{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GQEGXZPGJV7IIGUCDJ2RKN72YM","short_pith_number":"pith:GQEGXZPG","schema_version":"1.0","canonical_sha256":"34086be5e64d7e841a821a751537fac301450900fcd40e93cd8000680ed3d0e1","source":{"kind":"arxiv","id":"2005.01795","version":3},"attestation_state":"computed","paper":{"title":"Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jeffrey P. Bigham, Kundan Krishna, Sopan Khosla, Zachary C. Lipton","submitted_at":"2020-05-04T19:10:26Z","abstract_excerpt":"Following each patient visit, physicians draft long semi-structured clinical summaries called SOAP notes. While invaluable to clinicians and researchers, creating digital SOAP notes is burdensome, contributing to physician burnout. In this paper, we introduce the first complete pipelines to leverage deep summarization models to generate these notes based on transcripts of conversations between physicians and patients. After exploring a spectrum of methods across the extractive-abstractive spectrum, we propose Cluster2Sent, an algorithm that (i) extracts important utterances relevant to each su"},"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":"2005.01795","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T19:10:26Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"fefceecc34a362ff8fd3501ad6eaa4ca252c6e7f4263ebd98955de491d9151b5","abstract_canon_sha256":"b8cd6714be21ac60a766b3f5bedac575dbb623bdda497f1e59ee679fd746d075"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:32.122161Z","signature_b64":"Zz5UD5rcR+FhkPkxZIjQDOzQDg51Bi3ZChB6alIbsvW7YXSApKq3r/oBtWvQ5ikacmfmITg9ZzX9qmI0b5a3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34086be5e64d7e841a821a751537fac301450900fcd40e93cd8000680ed3d0e1","last_reissued_at":"2026-07-05T02:45:32.121791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:32.121791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jeffrey P. Bigham, Kundan Krishna, Sopan Khosla, Zachary C. Lipton","submitted_at":"2020-05-04T19:10:26Z","abstract_excerpt":"Following each patient visit, physicians draft long semi-structured clinical summaries called SOAP notes. While invaluable to clinicians and researchers, creating digital SOAP notes is burdensome, contributing to physician burnout. In this paper, we introduce the first complete pipelines to leverage deep summarization models to generate these notes based on transcripts of conversations between physicians and patients. After exploring a spectrum of methods across the extractive-abstractive spectrum, we propose Cluster2Sent, an algorithm that (i) extracts important utterances relevant to each su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01795","kind":"arxiv","version":3},"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/2005.01795/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":"2005.01795","created_at":"2026-07-05T02:45:32.121847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.01795v3","created_at":"2026-07-05T02:45:32.121847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01795","created_at":"2026-07-05T02:45:32.121847+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQEGXZPGJV7I","created_at":"2026-07-05T02:45:32.121847+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQEGXZPGJV7IIGUC","created_at":"2026-07-05T02:45:32.121847+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQEGXZPG","created_at":"2026-07-05T02:45:32.121847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04254","citing_title":"CLINICSUM: Utilizing Language Models for Generating Clinical Summaries from Patient-Doctor Conversations","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM","json":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM.json","graph_json":"https://pith.science/api/pith-number/GQEGXZPGJV7IIGUCDJ2RKN72YM/graph.json","events_json":"https://pith.science/api/pith-number/GQEGXZPGJV7IIGUCDJ2RKN72YM/events.json","paper":"https://pith.science/paper/GQEGXZPG"},"agent_actions":{"view_html":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM","download_json":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM.json","view_paper":"https://pith.science/paper/GQEGXZPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.01795&json=true","fetch_graph":"https://pith.science/api/pith-number/GQEGXZPGJV7IIGUCDJ2RKN72YM/graph.json","fetch_events":"https://pith.science/api/pith-number/GQEGXZPGJV7IIGUCDJ2RKN72YM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM/action/storage_attestation","attest_author":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM/action/author_attestation","sign_citation":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM/action/citation_signature","submit_replication":"https://pith.science/pith/GQEGXZPGJV7IIGUCDJ2RKN72YM/action/replication_record"}},"created_at":"2026-07-05T02:45:32.121847+00:00","updated_at":"2026-07-05T02:45:32.121847+00:00"}