{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QJQDIAHGXY5DERWW2VI5HOE5ZS","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":"61f6a9294006fa914aa6bcdf63d177fe39ded1409ce93ec5efe14b0cd97654e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T17:20:26Z","title_canon_sha256":"a97e9b44c9f17cccb65aa07f95d4245930a7a952ed3e1860069a35259809b470"},"schema_version":"1.0","source":{"id":"2605.13798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13798","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13798v1","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13798","created_at":"2026-05-18T02:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"QJQDIAHGXY5D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QJQDIAHGXY5DERWW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QJQDIAHG","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9b40ca109391f6650a8faca9ac6575c4134f705e0c3b06b7812b055e99009de4","target":"graph","created_at":"2026-05-18T02:44:15Z","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":"VoxCor improves the hardest cross-subject, cross-modality transfer settings, reduces encoder sensitivity for dense correspondence transfer, and yields registration performance competitive with handcrafted descriptors and learned 3D features."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the modality-stable anatomical directions identified by the WPLS projection on fitting-time correspondences will generalize to new volumes and unseen modality combinations without further adaptation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VoxCor creates reusable volumetric features from frozen 2D ViT models by combining triplanar inference with a closed-form weighted partial least squares projection, enabling direct voxel correspondence across modalities without training or registration."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A training-free fit-transform method creates reusable volumetric features from frozen 2D vision transformers for cross-modal voxel correspondence."}],"snapshot_sha256":"a6361fcef4f5e5632e73dd9ebb1ef8b77b0e90e1e623944c2e7b6ccf75f2dc03"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"81a2f818f677f73a96f1a698f2fee0365a872ffd4faab19512314a17b838a2bf"},"paper":{"abstract_excerpt":"Cross-modal 3D medical image analysis requires voxelwise representations that remain anatomically consistent across imaging contrasts, scanners, and acquisition protocols. Recent work has shown that frozen 2D Vision Transformer (ViT) foundation models can support such representations, but typical pipelines extract features along a single anatomical axis and adapt those features inside a registration solver for one image pair at a time, leaving complementary viewing directions unused and producing representations that do not transfer to new volumes. We introduce VoxCor, a training-free fit--tra","authors_text":"Ender Konukoglu, Ertunc Erdil, Guney Tombak","cross_cats":[],"headline":"A training-free fit-transform method creates reusable volumetric features from frozen 2D vision transformers for cross-modal voxel correspondence.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T17:20:26Z","title":"VoxCor: Training-Free Volumetric Features for Multimodal Voxel Correspondence"},"references":{"count":36,"internal_anchors":4,"resolved_work":36,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A survey of medical image registration.Medical image analysis, 2(1):1–36, 1998","work_id":"8bc4a712-5630-4dc7-8e26-75df5cf43a1c","year":1998},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Deformable medical image registration: A survey.IEEE transactions on medical imaging, 32(7):1153–1190, 2013","work_id":"8bf5983e-9122-4454-a375-8149032420c8","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A review of atlas-based segmentation for magnetic resonance brain images.Computer methods and programs in biomedicine, 104(3):e158–e177, 2011","work_id":"5cc6b669-9df7-4afe-9980-7cac1ad311f0","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain.Medical image analysis, 12(1):26–41, 2008","work_id":"762c979c-3247-45f4-a5e2-0c7390b40c5b","year":2008},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Elastix: a toolbox for intensity-based medical image registration.IEEE transactions on medical imaging, 29(1):196–205, 2009","work_id":"7e01ca15-3f1f-4407-a864-32842c1a4617","year":2009}],"snapshot_sha256":"bd440fce6121033ec422343c0040e00e96e4ae6c456098aedde3320108dcc77f"},"source":{"id":"2605.13798","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:30:58.368894Z","id":"6f54bd47-7096-4582-8c35-bca1cba09f97","model_set":{"reader":"grok-4.3"},"one_line_summary":"VoxCor creates reusable volumetric features from frozen 2D ViT models by combining triplanar inference with a closed-form weighted partial least squares projection, enabling direct voxel correspondence across modalities without training or registration.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A training-free fit-transform method creates reusable volumetric features from frozen 2D vision transformers for cross-modal voxel correspondence.","strongest_claim":"VoxCor improves the hardest cross-subject, cross-modality transfer settings, reduces encoder sensitivity for dense correspondence transfer, and yields registration performance competitive with handcrafted descriptors and learned 3D features.","weakest_assumption":"That the modality-stable anatomical directions identified by the WPLS projection on fitting-time correspondences will generalize to new volumes and unseen modality combinations without further adaptation."}},"verdict_id":"6f54bd47-7096-4582-8c35-bca1cba09f97"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b6151ba4fb3df080e5a677ba7893fb1314b015282bb53511973250f1011640ed","target":"record","created_at":"2026-05-18T02:44:15Z","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":"61f6a9294006fa914aa6bcdf63d177fe39ded1409ce93ec5efe14b0cd97654e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T17:20:26Z","title_canon_sha256":"a97e9b44c9f17cccb65aa07f95d4245930a7a952ed3e1860069a35259809b470"},"schema_version":"1.0","source":{"id":"2605.13798","kind":"arxiv","version":1}},"canonical_sha256":"82603400e6be3a3246d6d551d3b89dcc8d95cfe3ff3e6ad745886a7787dc55aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82603400e6be3a3246d6d551d3b89dcc8d95cfe3ff3e6ad745886a7787dc55aa","first_computed_at":"2026-05-18T02:44:15.546508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:15.546508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdnWiTMfFbcKgKFVx6t0LlCTLrVN3Ma/IrAoPGYyEWw+m3qRi4UTTWzMFSrLr+sY/9iCSVjGPcs8+UU6BWhkDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:15.547048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6151ba4fb3df080e5a677ba7893fb1314b015282bb53511973250f1011640ed","sha256:9b40ca109391f6650a8faca9ac6575c4134f705e0c3b06b7812b055e99009de4"],"state_sha256":"177cd246c88d3c792a6f5c4fde76923affd05d5ea49945b7a67edb6cc26ac1e3"}