{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EF5M7DANTEQGXWTYJSCWVRACQV","short_pith_number":"pith:EF5M7DAN","schema_version":"1.0","canonical_sha256":"217acf8c0d99206bda784c856ac402854938be0e774b50b8d103223cfd80b0df","source":{"kind":"arxiv","id":"2110.03352","version":2},"attestation_state":"computed","paper":{"title":"Optimized U-Net for Brain Tumor Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Alexandre Milesi, Micha{\\l} Futrega, Michal Marcinkiewicz, Pablo Ribalta","submitted_at":"2021-10-07T11:44:09Z","abstract_excerpt":"We propose an optimized U-Net architecture for a brain tumor segmentation task in the BraTS21 challenge. To find the optimal model architecture and the learning schedule, we have run an extensive ablation study to test: deep supervision loss, Focal loss, decoder attention, drop block, and residual connections. Additionally, we have searched for the optimal depth of the U-Net encoder, number of convolutional channels and post-processing strategy. Our method won the validation phase and took third place in the test phase. We have open-sourced the code to reproduce our BraTS21 submission at the N"},"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":"2110.03352","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2021-10-07T11:44:09Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"b646df5ed8ef08b3302dd3989fc01516cb07a1728f43dfb3e0cdb0cc1db322d7","abstract_canon_sha256":"6b24fd4214bc05ec6302020642c56d79d61824eefb17a772c1fd2f6cf0abcf38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:44.825510Z","signature_b64":"WtT7LvGwI9Ut+ZsfdclpR+0pZvlJHB/qUJ39PdwM+AAYTRqYp8k79cpDHpN5638tNe1JO7zggPbzBtE72GTTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217acf8c0d99206bda784c856ac402854938be0e774b50b8d103223cfd80b0df","last_reissued_at":"2026-07-05T03:43:44.825130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:44.825130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimized U-Net for Brain Tumor Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Alexandre Milesi, Micha{\\l} Futrega, Michal Marcinkiewicz, Pablo Ribalta","submitted_at":"2021-10-07T11:44:09Z","abstract_excerpt":"We propose an optimized U-Net architecture for a brain tumor segmentation task in the BraTS21 challenge. To find the optimal model architecture and the learning schedule, we have run an extensive ablation study to test: deep supervision loss, Focal loss, decoder attention, drop block, and residual connections. Additionally, we have searched for the optimal depth of the U-Net encoder, number of convolutional channels and post-processing strategy. Our method won the validation phase and took third place in the test phase. We have open-sourced the code to reproduce our BraTS21 submission at the N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03352","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/2110.03352/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":"2110.03352","created_at":"2026-07-05T03:43:44.825182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03352v2","created_at":"2026-07-05T03:43:44.825182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03352","created_at":"2026-07-05T03:43:44.825182+00:00"},{"alias_kind":"pith_short_12","alias_value":"EF5M7DANTEQG","created_at":"2026-07-05T03:43:44.825182+00:00"},{"alias_kind":"pith_short_16","alias_value":"EF5M7DANTEQGXWTY","created_at":"2026-07-05T03:43:44.825182+00:00"},{"alias_kind":"pith_short_8","alias_value":"EF5M7DAN","created_at":"2026-07-05T03:43:44.825182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02179","citing_title":"Deep Ensemble approach for Enhancing Brain Tumor Segmentation in Resource-Limited Settings","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV","json":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV.json","graph_json":"https://pith.science/api/pith-number/EF5M7DANTEQGXWTYJSCWVRACQV/graph.json","events_json":"https://pith.science/api/pith-number/EF5M7DANTEQGXWTYJSCWVRACQV/events.json","paper":"https://pith.science/paper/EF5M7DAN"},"agent_actions":{"view_html":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV","download_json":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV.json","view_paper":"https://pith.science/paper/EF5M7DAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03352&json=true","fetch_graph":"https://pith.science/api/pith-number/EF5M7DANTEQGXWTYJSCWVRACQV/graph.json","fetch_events":"https://pith.science/api/pith-number/EF5M7DANTEQGXWTYJSCWVRACQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV/action/storage_attestation","attest_author":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV/action/author_attestation","sign_citation":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV/action/citation_signature","submit_replication":"https://pith.science/pith/EF5M7DANTEQGXWTYJSCWVRACQV/action/replication_record"}},"created_at":"2026-07-05T03:43:44.825182+00:00","updated_at":"2026-07-05T03:43:44.825182+00:00"}