{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZRHD5K7GFJV6LAELCLAT4PEMN","short_pith_number":"pith:FZRHD5K7","schema_version":"1.0","canonical_sha256":"2e6271f55f31535f2c04589609f1e4635a5a362596fe3acc5e2d9538a7bfb7d4","source":{"kind":"arxiv","id":"2309.17285","version":1},"attestation_state":"computed","paper":{"title":"Efficient Large Scale Medical Image Dataset Preparation for Machine Learning Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Michael Bucher, Dimitrios Bounias, Jonas Scherer, Klaus Kades, Klaus Maier-Hein, Lisa Kausch, Markus Bujotzek, Philipp Schader, Stefan Denner, Tobias Penzkofer","submitted_at":"2023-09-29T14:41:02Z","abstract_excerpt":"In the rapidly evolving field of medical imaging, machine learning algorithms have become indispensable for enhancing diagnostic accuracy. However, the effectiveness of these algorithms is contingent upon the availability and organization of high-quality medical imaging datasets. Traditional Digital Imaging and Communications in Medicine (DICOM) data management systems are inadequate for handling the scale and complexity of data required to be facilitated in machine learning algorithms. This paper introduces an innovative data curation tool, developed as part of the Kaapana open-source toolkit"},"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":"2309.17285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T14:41:02Z","cross_cats_sorted":[],"title_canon_sha256":"37c28b96b4fcf1b29a6d9757fdf9129ce1790c0b3f43a3ae1d92df0420ac5983","abstract_canon_sha256":"ffc7ff8efb638e540b7deb4099d85818e20e24aaa2b29c6aa52a5a42da45b548"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:43.469400Z","signature_b64":"yxWUBwV0lykV2AcgXVyZDNDkTmN5UdjyQcC2Nb1TeYu+jJCs474KsCyfb1DHcWdoFRohMuyA+QYjNaL53eTqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6271f55f31535f2c04589609f1e4635a5a362596fe3acc5e2d9538a7bfb7d4","last_reissued_at":"2026-07-05T06:55:43.468924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:43.468924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Large Scale Medical Image Dataset Preparation for Machine Learning Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Michael Bucher, Dimitrios Bounias, Jonas Scherer, Klaus Kades, Klaus Maier-Hein, Lisa Kausch, Markus Bujotzek, Philipp Schader, Stefan Denner, Tobias Penzkofer","submitted_at":"2023-09-29T14:41:02Z","abstract_excerpt":"In the rapidly evolving field of medical imaging, machine learning algorithms have become indispensable for enhancing diagnostic accuracy. However, the effectiveness of these algorithms is contingent upon the availability and organization of high-quality medical imaging datasets. Traditional Digital Imaging and Communications in Medicine (DICOM) data management systems are inadequate for handling the scale and complexity of data required to be facilitated in machine learning algorithms. This paper introduces an innovative data curation tool, developed as part of the Kaapana open-source toolkit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17285","kind":"arxiv","version":1},"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/2309.17285/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":"2309.17285","created_at":"2026-07-05T06:55:43.468981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17285v1","created_at":"2026-07-05T06:55:43.468981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17285","created_at":"2026-07-05T06:55:43.468981+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZRHD5K7GFJV","created_at":"2026-07-05T06:55:43.468981+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZRHD5K7GFJV6LAE","created_at":"2026-07-05T06:55:43.468981+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZRHD5K7","created_at":"2026-07-05T06:55:43.468981+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/FZRHD5K7GFJV6LAELCLAT4PEMN","json":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN.json","graph_json":"https://pith.science/api/pith-number/FZRHD5K7GFJV6LAELCLAT4PEMN/graph.json","events_json":"https://pith.science/api/pith-number/FZRHD5K7GFJV6LAELCLAT4PEMN/events.json","paper":"https://pith.science/paper/FZRHD5K7"},"agent_actions":{"view_html":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN","download_json":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN.json","view_paper":"https://pith.science/paper/FZRHD5K7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17285&json=true","fetch_graph":"https://pith.science/api/pith-number/FZRHD5K7GFJV6LAELCLAT4PEMN/graph.json","fetch_events":"https://pith.science/api/pith-number/FZRHD5K7GFJV6LAELCLAT4PEMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN/action/storage_attestation","attest_author":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN/action/author_attestation","sign_citation":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN/action/citation_signature","submit_replication":"https://pith.science/pith/FZRHD5K7GFJV6LAELCLAT4PEMN/action/replication_record"}},"created_at":"2026-07-05T06:55:43.468981+00:00","updated_at":"2026-07-05T06:55:43.468981+00:00"}