{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UONY2ZU4VCLPI7G744FB4HYO62","short_pith_number":"pith:UONY2ZU4","schema_version":"1.0","canonical_sha256":"a39b8d669ca896f47cdfe70a1e1f0ef69f1bbff56dad22f9dd829ef7702c03d2","source":{"kind":"arxiv","id":"2407.09064","version":2},"attestation_state":"computed","paper":{"title":"Multi-Modal Dataset Creation for Federated Learning with DICOM Structured Reports","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Meyer, Andreas Leha, Anja Hennemuth, Clemens Scherer, Eike Nagel, Florian Andr\\'e, Gerhard Diller, Halvar Kelm, Jan Moritz Seliger, Lars Kaderali, Lukas Burger, Malte T\\\"olle, Moritz Seiffert, Nina Kr\\\"uger, Norbert Frey, Peter Bannas, Philipp Garthe, Sandy Engelhardt, Simon Martin, Stefan Gro{\\ss}, Stefan Orwat, Stefan Simm, Tim Friede, Tim Seidler","submitted_at":"2024-07-12T07:34:10Z","abstract_excerpt":"Purpose: Federated training is often hindered by heterogeneous datasets due to divergent data storage options, inconsistent naming schemes, varied annotation procedures, and disparities in label quality. This is particularly evident in the emerging multi-modal learning paradigms, where dataset harmonization including a uniform data representation and filtering options are of paramount importance.\n  Methods: DICOM structured reports enable the standardized linkage of arbitrary information beyond the imaging domain and can be used within Python deep learning pipelines with highdicom. Building on"},"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":"2407.09064","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-12T07:34:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"50bc0eb31f1f259dc515f1ee75706bd9e22bede1ef0a229f95c17e71f5fedd74","abstract_canon_sha256":"a4350728d1b147daae62c7fafdbe158d6b50af0009ebe242fa2bf806390a0061"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:36.269085Z","signature_b64":"cA+NYpY5kgBCwL1q1mU5hwclnWQ3HI1km9ZeWNyq+AlR4+ADM1p94BKFfkw+27nTktMy76PzY9528nRd4s/4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a39b8d669ca896f47cdfe70a1e1f0ef69f1bbff56dad22f9dd829ef7702c03d2","last_reissued_at":"2026-07-05T08:52:36.268590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:36.268590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Dataset Creation for Federated Learning with DICOM Structured Reports","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Meyer, Andreas Leha, Anja Hennemuth, Clemens Scherer, Eike Nagel, Florian Andr\\'e, Gerhard Diller, Halvar Kelm, Jan Moritz Seliger, Lars Kaderali, Lukas Burger, Malte T\\\"olle, Moritz Seiffert, Nina Kr\\\"uger, Norbert Frey, Peter Bannas, Philipp Garthe, Sandy Engelhardt, Simon Martin, Stefan Gro{\\ss}, Stefan Orwat, Stefan Simm, Tim Friede, Tim Seidler","submitted_at":"2024-07-12T07:34:10Z","abstract_excerpt":"Purpose: Federated training is often hindered by heterogeneous datasets due to divergent data storage options, inconsistent naming schemes, varied annotation procedures, and disparities in label quality. This is particularly evident in the emerging multi-modal learning paradigms, where dataset harmonization including a uniform data representation and filtering options are of paramount importance.\n  Methods: DICOM structured reports enable the standardized linkage of arbitrary information beyond the imaging domain and can be used within Python deep learning pipelines with highdicom. Building on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09064","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/2407.09064/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":"2407.09064","created_at":"2026-07-05T08:52:36.268648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09064v2","created_at":"2026-07-05T08:52:36.268648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09064","created_at":"2026-07-05T08:52:36.268648+00:00"},{"alias_kind":"pith_short_12","alias_value":"UONY2ZU4VCLP","created_at":"2026-07-05T08:52:36.268648+00:00"},{"alias_kind":"pith_short_16","alias_value":"UONY2ZU4VCLPI7G7","created_at":"2026-07-05T08:52:36.268648+00:00"},{"alias_kind":"pith_short_8","alias_value":"UONY2ZU4","created_at":"2026-07-05T08:52:36.268648+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/UONY2ZU4VCLPI7G744FB4HYO62","json":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62.json","graph_json":"https://pith.science/api/pith-number/UONY2ZU4VCLPI7G744FB4HYO62/graph.json","events_json":"https://pith.science/api/pith-number/UONY2ZU4VCLPI7G744FB4HYO62/events.json","paper":"https://pith.science/paper/UONY2ZU4"},"agent_actions":{"view_html":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62","download_json":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62.json","view_paper":"https://pith.science/paper/UONY2ZU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09064&json=true","fetch_graph":"https://pith.science/api/pith-number/UONY2ZU4VCLPI7G744FB4HYO62/graph.json","fetch_events":"https://pith.science/api/pith-number/UONY2ZU4VCLPI7G744FB4HYO62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62/action/storage_attestation","attest_author":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62/action/author_attestation","sign_citation":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62/action/citation_signature","submit_replication":"https://pith.science/pith/UONY2ZU4VCLPI7G744FB4HYO62/action/replication_record"}},"created_at":"2026-07-05T08:52:36.268648+00:00","updated_at":"2026-07-05T08:52:36.268648+00:00"}