{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2CPJNUDTIXSMFD4X25P6TL5PKO","short_pith_number":"pith:2CPJNUDT","canonical_record":{"source":{"id":"2605.13581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:14:13Z","cross_cats_sorted":[],"title_canon_sha256":"d0a02f4169f49481437d30264f936993e8ba2cf008990609f039ce3faead1c06","abstract_canon_sha256":"3b4ca972485c694eaeb37ff1120152fd8d394b548298b00d2137319cf4dcab1b"},"schema_version":"1.0"},"canonical_sha256":"d09e96d07345e4c28f97d75fe9afaf538cad2b6c3c1c15247706d12f01fc62bd","source":{"kind":"arxiv","id":"2605.13581","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13581","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13581v1","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13581","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"2CPJNUDTIXSM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2CPJNUDTIXSMFD4X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2CPJNUDT","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2CPJNUDTIXSMFD4X25P6TL5PKO","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:14:13Z","cross_cats_sorted":[],"title_canon_sha256":"d0a02f4169f49481437d30264f936993e8ba2cf008990609f039ce3faead1c06","abstract_canon_sha256":"3b4ca972485c694eaeb37ff1120152fd8d394b548298b00d2137319cf4dcab1b"},"schema_version":"1.0"},"canonical_sha256":"d09e96d07345e4c28f97d75fe9afaf538cad2b6c3c1c15247706d12f01fc62bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:23.232138Z","signature_b64":"fv7AwXtOi9B7m3ZcVYtpULA1JD/jVDxJI62kg3YKJ4U+6V3za+EJ9/JJJy1aTg9rtSktNlAh2fyrWyblzbB7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d09e96d07345e4c28f97d75fe9afaf538cad2b6c3c1c15247706d12f01fc62bd","last_reissued_at":"2026-05-18T02:44:23.231656Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:23.231656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13581","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f3Ed7oLL1RHNu4u/qMTr7ibj3BNJnZM7pwzqeqvgDaqnENeNpioqRn0ddyy6HNSi4V4zsEUjmtLox3n2FuN8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:02:49.821267Z"},"content_sha256":"4bfaca1114078b0bd4be998db8f4326904be765b85d6fca717b52dd97651bf6f","schema_version":"1.0","event_id":"sha256:4bfaca1114078b0bd4be998db8f4326904be765b85d6fca717b52dd97651bf6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2CPJNUDTIXSMFD4X25P6TL5PKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Diffusion-generated synthetic HSIs allow finetuning of restoration models to match target domains without clean references","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyu Meng, Heng Zhao, Li Pang, Xiangyong Cao, Yijia Zhang","submitted_at":"2026-05-13T14:14:13Z","abstract_excerpt":"Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real HSIs suffer from degradations like noise, blur, and resolution loss. However, existing models trained on source data often fail on target domains lacking clean references, a common occurrence in practice. To address this issue, we present HIR-ALIGN, a plug-and-play target-adaptive augmentation framework that enhances hyperspectral image restoration by augmenting limited training images with synthetic data that closely matches the target distribution using no extra data. It consists of three stages: (i) proxy genera"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"augmentation-based finetuning can achieve lower target-domain restoration risk by jointly improving target distribution coverage and controlling spectral bias","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The proxy HSIs produced by off-the-shelf restoration models are semantics-preserving approximations of clean target-domain images, and the diffusion-generated RGBs can be accurately aligned to proxies via warp-based spectral transfer without introducing new biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HIR-ALIGN augments limited target data for hyperspectral restoration by creating proxy clean images, synthesizing aligned HSIs with blur-robust diffusion and warp-based transfer, then finetuning models to lower target-domain risk.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Diffusion-generated synthetic HSIs allow finetuning of restoration models to match target domains without clean references","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fd05fcf05e2aa4e02075e7afd23bbbf0aaf3f409f04c7faf7c00de328b3a86d4"},"source":{"id":"2605.13581","kind":"arxiv","version":1},"verdict":{"id":"c93ee76c-9eec-407b-982c-9350613148fa","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:42:53.316869Z","strongest_claim":"augmentation-based finetuning can achieve lower target-domain restoration risk by jointly improving target distribution coverage and controlling spectral bias","one_line_summary":"HIR-ALIGN augments limited target data for hyperspectral restoration by creating proxy clean images, synthesizing aligned HSIs with blur-robust diffusion and warp-based transfer, then finetuning models to lower target-domain risk.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The proxy HSIs produced by off-the-shelf restoration models are semantics-preserving approximations of clean target-domain images, and the diffusion-generated RGBs can be accurately aligned to proxies via warp-based spectral transfer without introducing new biases.","pith_extraction_headline":"Diffusion-generated synthetic HSIs allow finetuning of restoration models to match target domains without clean references"},"references":{"count":69,"sample":[{"doi":"","year":2012,"title":"Coupled segmentation and denoising/deblurring models for hyperspectral material identification,","work_id":"2c84602a-b539-4f68-bfe2-9e8caf05f0b9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1999,"title":"Models and methods for automated material identification in hyperspectral imagery acquired under unknown illumi- nation and atmospheric conditions,","work_id":"2044acb9-3729-41be-90e5-1bbe49b4c22b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Hyperspectral image dataset for benchmarking on salient object detection,","work_id":"9536799a-9f97-4f5f-ab99-266ea1a047cb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Material based salient object detection from hyperspectral images,","work_id":"8ecc8ed8-91b0-4efc-ba1c-ec9be97868b7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Object detection in hyperspectral images,","work_id":"a824f832-ccb3-4ebb-b0be-3bce3f086259","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":69,"snapshot_sha256":"4abdeead3e6a2c6d74c80995018f323063de0de7fc1146ffc0608f912745a5a7","internal_anchors":5},"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"},"verdict_id":"c93ee76c-9eec-407b-982c-9350613148fa"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SdRJs8Y2XEjVpxyK+atyvgyrxzMTS423USlX8EpZoL05feqnFYI70tt7IptMTF9Mc9ZH0HHjKPZP+93IPWMDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:02:49.822212Z"},"content_sha256":"0ec0faf0cea364a3f943331b876cd1f2ebf1e9dae1a7a4c0b77c0d104c539a28","schema_version":"1.0","event_id":"sha256:0ec0faf0cea364a3f943331b876cd1f2ebf1e9dae1a7a4c0b77c0d104c539a28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CPJNUDTIXSMFD4X25P6TL5PKO/bundle.json","state_url":"https://pith.science/pith/2CPJNUDTIXSMFD4X25P6TL5PKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CPJNUDTIXSMFD4X25P6TL5PKO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T22:02:49Z","links":{"resolver":"https://pith.science/pith/2CPJNUDTIXSMFD4X25P6TL5PKO","bundle":"https://pith.science/pith/2CPJNUDTIXSMFD4X25P6TL5PKO/bundle.json","state":"https://pith.science/pith/2CPJNUDTIXSMFD4X25P6TL5PKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CPJNUDTIXSMFD4X25P6TL5PKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2CPJNUDTIXSMFD4X25P6TL5PKO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3b4ca972485c694eaeb37ff1120152fd8d394b548298b00d2137319cf4dcab1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:14:13Z","title_canon_sha256":"d0a02f4169f49481437d30264f936993e8ba2cf008990609f039ce3faead1c06"},"schema_version":"1.0","source":{"id":"2605.13581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13581","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13581v1","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13581","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"2CPJNUDTIXSM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2CPJNUDTIXSMFD4X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2CPJNUDT","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0ec0faf0cea364a3f943331b876cd1f2ebf1e9dae1a7a4c0b77c0d104c539a28","target":"graph","created_at":"2026-05-18T02:44:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"augmentation-based finetuning can achieve lower target-domain restoration risk by jointly improving target distribution coverage and controlling spectral bias"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The proxy HSIs produced by off-the-shelf restoration models are semantics-preserving approximations of clean target-domain images, and the diffusion-generated RGBs can be accurately aligned to proxies via warp-based spectral transfer without introducing new biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"HIR-ALIGN augments limited target data for hyperspectral restoration by creating proxy clean images, synthesizing aligned HSIs with blur-robust diffusion and warp-based transfer, then finetuning models to lower target-domain risk."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Diffusion-generated synthetic HSIs allow finetuning of restoration models to match target domains without clean references"}],"snapshot_sha256":"fd05fcf05e2aa4e02075e7afd23bbbf0aaf3f409f04c7faf7c00de328b3a86d4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real HSIs suffer from degradations like noise, blur, and resolution loss. However, existing models trained on source data often fail on target domains lacking clean references, a common occurrence in practice. To address this issue, we present HIR-ALIGN, a plug-and-play target-adaptive augmentation framework that enhances hyperspectral image restoration by augmenting limited training images with synthetic data that closely matches the target distribution using no extra data. It consists of three stages: (i) proxy genera","authors_text":"Deyu Meng, Heng Zhao, Li Pang, Xiangyong Cao, Yijia Zhang","cross_cats":[],"headline":"Diffusion-generated synthetic HSIs allow finetuning of restoration models to match target domains without clean references","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:14:13Z","title":"HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation"},"references":{"count":69,"internal_anchors":5,"resolved_work":69,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Coupled segmentation and denoising/deblurring models for hyperspectral material identification,","work_id":"2c84602a-b539-4f68-bfe2-9e8caf05f0b9","year":2012},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Models and methods for automated material identification in hyperspectral imagery acquired under unknown illumi- nation and atmospheric conditions,","work_id":"2044acb9-3729-41be-90e5-1bbe49b4c22b","year":1999},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Hyperspectral image dataset for benchmarking on salient object detection,","work_id":"9536799a-9f97-4f5f-ab99-266ea1a047cb","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Material based salient object detection from hyperspectral images,","work_id":"8ecc8ed8-91b0-4efc-ba1c-ec9be97868b7","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Object detection in hyperspectral images,","work_id":"a824f832-ccb3-4ebb-b0be-3bce3f086259","year":2021}],"snapshot_sha256":"4abdeead3e6a2c6d74c80995018f323063de0de7fc1146ffc0608f912745a5a7"},"source":{"id":"2605.13581","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:42:53.316869Z","id":"c93ee76c-9eec-407b-982c-9350613148fa","model_set":{"reader":"grok-4.3"},"one_line_summary":"HIR-ALIGN augments limited target data for hyperspectral restoration by creating proxy clean images, synthesizing aligned HSIs with blur-robust diffusion and warp-based transfer, then finetuning models to lower target-domain risk.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Diffusion-generated synthetic HSIs allow finetuning of restoration models to match target domains without clean references","strongest_claim":"augmentation-based finetuning can achieve lower target-domain restoration risk by jointly improving target distribution coverage and controlling spectral bias","weakest_assumption":"The proxy HSIs produced by off-the-shelf restoration models are semantics-preserving approximations of clean target-domain images, and the diffusion-generated RGBs can be accurately aligned to proxies via warp-based spectral transfer without introducing new biases."}},"verdict_id":"c93ee76c-9eec-407b-982c-9350613148fa"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4bfaca1114078b0bd4be998db8f4326904be765b85d6fca717b52dd97651bf6f","target":"record","created_at":"2026-05-18T02:44:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3b4ca972485c694eaeb37ff1120152fd8d394b548298b00d2137319cf4dcab1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:14:13Z","title_canon_sha256":"d0a02f4169f49481437d30264f936993e8ba2cf008990609f039ce3faead1c06"},"schema_version":"1.0","source":{"id":"2605.13581","kind":"arxiv","version":1}},"canonical_sha256":"d09e96d07345e4c28f97d75fe9afaf538cad2b6c3c1c15247706d12f01fc62bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d09e96d07345e4c28f97d75fe9afaf538cad2b6c3c1c15247706d12f01fc62bd","first_computed_at":"2026-05-18T02:44:23.231656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:23.231656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fv7AwXtOi9B7m3ZcVYtpULA1JD/jVDxJI62kg3YKJ4U+6V3za+EJ9/JJJy1aTg9rtSktNlAh2fyrWyblzbB7Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:23.232138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bfaca1114078b0bd4be998db8f4326904be765b85d6fca717b52dd97651bf6f","sha256:0ec0faf0cea364a3f943331b876cd1f2ebf1e9dae1a7a4c0b77c0d104c539a28"],"state_sha256":"4df64b0d109257a2bcea8aa6d703390205d32eb6a4fae502c8cc8c9420423063"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eh3G5m57ZpfjoHTU/3isIPxlb979XD0LsMS2EGI6+tDQ9XZ2tm1iWeNFO7bffmASb5N0s71iFk3Kk8/8kBIBCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T22:02:49.826258Z","bundle_sha256":"4f2807cf577cc30760e89ed14f5295cfa5b29e0cc0603dac2b553de168582803"}}