{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KF3ELOIOJ2MSUVBJHZMHEST4XT","short_pith_number":"pith:KF3ELOIO","schema_version":"1.0","canonical_sha256":"517645b90e4e992a54293e58724a7cbcd68e2a2f6a6f31a944406064fe5224b4","source":{"kind":"arxiv","id":"2507.03033","version":1},"attestation_state":"computed","paper":{"title":"Preserving Privacy, Increasing Accessibility, and Reducing Cost: An On-Device Artificial Intelligence Model for Medical Transcription and Note Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ayush Mudgal, Dhruv Diddi, Johnson Thomas, Nisten Tahiraj, Wendao Liu, Zeeshaan Mohammed","submitted_at":"2025-07-03T01:51:49Z","abstract_excerpt":"Background: Clinical documentation represents a significant burden for healthcare providers, with physicians spending up to 2 hours daily on administrative tasks. Recent advances in large language models (LLMs) offer promising solutions, but privacy concerns and computational requirements limit their adoption in healthcare settings. Objective: To develop and evaluate a privacy-preserving, on-device medical transcription system using a fine-tuned Llama 3.2 1B model capable of generating structured medical notes from medical transcriptions while maintaining complete data sovereignty entirely in "},"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":"2507.03033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T01:51:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4078a456f76438619d9b948cece37556cf6123583b4a3aee5188d266927f1474","abstract_canon_sha256":"1fd369e796b0aaf81d49bb333e61cb91849268864877a47688ea6761ea9a14da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:51.103288Z","signature_b64":"1en3fao+D/HaWFh398gRvC0HYFMHq59uBeeiobeVECLFhSpKJuyDwAUnNXtSF3DVp/nsEHF+NYdj43Qcz2dwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517645b90e4e992a54293e58724a7cbcd68e2a2f6a6f31a944406064fe5224b4","last_reissued_at":"2026-07-05T11:31:51.102812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:51.102812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preserving Privacy, Increasing Accessibility, and Reducing Cost: An On-Device Artificial Intelligence Model for Medical Transcription and Note Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ayush Mudgal, Dhruv Diddi, Johnson Thomas, Nisten Tahiraj, Wendao Liu, Zeeshaan Mohammed","submitted_at":"2025-07-03T01:51:49Z","abstract_excerpt":"Background: Clinical documentation represents a significant burden for healthcare providers, with physicians spending up to 2 hours daily on administrative tasks. Recent advances in large language models (LLMs) offer promising solutions, but privacy concerns and computational requirements limit their adoption in healthcare settings. Objective: To develop and evaluate a privacy-preserving, on-device medical transcription system using a fine-tuned Llama 3.2 1B model capable of generating structured medical notes from medical transcriptions while maintaining complete data sovereignty entirely in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03033","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/2507.03033/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":"2507.03033","created_at":"2026-07-05T11:31:51.102869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03033v1","created_at":"2026-07-05T11:31:51.102869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03033","created_at":"2026-07-05T11:31:51.102869+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF3ELOIOJ2MS","created_at":"2026-07-05T11:31:51.102869+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF3ELOIOJ2MSUVBJ","created_at":"2026-07-05T11:31:51.102869+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF3ELOIO","created_at":"2026-07-05T11:31:51.102869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25273","citing_title":"LLM-as-a-Judge in Healthcare: A Scoping Analysis of Applications, Methods, and Human Alignment","ref_index":146,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT","json":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT.json","graph_json":"https://pith.science/api/pith-number/KF3ELOIOJ2MSUVBJHZMHEST4XT/graph.json","events_json":"https://pith.science/api/pith-number/KF3ELOIOJ2MSUVBJHZMHEST4XT/events.json","paper":"https://pith.science/paper/KF3ELOIO"},"agent_actions":{"view_html":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT","download_json":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT.json","view_paper":"https://pith.science/paper/KF3ELOIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03033&json=true","fetch_graph":"https://pith.science/api/pith-number/KF3ELOIOJ2MSUVBJHZMHEST4XT/graph.json","fetch_events":"https://pith.science/api/pith-number/KF3ELOIOJ2MSUVBJHZMHEST4XT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT/action/storage_attestation","attest_author":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT/action/author_attestation","sign_citation":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT/action/citation_signature","submit_replication":"https://pith.science/pith/KF3ELOIOJ2MSUVBJHZMHEST4XT/action/replication_record"}},"created_at":"2026-07-05T11:31:51.102869+00:00","updated_at":"2026-07-05T11:31:51.102869+00:00"}