{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7C3I6F4FKYYJ6CWYCAQ22AA5DK","short_pith_number":"pith:7C3I6F4F","canonical_record":{"source":{"id":"1801.00096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.med-ph","submitted_at":"2017-12-30T07:56:46Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"5119169a998501992b7b28f75b23cca790c70e736b3cf1bfb7242f9387f65d22","abstract_canon_sha256":"39159b70af8cd7e6af490cddc223a142111756b11b8fe4492a65d682818cb10a"},"schema_version":"1.0"},"canonical_sha256":"f8b68f178556309f0ad81021ad001d1ab503aa242d18ae0c07f48d86e2b5d953","source":{"kind":"arxiv","id":"1801.00096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00096","created_at":"2026-05-18T00:26:59Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00096v1","created_at":"2026-05-18T00:26:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00096","created_at":"2026-05-18T00:26:59Z"},{"alias_kind":"pith_short_12","alias_value":"7C3I6F4FKYYJ","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"7C3I6F4FKYYJ6CWY","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"7C3I6F4F","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7C3I6F4FKYYJ6CWYCAQ22AA5DK","target":"record","payload":{"canonical_record":{"source":{"id":"1801.00096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.med-ph","submitted_at":"2017-12-30T07:56:46Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"5119169a998501992b7b28f75b23cca790c70e736b3cf1bfb7242f9387f65d22","abstract_canon_sha256":"39159b70af8cd7e6af490cddc223a142111756b11b8fe4492a65d682818cb10a"},"schema_version":"1.0"},"canonical_sha256":"f8b68f178556309f0ad81021ad001d1ab503aa242d18ae0c07f48d86e2b5d953","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:59.465181Z","signature_b64":"frF2hA+tvPjDyT1DzGEJyGYvaMufU7kx6jWKLUYq2rqEWRW206f8FIB6QNVpyMjWyqsXK/eXYQJlq+ZhxYvxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8b68f178556309f0ad81021ad001d1ab503aa242d18ae0c07f48d86e2b5d953","last_reissued_at":"2026-05-18T00:26:59.464563Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:59.464563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.00096","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdU7NuetYXQYXl93k6oGwibzBWQQMf9Qei0+gvIgZ3u/nuQGRiKJrALFLbFxp0ef/x981ixvF7m06NIjVjmqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:35:48.448466Z"},"content_sha256":"0954a75045f431a00464231662c4ba70d5ba6f8cbcb9b27625fc91340aae5269","schema_version":"1.0","event_id":"sha256:0954a75045f431a00464231662c4ba70d5ba6f8cbcb9b27625fc91340aae5269"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7C3I6F4FKYYJ6CWYCAQ22AA5DK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards automated patient data cleaning using deep learning: A feasibility study on the standardization of organ labeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"physics.med-ph","authors_text":"Mingli Chen, Steve Jiang, Timothy Rozario, Troy Long, Weiguo Lu","submitted_at":"2017-12-30T07:56:46Z","abstract_excerpt":"Data cleaning consumes about 80% of the time spent on data analysis for clinical research projects. This is a much bigger problem in the era of big data and machine learning in the field of medicine where large volumes of data are being generated. We report an initial effort towards automated patient data cleaning using deep learning: the standardization of organ labeling in radiation therapy. Organs are often labeled inconsistently at different institutions (sometimes even within the same institution) and at different time periods, which poses a problem for clinical research, especially for m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00096","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rwJf+CgqrdBbcGtDRL6iXrVeTpO93S306Nl8g5uo0vdYp9u7tY0n8QG4zM19LFoxjFxwKbVGG/RlvpYglEOSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:35:48.449137Z"},"content_sha256":"a5e65e251811288067a33db0bae677a8d0605e983c7653166fdc3a798a06c686","schema_version":"1.0","event_id":"sha256:a5e65e251811288067a33db0bae677a8d0605e983c7653166fdc3a798a06c686"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7C3I6F4FKYYJ6CWYCAQ22AA5DK/bundle.json","state_url":"https://pith.science/pith/7C3I6F4FKYYJ6CWYCAQ22AA5DK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7C3I6F4FKYYJ6CWYCAQ22AA5DK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T07:35:48Z","links":{"resolver":"https://pith.science/pith/7C3I6F4FKYYJ6CWYCAQ22AA5DK","bundle":"https://pith.science/pith/7C3I6F4FKYYJ6CWYCAQ22AA5DK/bundle.json","state":"https://pith.science/pith/7C3I6F4FKYYJ6CWYCAQ22AA5DK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7C3I6F4FKYYJ6CWYCAQ22AA5DK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7C3I6F4FKYYJ6CWYCAQ22AA5DK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"39159b70af8cd7e6af490cddc223a142111756b11b8fe4492a65d682818cb10a","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.med-ph","submitted_at":"2017-12-30T07:56:46Z","title_canon_sha256":"5119169a998501992b7b28f75b23cca790c70e736b3cf1bfb7242f9387f65d22"},"schema_version":"1.0","source":{"id":"1801.00096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00096","created_at":"2026-05-18T00:26:59Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00096v1","created_at":"2026-05-18T00:26:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00096","created_at":"2026-05-18T00:26:59Z"},{"alias_kind":"pith_short_12","alias_value":"7C3I6F4FKYYJ","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"7C3I6F4FKYYJ6CWY","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"7C3I6F4F","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:a5e65e251811288067a33db0bae677a8d0605e983c7653166fdc3a798a06c686","target":"graph","created_at":"2026-05-18T00:26:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Data cleaning consumes about 80% of the time spent on data analysis for clinical research projects. This is a much bigger problem in the era of big data and machine learning in the field of medicine where large volumes of data are being generated. We report an initial effort towards automated patient data cleaning using deep learning: the standardization of organ labeling in radiation therapy. Organs are often labeled inconsistently at different institutions (sometimes even within the same institution) and at different time periods, which poses a problem for clinical research, especially for m","authors_text":"Mingli Chen, Steve Jiang, Timothy Rozario, Troy Long, Weiguo Lu","cross_cats":["cs.CV","cs.LG","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.med-ph","submitted_at":"2017-12-30T07:56:46Z","title":"Towards automated patient data cleaning using deep learning: A feasibility study on the standardization of organ labeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00096","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0954a75045f431a00464231662c4ba70d5ba6f8cbcb9b27625fc91340aae5269","target":"record","created_at":"2026-05-18T00:26:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"39159b70af8cd7e6af490cddc223a142111756b11b8fe4492a65d682818cb10a","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.med-ph","submitted_at":"2017-12-30T07:56:46Z","title_canon_sha256":"5119169a998501992b7b28f75b23cca790c70e736b3cf1bfb7242f9387f65d22"},"schema_version":"1.0","source":{"id":"1801.00096","kind":"arxiv","version":1}},"canonical_sha256":"f8b68f178556309f0ad81021ad001d1ab503aa242d18ae0c07f48d86e2b5d953","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8b68f178556309f0ad81021ad001d1ab503aa242d18ae0c07f48d86e2b5d953","first_computed_at":"2026-05-18T00:26:59.464563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:59.464563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"frF2hA+tvPjDyT1DzGEJyGYvaMufU7kx6jWKLUYq2rqEWRW206f8FIB6QNVpyMjWyqsXK/eXYQJlq+ZhxYvxCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:59.465181Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.00096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0954a75045f431a00464231662c4ba70d5ba6f8cbcb9b27625fc91340aae5269","sha256:a5e65e251811288067a33db0bae677a8d0605e983c7653166fdc3a798a06c686"],"state_sha256":"8277a473f78f87959811ae193258052b30719e457906ca4f704435ae0efcb983"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6q65f82bNesuHlsIeyILU/y16AJAox4o17e7+2ohPUZyzo+7p0Y1Jt9ChuvyulImLEwemhkvoOqPoAwdRom0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:35:48.452677Z","bundle_sha256":"884b7a5d3be0d1cbf3cc4ab71712cfb37481c5e2519085be04e2ade37435f8fc"}}