{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UNEBNJCZ3CPKXDUXKNTQFU5AQN","short_pith_number":"pith:UNEBNJCZ","schema_version":"1.0","canonical_sha256":"a34816a459d89eab8e97536702d3a083692f293b6d2621f79795b5922158ccdf","source":{"kind":"arxiv","id":"2605.14654","version":1},"attestation_state":"computed","paper":{"title":"Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Leveraging cross-instance anatomical topology consistency as a supervisory signal improves self-supervised representations in 3D multi-modal medical imaging.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Kaiyu Guo, Limei Han, Mahsa Baktashmotlagh, Mengzhu Li, Shuhao Mei, Tan Pan, Xiang Zou, Yixuan Sun, Yuan Cheng, Zhaorui Tan","submitted_at":"2026-05-14T10:10:34Z","abstract_excerpt":"Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or masked reconstruction. They often do not adequately capitalize on a key characteristic of physiological features: anatomical structures maintain consistent spatial relationships across individuals (instances), such as the thalamus being medial to the basal ganglia, regardless of variations in brain size, shape, or pathology. We propose leveraging this cross-instance topological consistency as a supervisory signal. The"},"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":"2605.14654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T10:10:34Z","cross_cats_sorted":[],"title_canon_sha256":"2dcceb91be2159d33103e76534206fb58b7088443c58e2cf9b62e54398d70685","abstract_canon_sha256":"c19cb36cb13c506496b016bde150983e84d059842666387512a88ec7e037e46c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:03.771512Z","signature_b64":"AR8DHrtJlDxbBe810lS+bjdTy8OUNIXtSJHjYIIqcPPAb0wXXnt4dWO8dcPO1SaP4q0o3UHFPGkZv8Tl1QuXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a34816a459d89eab8e97536702d3a083692f293b6d2621f79795b5922158ccdf","last_reissued_at":"2026-05-17T23:39:03.770842Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:03.770842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Leveraging cross-instance anatomical topology consistency as a supervisory signal improves self-supervised representations in 3D multi-modal medical imaging.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Kaiyu Guo, Limei Han, Mahsa Baktashmotlagh, Mengzhu Li, Shuhao Mei, Tan Pan, Xiang Zou, Yixuan Sun, Yuan Cheng, Zhaorui Tan","submitted_at":"2026-05-14T10:10:34Z","abstract_excerpt":"Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or masked reconstruction. They often do not adequately capitalize on a key characteristic of physiological features: anatomical structures maintain consistent spatial relationships across individuals (instances), such as the thalamus being medial to the basal ganglia, regardless of variations in brain size, shape, or pathology. We propose leveraging this cross-instance topological consistency as a supervisory signal. The"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose leveraging this cross-instance topological consistency as a supervisory signal... We validate our approach across 7 downstream multi-modal tasks, achieving average improvements of 1.1% and 5.94% in segmentation and classification tasks, respectively, and demonstrating significantly better robustness when modalities are missing at test time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"anatomical structures maintain consistent spatial relationships across individuals (instances), such as the thalamus being medial to the basal ganglia, regardless of variations in brain size, shape, or pathology","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Leveraging cross-instance anatomical topology consistency as a supervisory signal improves self-supervised representations in 3D multi-modal medical imaging.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"548d16468761b309fb0ec91d5fea095eade0f80a9ec7ad4d60a34d83e7d7bcb5"},"source":{"id":"2605.14654","kind":"arxiv","version":1},"verdict":{"id":"d7c387d9-78ab-403b-8ace-a90a8261d9b7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:24:17.288570Z","strongest_claim":"We propose leveraging this cross-instance topological consistency as a supervisory signal... We validate our approach across 7 downstream multi-modal tasks, achieving average improvements of 1.1% and 5.94% in segmentation and classification tasks, respectively, and demonstrating significantly better robustness when modalities are missing at test time.","one_line_summary":"A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"anatomical structures maintain consistent spatial relationships across individuals (instances), such as the thalamus being medial to the basal ganglia, regardless of variations in brain size, shape, or pathology","pith_extraction_headline":"Leveraging cross-instance anatomical topology consistency as a supervisory signal improves self-supervised representations in 3D multi-modal medical imaging."},"references":{"count":234,"sample":[{"doi":"","year":null,"title":"FirstName LastName , title =","work_id":"d9cab501-317f-4237-9e32-b5ead5964402","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"FirstName Alpher , title =","work_id":"42297990-8783-41a1-b0fa-8ccdbf630852","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Journal of Foo , volume = 13, number = 1, pages =","work_id":"65a8b3d0-af84-4f68-87eb-101c85ab18b2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Journal of Foo , volume = 14, number = 1, pages =","work_id":"b3089947-bd36-4a24-9199-cc535e299537","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"FirstName Alpher and FirstName Gamow , title =","work_id":"caed320b-7cdc-41ca-bb08-00fb14feec62","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":234,"snapshot_sha256":"6cd8c71ae762200186cc7874abb20f07728835bd855a7cbe30eadd0257cea706","internal_anchors":15},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46b285fb13f67709ebf39f2cf0084b25f50863f052651321e4b484bde379512e"},"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":"2605.14654","created_at":"2026-05-17T23:39:03.770964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14654v1","created_at":"2026-05-17T23:39:03.770964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14654","created_at":"2026-05-17T23:39:03.770964+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNEBNJCZ3CPK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNEBNJCZ3CPKXDUX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNEBNJCZ","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":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN","json":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN.json","graph_json":"https://pith.science/api/pith-number/UNEBNJCZ3CPKXDUXKNTQFU5AQN/graph.json","events_json":"https://pith.science/api/pith-number/UNEBNJCZ3CPKXDUXKNTQFU5AQN/events.json","paper":"https://pith.science/paper/UNEBNJCZ"},"agent_actions":{"view_html":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN","download_json":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN.json","view_paper":"https://pith.science/paper/UNEBNJCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14654&json=true","fetch_graph":"https://pith.science/api/pith-number/UNEBNJCZ3CPKXDUXKNTQFU5AQN/graph.json","fetch_events":"https://pith.science/api/pith-number/UNEBNJCZ3CPKXDUXKNTQFU5AQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN/action/storage_attestation","attest_author":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN/action/author_attestation","sign_citation":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN/action/citation_signature","submit_replication":"https://pith.science/pith/UNEBNJCZ3CPKXDUXKNTQFU5AQN/action/replication_record"}},"created_at":"2026-05-17T23:39:03.770964+00:00","updated_at":"2026-05-17T23:39:03.770964+00:00"}