{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GEKB6WY7DPKC77BZSGRZEUHQWJ","short_pith_number":"pith:GEKB6WY7","schema_version":"1.0","canonical_sha256":"31141f5b1f1bd42ffc3991a39250f0b268097c158aade3156375dbb75c479b95","source":{"kind":"arxiv","id":"2411.06713","version":1},"attestation_state":"computed","paper":{"title":"Ambient AI Scribing Support: Comparing the Performance of Specialized AI Agentic Architecture to Leading Foundational Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chanseo Lee, Kimon A. Vogt, Sam Meraj, Sonu Kumar","submitted_at":"2024-11-11T04:45:48Z","abstract_excerpt":"This study compares Sporo Health's AI Scribe, a proprietary model fine-tuned for medical scribing, with various LLMs (GPT-4o, GPT-3.5, Gemma-9B, and Llama-3.2-3B) in clinical documentation. We analyzed de-identified patient transcripts from partner clinics, using clinician-provided SOAP notes as the ground truth. Each model generated SOAP summaries using zero-shot prompting, with performance assessed via recall, precision, and F1 scores. Sporo outperformed all models, achieving the highest recall (73.3%), precision (78.6%), and F1 score (75.3%) with the lowest performance variance. Statistical"},"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":"2411.06713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-11T04:45:48Z","cross_cats_sorted":[],"title_canon_sha256":"bf04a3f47f7e7623b1aebafaabce25bdcbe66ffff2537b794bff09be558512f7","abstract_canon_sha256":"1dd1e0ede07ed3fe26f4c1377da5ed1caf3a18803007560977136eba68b6b14e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:50.431412Z","signature_b64":"6m9ImNEbsoOB+rzCmZBen8p8EeObCfzqF1XXJKTdzr22aaBUleKIrnywKB8HeM/qS4tL8L6XmsfGG21P35WhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31141f5b1f1bd42ffc3991a39250f0b268097c158aade3156375dbb75c479b95","last_reissued_at":"2026-07-05T09:33:50.430988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:50.430988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ambient AI Scribing Support: Comparing the Performance of Specialized AI Agentic Architecture to Leading Foundational Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chanseo Lee, Kimon A. Vogt, Sam Meraj, Sonu Kumar","submitted_at":"2024-11-11T04:45:48Z","abstract_excerpt":"This study compares Sporo Health's AI Scribe, a proprietary model fine-tuned for medical scribing, with various LLMs (GPT-4o, GPT-3.5, Gemma-9B, and Llama-3.2-3B) in clinical documentation. We analyzed de-identified patient transcripts from partner clinics, using clinician-provided SOAP notes as the ground truth. Each model generated SOAP summaries using zero-shot prompting, with performance assessed via recall, precision, and F1 scores. Sporo outperformed all models, achieving the highest recall (73.3%), precision (78.6%), and F1 score (75.3%) with the lowest performance variance. Statistical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06713","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/2411.06713/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":"2411.06713","created_at":"2026-07-05T09:33:50.431042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06713v1","created_at":"2026-07-05T09:33:50.431042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06713","created_at":"2026-07-05T09:33:50.431042+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEKB6WY7DPKC","created_at":"2026-07-05T09:33:50.431042+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEKB6WY7DPKC77BZ","created_at":"2026-07-05T09:33:50.431042+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEKB6WY7","created_at":"2026-07-05T09:33:50.431042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22902","citing_title":"Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ","json":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ.json","graph_json":"https://pith.science/api/pith-number/GEKB6WY7DPKC77BZSGRZEUHQWJ/graph.json","events_json":"https://pith.science/api/pith-number/GEKB6WY7DPKC77BZSGRZEUHQWJ/events.json","paper":"https://pith.science/paper/GEKB6WY7"},"agent_actions":{"view_html":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ","download_json":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ.json","view_paper":"https://pith.science/paper/GEKB6WY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06713&json=true","fetch_graph":"https://pith.science/api/pith-number/GEKB6WY7DPKC77BZSGRZEUHQWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GEKB6WY7DPKC77BZSGRZEUHQWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ/action/storage_attestation","attest_author":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ/action/author_attestation","sign_citation":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ/action/citation_signature","submit_replication":"https://pith.science/pith/GEKB6WY7DPKC77BZSGRZEUHQWJ/action/replication_record"}},"created_at":"2026-07-05T09:33:50.431042+00:00","updated_at":"2026-07-05T09:33:50.431042+00:00"}