{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3FY3ANFIO2Q44LB7OGRKSVRZBU","short_pith_number":"pith:3FY3ANFI","schema_version":"1.0","canonical_sha256":"d971b034a876a1ce2c3f71a2a956390d1a62c070f5c45ee45e3c92667436e3b8","source":{"kind":"arxiv","id":"2509.05238","version":2},"attestation_state":"computed","paper":{"title":"Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA"],"primary_cat":"math.NA","authors_text":"In\\'es Gonzalez-Pepe, Tristan Glatard, Vinuyan Sivakolunthu, Yohan Chatelain","submitted_at":"2025-09-05T16:54:26Z","abstract_excerpt":"Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance with reduced computation times. Yet, the numerical uncertainty inherent to DL training remains largely underexplored despite its potential to significantly impact the reliability of model outcomes. We show that training the FastSurfer segmentation model introduces substantial numerical uncertainty that exceeds its non-DL counterpart (FreeSurfer 7.3.2) in cortical regions, potentially impacting downstream clinical results. We also characterize this training-time uncertainty using random seed perturbations"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.05238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-09-05T16:54:26Z","cross_cats_sorted":["cs.AI","cs.NA"],"title_canon_sha256":"a6c72be6002e1e3557d4503a10033fdf0195caa530feb962b7b3829556dadb89","abstract_canon_sha256":"ce1fab49fbb888b1979adc55a7a9fc3018453f8ffc075ce6c10a97257ed0776f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:53.801479Z","signature_b64":"wgq9Hr/OILBcY/srN5kQxf4T5or+lJTFqVC1XFEBrb/WsycrRTLMSwlmCpaDkrystBFdugnZS1rsaxDOICURDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d971b034a876a1ce2c3f71a2a956390d1a62c070f5c45ee45e3c92667436e3b8","last_reissued_at":"2026-07-03T01:17:53.800981Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:53.800981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA"],"primary_cat":"math.NA","authors_text":"In\\'es Gonzalez-Pepe, Tristan Glatard, Vinuyan Sivakolunthu, Yohan Chatelain","submitted_at":"2025-09-05T16:54:26Z","abstract_excerpt":"Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance with reduced computation times. Yet, the numerical uncertainty inherent to DL training remains largely underexplored despite its potential to significantly impact the reliability of model outcomes. We show that training the FastSurfer segmentation model introduces substantial numerical uncertainty that exceeds its non-DL counterpart (FreeSurfer 7.3.2) in cortical regions, potentially impacting downstream clinical results. We also characterize this training-time uncertainty using random seed perturbations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05238","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.05238/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.05238","created_at":"2026-07-03T01:17:53.801040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05238v2","created_at":"2026-07-03T01:17:53.801040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05238","created_at":"2026-07-03T01:17:53.801040+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FY3ANFIO2Q4","created_at":"2026-07-03T01:17:53.801040+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FY3ANFIO2Q44LB7","created_at":"2026-07-03T01:17:53.801040+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FY3ANFI","created_at":"2026-07-03T01:17:53.801040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU","json":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU.json","graph_json":"https://pith.science/api/pith-number/3FY3ANFIO2Q44LB7OGRKSVRZBU/graph.json","events_json":"https://pith.science/api/pith-number/3FY3ANFIO2Q44LB7OGRKSVRZBU/events.json","paper":"https://pith.science/paper/3FY3ANFI"},"agent_actions":{"view_html":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU","download_json":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU.json","view_paper":"https://pith.science/paper/3FY3ANFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05238&json=true","fetch_graph":"https://pith.science/api/pith-number/3FY3ANFIO2Q44LB7OGRKSVRZBU/graph.json","fetch_events":"https://pith.science/api/pith-number/3FY3ANFIO2Q44LB7OGRKSVRZBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU/action/storage_attestation","attest_author":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU/action/author_attestation","sign_citation":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU/action/citation_signature","submit_replication":"https://pith.science/pith/3FY3ANFIO2Q44LB7OGRKSVRZBU/action/replication_record"}},"created_at":"2026-07-03T01:17:53.801040+00:00","updated_at":"2026-07-03T01:17:53.801040+00:00"}