{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CQZQCNTASWXCQGWCPMUJ3EXRCX","short_pith_number":"pith:CQZQCNTA","schema_version":"1.0","canonical_sha256":"143301366095ae281ac27b289d92f115ce6baa110d09860ec6748f885268bf27","source":{"kind":"arxiv","id":"2312.12442","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Classification System for Breast Cancer Specimen Report (HCSBC) -- an end-to-end model for characterizing severity and diagnosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Christopher R. McAdams, Constance Lehman, Gabriela Oprea-Ilies, Geoffrey Smith, Harish Kamath, Hari Trivedi, Imon Banerjee, Judy Gichoya, Marina Mosunjac, Mary S. Newell, Thiago Santos","submitted_at":"2023-11-02T18:37:45Z","abstract_excerpt":"Automated classification of cancer pathology reports can extract information from unstructured reports and categorize each report into structured diagnosis and severity categories. Thus, such system can reduce the burden for populating tumor registries, help registration for clinical trial as well as developing large dataset for deep learning model development using true pathologic ground truth. However, the content of breast pathology reports can be difficult for categorize due to the high linguistic variability in content and wide variety of potential diagnoses >50. Existing NLP models are p"},"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":"2312.12442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T18:37:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c615fa432a7fec6393af605804c33cf1ffdf6ef53facfd6a268281c74e05a47","abstract_canon_sha256":"0d259b221e91c80be30c4eeae11b31722c384618199b50f5212870344d506010"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:21.006505Z","signature_b64":"HLVTQzYBtsEmIvKz0sn6asiMCyDS0SGNTGQiUgN9rhLrweenPgEDbKJ0y3L5/Gltp7m+nq+ebltj++KyTlH1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"143301366095ae281ac27b289d92f115ce6baa110d09860ec6748f885268bf27","last_reissued_at":"2026-07-05T07:26:21.006090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:21.006090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Classification System for Breast Cancer Specimen Report (HCSBC) -- an end-to-end model for characterizing severity and diagnosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Christopher R. McAdams, Constance Lehman, Gabriela Oprea-Ilies, Geoffrey Smith, Harish Kamath, Hari Trivedi, Imon Banerjee, Judy Gichoya, Marina Mosunjac, Mary S. Newell, Thiago Santos","submitted_at":"2023-11-02T18:37:45Z","abstract_excerpt":"Automated classification of cancer pathology reports can extract information from unstructured reports and categorize each report into structured diagnosis and severity categories. Thus, such system can reduce the burden for populating tumor registries, help registration for clinical trial as well as developing large dataset for deep learning model development using true pathologic ground truth. However, the content of breast pathology reports can be difficult for categorize due to the high linguistic variability in content and wide variety of potential diagnoses >50. Existing NLP models are p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12442","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/2312.12442/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":"2312.12442","created_at":"2026-07-05T07:26:21.006152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12442v1","created_at":"2026-07-05T07:26:21.006152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12442","created_at":"2026-07-05T07:26:21.006152+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQZQCNTASWXC","created_at":"2026-07-05T07:26:21.006152+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQZQCNTASWXCQGWC","created_at":"2026-07-05T07:26:21.006152+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQZQCNTA","created_at":"2026-07-05T07:26:21.006152+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/CQZQCNTASWXCQGWCPMUJ3EXRCX","json":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX.json","graph_json":"https://pith.science/api/pith-number/CQZQCNTASWXCQGWCPMUJ3EXRCX/graph.json","events_json":"https://pith.science/api/pith-number/CQZQCNTASWXCQGWCPMUJ3EXRCX/events.json","paper":"https://pith.science/paper/CQZQCNTA"},"agent_actions":{"view_html":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX","download_json":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX.json","view_paper":"https://pith.science/paper/CQZQCNTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12442&json=true","fetch_graph":"https://pith.science/api/pith-number/CQZQCNTASWXCQGWCPMUJ3EXRCX/graph.json","fetch_events":"https://pith.science/api/pith-number/CQZQCNTASWXCQGWCPMUJ3EXRCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX/action/storage_attestation","attest_author":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX/action/author_attestation","sign_citation":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX/action/citation_signature","submit_replication":"https://pith.science/pith/CQZQCNTASWXCQGWCPMUJ3EXRCX/action/replication_record"}},"created_at":"2026-07-05T07:26:21.006152+00:00","updated_at":"2026-07-05T07:26:21.006152+00:00"}