{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KUVCXGSQSVAO7MFCSLUOA5J2Z2","short_pith_number":"pith:KUVCXGSQ","schema_version":"1.0","canonical_sha256":"552a2b9a509540efb0a292e8e0753ace939d74a0f49f05eb963279f001c2133d","source":{"kind":"arxiv","id":"2605.13730","version":1},"attestation_state":"computed","paper":{"title":"Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A stacked ensemble of video models distinguishes bicuspid from tricuspid aortic valves on routine echocardiography cine loops with an F1-score of 0.907.","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Christos Chrysanthos Nikolaidis, Nikolas Moustakidis, Pavlos S. Efraimidis, Theofilos Moustakidis, Vasileios Sachpekidis","submitted_at":"2026-05-13T16:10:39Z","abstract_excerpt":"Transthoracic echocardiography (TTE) is the first-line imaging modality for diagnosing bicuspid aortic valve (BAV), yet diagnostic performance varies with operator expertise and image quality. We developed an explainable AI model that distinguishes BAV from tricuspid aortic valves (TAV) using routinely acquired parasternal long-axis (PLAX) cine loops. A multi-backbone video ensemble was trained and evaluated using a leakage-aware, stratified outer cross-validation protocol on $N{=}90$ patient studies (48 BAV, 42 TAV). Across fixed outer splits and 10 random seeds, the calibrated stacked ensemb"},"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":"2605.13730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:10:39Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"aa8c90194b2153afa2f5904667872908c0672019ce6f7e6cd99ed8ee4cc11f41","abstract_canon_sha256":"eacc64200159e05eea575f8d678765462bc92d29829a51ffeae3241fcc25e38d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.566490Z","signature_b64":"CHp7kft1tIwYypFhlq7aFOwwVwHzpbxFrPmGG7/+thnyct9lPSW0bOY6z3Og5Y+BA0NJ6MtVWXyvBpQviBIDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552a2b9a509540efb0a292e8e0753ace939d74a0f49f05eb963279f001c2133d","last_reissued_at":"2026-05-18T02:44:16.565898Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.565898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A stacked ensemble of video models distinguishes bicuspid from tricuspid aortic valves on routine echocardiography cine loops with an F1-score of 0.907.","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Christos Chrysanthos Nikolaidis, Nikolas Moustakidis, Pavlos S. Efraimidis, Theofilos Moustakidis, Vasileios Sachpekidis","submitted_at":"2026-05-13T16:10:39Z","abstract_excerpt":"Transthoracic echocardiography (TTE) is the first-line imaging modality for diagnosing bicuspid aortic valve (BAV), yet diagnostic performance varies with operator expertise and image quality. We developed an explainable AI model that distinguishes BAV from tricuspid aortic valves (TAV) using routinely acquired parasternal long-axis (PLAX) cine loops. A multi-backbone video ensemble was trained and evaluated using a leakage-aware, stratified outer cross-validation protocol on $N{=}90$ patient studies (48 BAV, 42 TAV). Across fixed outer splits and 10 random seeds, the calibrated stacked ensemb"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across fixed outer splits and 10 random seeds, the calibrated stacked ensemble achieved an outer-CV F1-score of 0.907 and recall of 0.877 on N=90 patient studies (48 BAV, 42 TAV).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the leakage-aware stratified outer cross-validation on this small internal cohort fully ensures robustness and generalizability to new patients and imaging conditions without external validation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Stacked video ensemble model distinguishes BAV from TAV on PLAX cine loops with outer-CV F1 of 0.907 using Grad-CAM and SHAP for explainability.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A stacked ensemble of video models distinguishes bicuspid from tricuspid aortic valves on routine echocardiography cine loops with an F1-score of 0.907.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"df709df9dcc5ae04f2428047806313f46ff11df61a3808542a28773cdabc8d49"},"source":{"id":"2605.13730","kind":"arxiv","version":1},"verdict":{"id":"850e1968-eede-4861-9a33-fa76f78364bb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:04:53.005223Z","strongest_claim":"Across fixed outer splits and 10 random seeds, the calibrated stacked ensemble achieved an outer-CV F1-score of 0.907 and recall of 0.877 on N=90 patient studies (48 BAV, 42 TAV).","one_line_summary":"Stacked video ensemble model distinguishes BAV from TAV on PLAX cine loops with outer-CV F1 of 0.907 using Grad-CAM and SHAP for explainability.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the leakage-aware stratified outer cross-validation on this small internal cohort fully ensures robustness and generalizability to new patients and imaging conditions without external validation.","pith_extraction_headline":"A stacked ensemble of video models distinguishes bicuspid from tricuspid aortic valves on routine echocardiography cine loops with an F1-score of 0.907."},"references":{"count":26,"sample":[{"doi":"","year":2021,"title":"Braverman and Andrew Cheng","work_id":"e637c726-f7bc-48f9-bd88-70338a346686","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"M. Hillebrand, W. Li, S. Gross, et al. Accuracy of transthoracic echocardiography to diagnose bicuspid aortic valve: comparison with surgical findings and cardiac magnetic resonance imaging.Internatio","work_id":"737a5a1d-2df1-4ac6-9e82-68dc82e50a84","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"R.F. Ayad, J.J. Puthumana, and R. Doukky. Echocardio- graphic accuracy in diagnosing bicuspid aortic valve and its clinical implications.Echocardiography, 28(5): 558–562, 2011","work_id":"2f898a43-716b-4fdf-b234-f9d2213ac803","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"J. Chen, S. Li, and Y . Xiao. Automatic classification of BA V using CNNs on echocardiography.IEEE Journal of Biomedical and Health Informatics, 24(11):3120– 3130, 2020","work_id":"fec787ac-f78d-45a2-81e1-b3314a539574","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"D. Ouyang, T. He, C. Cao, et al. Video-based AI for beat-to-beat assessment of cardiac function.Nature, 580(7802):252–256, 2020","work_id":"9f81fae6-d2b2-4176-98d9-e9cc75b2df7d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"fbc1c87f45ef51a951c101f90dd3ed9256d07044159ac94386bd8f1369a9f512","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7be14f5f60b9a4c9d6a94ee33b5001d95d88b15b956aae13ec95d3d3cfed23e4"},"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":"2605.13730","created_at":"2026-05-18T02:44:16.565986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13730v1","created_at":"2026-05-18T02:44:16.565986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13730","created_at":"2026-05-18T02:44:16.565986+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUVCXGSQSVAO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUVCXGSQSVAO7MFC","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUVCXGSQ","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/KUVCXGSQSVAO7MFCSLUOA5J2Z2","json":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2.json","graph_json":"https://pith.science/api/pith-number/KUVCXGSQSVAO7MFCSLUOA5J2Z2/graph.json","events_json":"https://pith.science/api/pith-number/KUVCXGSQSVAO7MFCSLUOA5J2Z2/events.json","paper":"https://pith.science/paper/KUVCXGSQ"},"agent_actions":{"view_html":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2","download_json":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2.json","view_paper":"https://pith.science/paper/KUVCXGSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13730&json=true","fetch_graph":"https://pith.science/api/pith-number/KUVCXGSQSVAO7MFCSLUOA5J2Z2/graph.json","fetch_events":"https://pith.science/api/pith-number/KUVCXGSQSVAO7MFCSLUOA5J2Z2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2/action/storage_attestation","attest_author":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2/action/author_attestation","sign_citation":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2/action/citation_signature","submit_replication":"https://pith.science/pith/KUVCXGSQSVAO7MFCSLUOA5J2Z2/action/replication_record"}},"created_at":"2026-05-18T02:44:16.565986+00:00","updated_at":"2026-05-18T02:44:16.565986+00:00"}