{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JRAO2KZXD2I7I2QHVKFQZKXTXR","short_pith_number":"pith:JRAO2KZX","schema_version":"1.0","canonical_sha256":"4c40ed2b371e91f46a07aa8b0caaf3bc5c34c6cc9fa9f333b5b0cc4abf52792a","source":{"kind":"arxiv","id":"2102.04525","version":4},"attestation_state":"computed","paper":{"title":"Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Carola-Bibiane Sch\\\"onlieb, Evis Sala, Leonardo Rundo, Michael Yeung","submitted_at":"2021-02-08T20:47:38Z","abstract_excerpt":"Automatic segmentation methods are an important advancement in medical image analysis. Machine learning techniques, and deep neural networks in particular, are the state-of-the-art for most medical image segmentation tasks. Issues with class imbalance pose a significant challenge in medical datasets, with lesions often occupying a considerably smaller volume relative to the background. Loss functions used in the training of deep learning algorithms differ in their robustness to class imbalance, with direct consequences for model convergence. The most commonly used loss functions for segmentati"},"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":"2102.04525","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-02-08T20:47:38Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"6f5521e36254007d2ec9b4bfbbee74751fd079d8a5ee43cdbabaaacbb042e0d1","abstract_canon_sha256":"e5273d530c4b1c8eca03ded3c63a9cada1ae97fc2117ad34ccc0232827efca54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:42.894633Z","signature_b64":"8XnRjcIbvA/LsN08JKo2IGYSv9JbIlFKx01WDNK8H2wQ1vNeAEW5JUgnW/UCLGnzXgS76hzsdzf+xJlEDuUyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c40ed2b371e91f46a07aa8b0caaf3bc5c34c6cc9fa9f333b5b0cc4abf52792a","last_reissued_at":"2026-07-05T03:34:42.894225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:42.894225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Carola-Bibiane Sch\\\"onlieb, Evis Sala, Leonardo Rundo, Michael Yeung","submitted_at":"2021-02-08T20:47:38Z","abstract_excerpt":"Automatic segmentation methods are an important advancement in medical image analysis. Machine learning techniques, and deep neural networks in particular, are the state-of-the-art for most medical image segmentation tasks. Issues with class imbalance pose a significant challenge in medical datasets, with lesions often occupying a considerably smaller volume relative to the background. Loss functions used in the training of deep learning algorithms differ in their robustness to class imbalance, with direct consequences for model convergence. The most commonly used loss functions for segmentati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04525","kind":"arxiv","version":4},"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/2102.04525/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":"2102.04525","created_at":"2026-07-05T03:34:42.894280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04525v4","created_at":"2026-07-05T03:34:42.894280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04525","created_at":"2026-07-05T03:34:42.894280+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRAO2KZXD2I7","created_at":"2026-07-05T03:34:42.894280+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRAO2KZXD2I7I2QH","created_at":"2026-07-05T03:34:42.894280+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRAO2KZX","created_at":"2026-07-05T03:34:42.894280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.05892","citing_title":"Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR","json":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR.json","graph_json":"https://pith.science/api/pith-number/JRAO2KZXD2I7I2QHVKFQZKXTXR/graph.json","events_json":"https://pith.science/api/pith-number/JRAO2KZXD2I7I2QHVKFQZKXTXR/events.json","paper":"https://pith.science/paper/JRAO2KZX"},"agent_actions":{"view_html":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR","download_json":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR.json","view_paper":"https://pith.science/paper/JRAO2KZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04525&json=true","fetch_graph":"https://pith.science/api/pith-number/JRAO2KZXD2I7I2QHVKFQZKXTXR/graph.json","fetch_events":"https://pith.science/api/pith-number/JRAO2KZXD2I7I2QHVKFQZKXTXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR/action/storage_attestation","attest_author":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR/action/author_attestation","sign_citation":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR/action/citation_signature","submit_replication":"https://pith.science/pith/JRAO2KZXD2I7I2QHVKFQZKXTXR/action/replication_record"}},"created_at":"2026-07-05T03:34:42.894280+00:00","updated_at":"2026-07-05T03:34:42.894280+00:00"}