{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SJ6V5MBNR6EM4XXFBUYGCT2KV5","short_pith_number":"pith:SJ6V5MBN","canonical_record":{"source":{"id":"2605.15895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:23:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4f39bcaebc394611bb316f3cb829e4ea857d5d22decc56b2456b15163081db61","abstract_canon_sha256":"ea135cec810960c662be5868ef04fbfaa72ed8a5b15ee567c67caaa693738c85"},"schema_version":"1.0"},"canonical_sha256":"927d5eb02d8f88ce5ee50d30614f4aaf4889be38990b985599e5301f7ebc5a42","source":{"kind":"arxiv","id":"2605.15895","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15895","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15895v1","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15895","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"SJ6V5MBNR6EM","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"pith_short_16","alias_value":"SJ6V5MBNR6EM4XXF","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"pith_short_8","alias_value":"SJ6V5MBN","created_at":"2026-05-20T00:01:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SJ6V5MBNR6EM4XXFBUYGCT2KV5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:23:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4f39bcaebc394611bb316f3cb829e4ea857d5d22decc56b2456b15163081db61","abstract_canon_sha256":"ea135cec810960c662be5868ef04fbfaa72ed8a5b15ee567c67caaa693738c85"},"schema_version":"1.0"},"canonical_sha256":"927d5eb02d8f88ce5ee50d30614f4aaf4889be38990b985599e5301f7ebc5a42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:24.222687Z","signature_b64":"0zayoOdnCkTbAmdaVgy+7dwTSqL+cASUkH4YcgqPY1BmcfqNd/LnLgvqCi4C5hy26A8AzDzGOEtBQHUyC7ZxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"927d5eb02d8f88ce5ee50d30614f4aaf4889be38990b985599e5301f7ebc5a42","last_reissued_at":"2026-05-20T00:01:24.221464Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:24.221464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15895","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":"2026-05-20T00:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lYTBIlfVZ/UMNKLYFWCouyNZzsLC63nYrsVw8sWnZsZiTUDPxwgTiY6OfJALilsuptcRee231IFoXU6pBbsGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:41:38.646876Z"},"content_sha256":"a462e1fdaa9609afc826f1620f4ccde539a4d224eca6fde9b1108f39275e421f","schema_version":"1.0","event_id":"sha256:a462e1fdaa9609afc826f1620f4ccde539a4d224eca6fde9b1108f39275e421f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SJ6V5MBNR6EM4XXFBUYGCT2KV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Layer Selection in Feature-Based Losses Affects Image Quality and Microstructural Consistency in Deep Learning Super-Resolution of Brain Diffusion MRI","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Choosing the shallowest VGG16 layer for feature-based losses avoids grid-like artifacts in super-resolved brain diffusion MRI and maintains microstructural consistency.","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"David Lohr, Rene Werner","submitted_at":"2026-05-15T12:23:40Z","abstract_excerpt":"Clinical application of high-resolution diffusion MRI is hindered by hardware limitations and prohibitive scan times, motivating computational super-resolution. This study investigates the efficacy of a feature-based loss function in preserving diffusion signal consistency in deep learning super-resolution. Using 7T data from the human connectome project to generate pairs of low- and high-resolution diffusion weighted images (DWI), we trained UNets for 2D super-resolution. Ablation and isolation studies evaluated different VGG16-layers for feature-based losses against an image-based L1 baselin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Deeper layers and combinations thereof resulted in grid-like artifacts in super-resolution DWIs, which persisted in diffusion parameters like quantitative and fractional anisotropy. No such artifacts were present when using the shallowest layer. Downstream analysis for this layer showed great consistency with the ground truth, even for 9-fold super-resolution.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The ablation and isolation studies sufficiently isolate the effect of VGG16 layer depth from other training choices such as optimizer settings, data augmentation, or network capacity, so that the observed grid artifacts can be attributed primarily to layer selection.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Deeper VGG16 layers in feature losses for diffusion MRI super-resolution introduce persistent grid artifacts in images and anisotropy maps, whereas the shallowest layer preserves consistency with ground truth at high upsampling factors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Choosing the shallowest VGG16 layer for feature-based losses avoids grid-like artifacts in super-resolved brain diffusion MRI and maintains microstructural consistency.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d564ba397674e0e3b7c63d1da7812deaa2032860ee0ef16563848a0fd66c5d4b"},"source":{"id":"2605.15895","kind":"arxiv","version":1},"verdict":{"id":"832f77c1-4410-449b-af1a-20151bed02ff","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:37:48.344528Z","strongest_claim":"Deeper layers and combinations thereof resulted in grid-like artifacts in super-resolution DWIs, which persisted in diffusion parameters like quantitative and fractional anisotropy. No such artifacts were present when using the shallowest layer. Downstream analysis for this layer showed great consistency with the ground truth, even for 9-fold super-resolution.","one_line_summary":"Deeper VGG16 layers in feature losses for diffusion MRI super-resolution introduce persistent grid artifacts in images and anisotropy maps, whereas the shallowest layer preserves consistency with ground truth at high upsampling factors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The ablation and isolation studies sufficiently isolate the effect of VGG16 layer depth from other training choices such as optimizer settings, data augmentation, or network capacity, so that the observed grid artifacts can be attributed primarily to layer selection.","pith_extraction_headline":"Choosing the shallowest VGG16 layer for feature-based losses avoids grid-like artifacts in super-resolved brain diffusion MRI and maintains microstructural consistency."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15895/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.001382Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:52:03.610389Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:46.568344Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.779024Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2ce9ed3033b33836702bbcefa225090f5981d04aa9483ea795398c99e115612e"},"references":{"count":41,"sample":[{"doi":"10.1016/b978-0-12-396460-1.00012-3","year":2014,"title":"Salat, D.H. (2014). Chapter 12 - Diffusion Tensor Imaging in the Study of Aging and Age-Associated Neural Disease. In Diffusion MRI (Second Edition), H. Johansen-Berg, and T.E.J. Behrens, eds. (Academ","work_id":"eda0437d-1353-44f3-b507-54e064d89ced","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.mri.2015.04.006","year":2015,"title":"Goveas, J., O'Dwyer, L., Mascalchi, M., Cosottini, M., Diciotti, S., De Santis, S., Passamonti, L., Tessa, C., Toschi, N., and Giannelli, M. (2015). Diffusion-MRI in neurodegenerative disorders. Magne","work_id":"3f39c09f-bd21-4b94-a1f0-f834f9141324","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.pnmrs.2019.03.001","year":2019,"title":"Tournier, J.D. (2019). Diffusion MRI in the brain - Theory and concepts. Prog Nucl Magn Reson Spectrosc 112-113, 1–16. 10.1016/j.pnmrs.2019.03.001","work_id":"bfc62502-149f-4b5c-8296-1e7494f12f0d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1038/nn.4501","year":2017,"title":"Lerch, J.P., van der Kouwe, A.J.W., Raznahan, A., Paus, T., Johansen-Berg, H., Miller, K.L., Smith, S.M., Fischl, B., and Sotiropoulos, S.N. (2017). Studying neuroanatomy using MRI. Nature Neuroscienc","work_id":"979eb14f-ae96-4370-864a-1bd76621f734","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.neuroimage.2013.05.041","year":2013,"title":"Van Essen, Stephen M","work_id":"d4c81d6f-f317-497f-97ff-5f9238bd863e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"c53f23702874b88b52b7f59a5e8eef053a315141208c1ef3e217b646fab7cc6a","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7e64b5223297784cc2d26fb6d818e65bc53767d31f94e16f704e2f89dcd1ad02"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"832f77c1-4410-449b-af1a-20151bed02ff"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIWr7W0JDt46gP4FGK/8rmDmUK1K3m/mmLz5cXhzjRgXWDzN6KSQ6Q38NbSkWL+9UUEAQ6WL1UZ5vHDvU1JrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:41:38.647860Z"},"content_sha256":"084e4eff2ce6c2210e08f44dda81a1dc8a0cae4f63854dc58bba3aecbe80c583","schema_version":"1.0","event_id":"sha256:084e4eff2ce6c2210e08f44dda81a1dc8a0cae4f63854dc58bba3aecbe80c583"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJ6V5MBNR6EM4XXFBUYGCT2KV5/bundle.json","state_url":"https://pith.science/pith/SJ6V5MBNR6EM4XXFBUYGCT2KV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJ6V5MBNR6EM4XXFBUYGCT2KV5/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":"2026-05-27T14:41:38Z","links":{"resolver":"https://pith.science/pith/SJ6V5MBNR6EM4XXFBUYGCT2KV5","bundle":"https://pith.science/pith/SJ6V5MBNR6EM4XXFBUYGCT2KV5/bundle.json","state":"https://pith.science/pith/SJ6V5MBNR6EM4XXFBUYGCT2KV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJ6V5MBNR6EM4XXFBUYGCT2KV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SJ6V5MBNR6EM4XXFBUYGCT2KV5","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":"ea135cec810960c662be5868ef04fbfaa72ed8a5b15ee567c67caaa693738c85","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:23:40Z","title_canon_sha256":"4f39bcaebc394611bb316f3cb829e4ea857d5d22decc56b2456b15163081db61"},"schema_version":"1.0","source":{"id":"2605.15895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15895","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15895v1","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15895","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"SJ6V5MBNR6EM","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"pith_short_16","alias_value":"SJ6V5MBNR6EM4XXF","created_at":"2026-05-20T00:01:24Z"},{"alias_kind":"pith_short_8","alias_value":"SJ6V5MBN","created_at":"2026-05-20T00:01:24Z"}],"graph_snapshots":[{"event_id":"sha256:084e4eff2ce6c2210e08f44dda81a1dc8a0cae4f63854dc58bba3aecbe80c583","target":"graph","created_at":"2026-05-20T00:01:24Z","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":"Deeper layers and combinations thereof resulted in grid-like artifacts in super-resolution DWIs, which persisted in diffusion parameters like quantitative and fractional anisotropy. No such artifacts were present when using the shallowest layer. Downstream analysis for this layer showed great consistency with the ground truth, even for 9-fold super-resolution."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The ablation and isolation studies sufficiently isolate the effect of VGG16 layer depth from other training choices such as optimizer settings, data augmentation, or network capacity, so that the observed grid artifacts can be attributed primarily to layer selection."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Deeper VGG16 layers in feature losses for diffusion MRI super-resolution introduce persistent grid artifacts in images and anisotropy maps, whereas the shallowest layer preserves consistency with ground truth at high upsampling factors."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Choosing the shallowest VGG16 layer for feature-based losses avoids grid-like artifacts in super-resolved brain diffusion MRI and maintains microstructural consistency."}],"snapshot_sha256":"d564ba397674e0e3b7c63d1da7812deaa2032860ee0ef16563848a0fd66c5d4b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7e64b5223297784cc2d26fb6d818e65bc53767d31f94e16f704e2f89dcd1ad02"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.001382Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:52:03.610389Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:46.568344Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.779024Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15895/integrity.json","findings":[],"snapshot_sha256":"2ce9ed3033b33836702bbcefa225090f5981d04aa9483ea795398c99e115612e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical application of high-resolution diffusion MRI is hindered by hardware limitations and prohibitive scan times, motivating computational super-resolution. This study investigates the efficacy of a feature-based loss function in preserving diffusion signal consistency in deep learning super-resolution. Using 7T data from the human connectome project to generate pairs of low- and high-resolution diffusion weighted images (DWI), we trained UNets for 2D super-resolution. Ablation and isolation studies evaluated different VGG16-layers for feature-based losses against an image-based L1 baselin","authors_text":"David Lohr, Rene Werner","cross_cats":["cs.CV"],"headline":"Choosing the shallowest VGG16 layer for feature-based losses avoids grid-like artifacts in super-resolved brain diffusion MRI and maintains microstructural consistency.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:23:40Z","title":"Layer Selection in Feature-Based Losses Affects Image Quality and Microstructural Consistency in Deep Learning Super-Resolution of Brain Diffusion MRI"},"references":{"count":41,"internal_anchors":3,"resolved_work":41,"sample":[{"cited_arxiv_id":"","doi":"10.1016/b978-0-12-396460-1.00012-3","is_internal_anchor":false,"ref_index":1,"title":"Salat, D.H. (2014). Chapter 12 - Diffusion Tensor Imaging in the Study of Aging and Age-Associated Neural Disease. In Diffusion MRI (Second Edition), H. Johansen-Berg, and T.E.J. Behrens, eds. (Academ","work_id":"eda0437d-1353-44f3-b507-54e064d89ced","year":2014},{"cited_arxiv_id":"","doi":"10.1016/j.mri.2015.04.006","is_internal_anchor":false,"ref_index":2,"title":"Goveas, J., O'Dwyer, L., Mascalchi, M., Cosottini, M., Diciotti, S., De Santis, S., Passamonti, L., Tessa, C., Toschi, N., and Giannelli, M. (2015). Diffusion-MRI in neurodegenerative disorders. Magne","work_id":"3f39c09f-bd21-4b94-a1f0-f834f9141324","year":2015},{"cited_arxiv_id":"","doi":"10.1016/j.pnmrs.2019.03.001","is_internal_anchor":false,"ref_index":3,"title":"Tournier, J.D. (2019). Diffusion MRI in the brain - Theory and concepts. Prog Nucl Magn Reson Spectrosc 112-113, 1–16. 10.1016/j.pnmrs.2019.03.001","work_id":"bfc62502-149f-4b5c-8296-1e7494f12f0d","year":2019},{"cited_arxiv_id":"","doi":"10.1038/nn.4501","is_internal_anchor":false,"ref_index":4,"title":"Lerch, J.P., van der Kouwe, A.J.W., Raznahan, A., Paus, T., Johansen-Berg, H., Miller, K.L., Smith, S.M., Fischl, B., and Sotiropoulos, S.N. (2017). Studying neuroanatomy using MRI. Nature Neuroscienc","work_id":"979eb14f-ae96-4370-864a-1bd76621f734","year":2017},{"cited_arxiv_id":"","doi":"10.1016/j.neuroimage.2013.05.041","is_internal_anchor":false,"ref_index":5,"title":"Van Essen, Stephen M","work_id":"d4c81d6f-f317-497f-97ff-5f9238bd863e","year":2013}],"snapshot_sha256":"c53f23702874b88b52b7f59a5e8eef053a315141208c1ef3e217b646fab7cc6a"},"source":{"id":"2605.15895","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T18:37:48.344528Z","id":"832f77c1-4410-449b-af1a-20151bed02ff","model_set":{"reader":"grok-4.3"},"one_line_summary":"Deeper VGG16 layers in feature losses for diffusion MRI super-resolution introduce persistent grid artifacts in images and anisotropy maps, whereas the shallowest layer preserves consistency with ground truth at high upsampling factors.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Choosing the shallowest VGG16 layer for feature-based losses avoids grid-like artifacts in super-resolved brain diffusion MRI and maintains microstructural consistency.","strongest_claim":"Deeper layers and combinations thereof resulted in grid-like artifacts in super-resolution DWIs, which persisted in diffusion parameters like quantitative and fractional anisotropy. No such artifacts were present when using the shallowest layer. Downstream analysis for this layer showed great consistency with the ground truth, even for 9-fold super-resolution.","weakest_assumption":"The ablation and isolation studies sufficiently isolate the effect of VGG16 layer depth from other training choices such as optimizer settings, data augmentation, or network capacity, so that the observed grid artifacts can be attributed primarily to layer selection."}},"verdict_id":"832f77c1-4410-449b-af1a-20151bed02ff"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a462e1fdaa9609afc826f1620f4ccde539a4d224eca6fde9b1108f39275e421f","target":"record","created_at":"2026-05-20T00:01:24Z","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":"ea135cec810960c662be5868ef04fbfaa72ed8a5b15ee567c67caaa693738c85","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-15T12:23:40Z","title_canon_sha256":"4f39bcaebc394611bb316f3cb829e4ea857d5d22decc56b2456b15163081db61"},"schema_version":"1.0","source":{"id":"2605.15895","kind":"arxiv","version":1}},"canonical_sha256":"927d5eb02d8f88ce5ee50d30614f4aaf4889be38990b985599e5301f7ebc5a42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"927d5eb02d8f88ce5ee50d30614f4aaf4889be38990b985599e5301f7ebc5a42","first_computed_at":"2026-05-20T00:01:24.221464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:24.221464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0zayoOdnCkTbAmdaVgy+7dwTSqL+cASUkH4YcgqPY1BmcfqNd/LnLgvqCi4C5hy26A8AzDzGOEtBQHUyC7ZxDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:24.222687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a462e1fdaa9609afc826f1620f4ccde539a4d224eca6fde9b1108f39275e421f","sha256:084e4eff2ce6c2210e08f44dda81a1dc8a0cae4f63854dc58bba3aecbe80c583"],"state_sha256":"d819e4782e84c4f2a0893f6480cea9e3ca667e3c73f89b4531186a09aeaaf8a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C5vAydmHDWi4250+Nr4hpG+MMA+n17mwm+9RzUnwCTwcU/jngqVlwAW9NWeDapVuQclhrc8V/NQ/4P14IL3aCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:41:38.652496Z","bundle_sha256":"1a4c3dd82b3d8886481bea22a62b04743a6933514e36b7dd95ebec2ee8f50db7"}}