{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LBXOZURROXEJMK2E5GERBL2FFY","short_pith_number":"pith:LBXOZURR","schema_version":"1.0","canonical_sha256":"586eecd23175c8962b44e98910af452e19de565be989a55d5add9ce60cb8878b","source":{"kind":"arxiv","id":"1910.13573","version":2},"attestation_state":"computed","paper":{"title":"Semi-Supervised Natural Language Approach for Fine-Grained Classification of Medical Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernardo Bizzo, Bradley Wright, Christopher Bridge, Katherine Andriole, Neil Deshmukh, Ram Naidu, Romane Gauriau, Selin Gumustop, Varun Buch","submitted_at":"2019-10-29T23:25:59Z","abstract_excerpt":"Although machine learning has become a powerful tool to augment doctors in clinical analysis, the immense amount of labeled data that is necessary to train supervised learning approaches burdens each development task as time and resource intensive. The vast majority of dense clinical information is stored in written reports, detailing pertinent patient information. The challenge with utilizing natural language data for standard model development is due to the complex nature of the modality. In this research, a model pipeline was developed to utilize an unsupervised approach to train an encoder"},"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":"1910.13573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-29T23:25:59Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"55fa0d11589a34851c61aa5daefd81cb6bb315313e3eece39e89197e11910937","abstract_canon_sha256":"d2a51871c9de5231266f3bd1dc5c7c7f2e3cc2ce56a6d62262a4e10cedb80ad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:10.986382Z","signature_b64":"iYwHLYx/w40F6abMGa5c78yVnseNVCYSF3PdmUZVl/sqHoh4Zh7ORoOPsCuxMMrjCTad3zr5keLN6Niw1qL5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586eecd23175c8962b44e98910af452e19de565be989a55d5add9ce60cb8878b","last_reissued_at":"2026-07-05T00:19:10.985887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:10.985887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Natural Language Approach for Fine-Grained Classification of Medical Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernardo Bizzo, Bradley Wright, Christopher Bridge, Katherine Andriole, Neil Deshmukh, Ram Naidu, Romane Gauriau, Selin Gumustop, Varun Buch","submitted_at":"2019-10-29T23:25:59Z","abstract_excerpt":"Although machine learning has become a powerful tool to augment doctors in clinical analysis, the immense amount of labeled data that is necessary to train supervised learning approaches burdens each development task as time and resource intensive. The vast majority of dense clinical information is stored in written reports, detailing pertinent patient information. The challenge with utilizing natural language data for standard model development is due to the complex nature of the modality. In this research, a model pipeline was developed to utilize an unsupervised approach to train an encoder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13573","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/1910.13573/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":"1910.13573","created_at":"2026-07-05T00:19:10.985955+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.13573v2","created_at":"2026-07-05T00:19:10.985955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13573","created_at":"2026-07-05T00:19:10.985955+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBXOZURROXEJ","created_at":"2026-07-05T00:19:10.985955+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBXOZURROXEJMK2E","created_at":"2026-07-05T00:19:10.985955+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBXOZURR","created_at":"2026-07-05T00:19:10.985955+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/LBXOZURROXEJMK2E5GERBL2FFY","json":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY.json","graph_json":"https://pith.science/api/pith-number/LBXOZURROXEJMK2E5GERBL2FFY/graph.json","events_json":"https://pith.science/api/pith-number/LBXOZURROXEJMK2E5GERBL2FFY/events.json","paper":"https://pith.science/paper/LBXOZURR"},"agent_actions":{"view_html":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY","download_json":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY.json","view_paper":"https://pith.science/paper/LBXOZURR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.13573&json=true","fetch_graph":"https://pith.science/api/pith-number/LBXOZURROXEJMK2E5GERBL2FFY/graph.json","fetch_events":"https://pith.science/api/pith-number/LBXOZURROXEJMK2E5GERBL2FFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY/action/storage_attestation","attest_author":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY/action/author_attestation","sign_citation":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY/action/citation_signature","submit_replication":"https://pith.science/pith/LBXOZURROXEJMK2E5GERBL2FFY/action/replication_record"}},"created_at":"2026-07-05T00:19:10.985955+00:00","updated_at":"2026-07-05T00:19:10.985955+00:00"}