{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XO6O2YTHDETAQSAONDI2O75FP6","short_pith_number":"pith:XO6O2YTH","schema_version":"1.0","canonical_sha256":"bbbced6267192608480e68d1a77fa57fb0c34f52561628d3f3ba8f7611c06f11","source":{"kind":"arxiv","id":"2404.03010","version":2},"attestation_state":"computed","paper":{"title":"Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Balint Kovacs, Constantin Ulrich, Fabian Isensee, Jens Kleesiek, Klaus Maier-Hein, Maximilian R. Rokuss, Maximilian Zenk, Philipp Vollmuth, Saikat Roy, Tassilo Wald, Yannick Kirchhoff","submitted_at":"2024-04-03T18:42:19Z","abstract_excerpt":"Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and memory overheads. This "},"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":"2404.03010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-04-03T18:42:19Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"50df64d4c0ca963e12a62e5cd6967a2e6d658d00d457497f83541e5462c08a45","abstract_canon_sha256":"c405d7f14d2e3ee3a295200767da04bf9af08de9c7b37ec99bfbbd896576e09c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:53.104027Z","signature_b64":"uySD1RsdCvWbsAr4uIetG8BWSUh+pSgyhbfTXVhpLF3WTIhscPGzKMb9lg6qn6ZCIkt+MMl2hMPk2/mi9JQDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbbced6267192608480e68d1a77fa57fb0c34f52561628d3f3ba8f7611c06f11","last_reissued_at":"2026-07-05T08:44:53.103569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:53.103569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Balint Kovacs, Constantin Ulrich, Fabian Isensee, Jens Kleesiek, Klaus Maier-Hein, Maximilian R. Rokuss, Maximilian Zenk, Philipp Vollmuth, Saikat Roy, Tassilo Wald, Yannick Kirchhoff","submitted_at":"2024-04-03T18:42:19Z","abstract_excerpt":"Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and memory overheads. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03010","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/2404.03010/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":"2404.03010","created_at":"2026-07-05T08:44:53.103629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03010v2","created_at":"2026-07-05T08:44:53.103629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03010","created_at":"2026-07-05T08:44:53.103629+00:00"},{"alias_kind":"pith_short_12","alias_value":"XO6O2YTHDETA","created_at":"2026-07-05T08:44:53.103629+00:00"},{"alias_kind":"pith_short_16","alias_value":"XO6O2YTHDETAQSAO","created_at":"2026-07-05T08:44:53.103629+00:00"},{"alias_kind":"pith_short_8","alias_value":"XO6O2YTH","created_at":"2026-07-05T08:44:53.103629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29085","citing_title":"Complete virtual unwrapping and reading of a rolled Herculaneum papyrus","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6","json":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6.json","graph_json":"https://pith.science/api/pith-number/XO6O2YTHDETAQSAONDI2O75FP6/graph.json","events_json":"https://pith.science/api/pith-number/XO6O2YTHDETAQSAONDI2O75FP6/events.json","paper":"https://pith.science/paper/XO6O2YTH"},"agent_actions":{"view_html":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6","download_json":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6.json","view_paper":"https://pith.science/paper/XO6O2YTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03010&json=true","fetch_graph":"https://pith.science/api/pith-number/XO6O2YTHDETAQSAONDI2O75FP6/graph.json","fetch_events":"https://pith.science/api/pith-number/XO6O2YTHDETAQSAONDI2O75FP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6/action/storage_attestation","attest_author":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6/action/author_attestation","sign_citation":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6/action/citation_signature","submit_replication":"https://pith.science/pith/XO6O2YTHDETAQSAONDI2O75FP6/action/replication_record"}},"created_at":"2026-07-05T08:44:53.103629+00:00","updated_at":"2026-07-05T08:44:53.103629+00:00"}