668cffed740ee6eab14099e2554ff769a4a1eac4c781ca5bf3a500fa3c"},"references":{"count":16,"sample":[{"doi":"","year":2019,"title":"Deep learning in remote sensing applications: A meta-analysis and review,","work_id":"043e2a1b-995e-46ae-8ddb-72923c5b40a2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Adaptive frequency enhancement network for remote sensing image semantic segmentation,","work_id":"5c6c312a-c69d-44b2-9490-10e7b88b1410","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Elevation information- guided multimodal fusion robust framework for remote sensing image segmentation,","work_id":"58710bab-7a10-478b-87c3-22906bea35bb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A multilevel multimodal fusion Transformer for remote sensing semantic segmentation,","work_id":"4c7051f1-645e-4455-b471-9c489e16c8a0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"A multisensor data fusion model for semantic segmentation in aerial images,","work_id":"58806e15-c22e-4d1c-9a7d-00c6fbc9e681","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":16,"snapshot_sha256":"ffd657ed6bf1093eb2ec7f897dd314e98ec69266f0aaa5a1f1363b2c95b0c2ff","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b6c766b83f98a355155d30dbe977afcfe83b1431065d93ca1265282b2969d0d4"},"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":"2605.16768","created_at":"2026-05-20T00:03:20.937650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16768v1","created_at":"2026-05-20T00:03:20.937650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16768","created_at":"2026-05-20T00:03:20.937650+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDHM4CNNW36T","created_at":"2026-05-20T00:03:20.937650+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDHM4CNNW36TNV3Y","created_at":"2026-05-20T00:03:20.937650+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDHM4CNN","created_at":"2026-05-20T00:03:20.937650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A","json":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A.json","graph_json":"https://pith.science/api/pith-number/MDHM4CNNW36TNV3YAAYKL7ZQ4A/graph.json","events_json":"https://pith.science/api/pith-number/MDHM4CNNW36TNV3YAAYKL7ZQ4A/events.json","paper":"https://pith.science/paper/MDHM4CNN"},"agent_actions":{"view_html":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A","download_json":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A.json","view_paper":"https://pith.science/paper/MDHM4CNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16768&json=true","fetch_graph":"https://pith.science/api/pith-number/MDHM4CNNW36TNV3YAAYKL7ZQ4A/graph.json","fetch_events":"https://pith.science/api/pith-number/MDHM4CNNW36TNV3YAAYKL7ZQ4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A/action/storage_attestation","attest_author":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A/action/author_attestation","sign_citation":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A/action/citation_signature","submit_replication":"https://pith.science/pith/MDHM4CNNW36TNV3YAAYKL7ZQ4A/action/replication_record"}},"created_at":"2026-05-20T00:03:20.937650+00:00","updated_at":"2026-05-20T00:03:20.937650+00:00"}