{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6HKVCA5WEDMVRFBGRS2ZSBHTOT","short_pith_number":"pith:6HKVCA5W","schema_version":"1.0","canonical_sha256":"f1d55103b620d95894268cb59904f374c44e866148be16c2702da7305aad6d17","source":{"kind":"arxiv","id":"2606.02487","version":1},"attestation_state":"computed","paper":{"title":"Towards Multidisciplinary Summarization of Hospital Stays: Efficient Sentence-Level Clinical Provenance Categorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Karstens, Andrew D. Boyd, Angie Tipton, Barbara Di Eugenio, Baris Karacan, Brianna Clarahan, Catherine K. Craven, Danielle Hitzel, Emily Spellman, Jaewon Bae, Janine Petitgout, Julie Vignato, Karen Dunn Lopez, Kristi Haughey, Lauren Boyd, Lindsey Knake, Mackenzie Weis, Mary Khetani, Natalie Parde, Rachel Dawson, Rajashree Dahal, Vaibhav Bhargava, Vanessa Barbosa, Yu-Shan Tseng","submitted_at":"2026-06-01T16:57:51Z","abstract_excerpt":"Effective \"all-team\" summarization in high-complexity settings like the Neonatal Intensive Care Unit (NICU) requires aggregating insights from diverse disciplines (physicians, nurses, therapists) spread across hundreds of clinical free-text notes. Simply pooling heterogeneous text often leads to incoherent outputs. Structured summarization therefore first requires accurate categorization of sentence-level provenance across multi-source notes. This pilot study introduces a clinical provenance categorization pipeline using supervised fine-tuning (SFT) of large language models (LLMs). We adapted "},"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":"2606.02487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T16:57:51Z","cross_cats_sorted":[],"title_canon_sha256":"6c50406c41810ad823b6e21a1290727f200dd8a6991eec3148dd07ef0d8b8b2b","abstract_canon_sha256":"818292856fe40443210f2cbb9dd5466576b6881f9003ab373a0e6d211486be6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:07.595704Z","signature_b64":"DgyZyTAJno/kqfBP5S8MkkuPMRJUnTFHM3q8wfHCjbsQ7id7fycPqB+92i8p73o7nHHhaqtb/B1V56gJa2l4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1d55103b620d95894268cb59904f374c44e866148be16c2702da7305aad6d17","last_reissued_at":"2026-06-02T03:05:07.595279Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:07.595279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Multidisciplinary Summarization of Hospital Stays: Efficient Sentence-Level Clinical Provenance Categorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Karstens, Andrew D. Boyd, Angie Tipton, Barbara Di Eugenio, Baris Karacan, Brianna Clarahan, Catherine K. Craven, Danielle Hitzel, Emily Spellman, Jaewon Bae, Janine Petitgout, Julie Vignato, Karen Dunn Lopez, Kristi Haughey, Lauren Boyd, Lindsey Knake, Mackenzie Weis, Mary Khetani, Natalie Parde, Rachel Dawson, Rajashree Dahal, Vaibhav Bhargava, Vanessa Barbosa, Yu-Shan Tseng","submitted_at":"2026-06-01T16:57:51Z","abstract_excerpt":"Effective \"all-team\" summarization in high-complexity settings like the Neonatal Intensive Care Unit (NICU) requires aggregating insights from diverse disciplines (physicians, nurses, therapists) spread across hundreds of clinical free-text notes. Simply pooling heterogeneous text often leads to incoherent outputs. Structured summarization therefore first requires accurate categorization of sentence-level provenance across multi-source notes. This pilot study introduces a clinical provenance categorization pipeline using supervised fine-tuning (SFT) of large language models (LLMs). We adapted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02487","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/2606.02487/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":"2606.02487","created_at":"2026-06-02T03:05:07.595343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02487v1","created_at":"2026-06-02T03:05:07.595343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02487","created_at":"2026-06-02T03:05:07.595343+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HKVCA5WEDMV","created_at":"2026-06-02T03:05:07.595343+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HKVCA5WEDMVRFBG","created_at":"2026-06-02T03:05:07.595343+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HKVCA5W","created_at":"2026-06-02T03:05:07.595343+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/6HKVCA5WEDMVRFBGRS2ZSBHTOT","json":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT.json","graph_json":"https://pith.science/api/pith-number/6HKVCA5WEDMVRFBGRS2ZSBHTOT/graph.json","events_json":"https://pith.science/api/pith-number/6HKVCA5WEDMVRFBGRS2ZSBHTOT/events.json","paper":"https://pith.science/paper/6HKVCA5W"},"agent_actions":{"view_html":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT","download_json":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT.json","view_paper":"https://pith.science/paper/6HKVCA5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02487&json=true","fetch_graph":"https://pith.science/api/pith-number/6HKVCA5WEDMVRFBGRS2ZSBHTOT/graph.json","fetch_events":"https://pith.science/api/pith-number/6HKVCA5WEDMVRFBGRS2ZSBHTOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT/action/storage_attestation","attest_author":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT/action/author_attestation","sign_citation":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT/action/citation_signature","submit_replication":"https://pith.science/pith/6HKVCA5WEDMVRFBGRS2ZSBHTOT/action/replication_record"}},"created_at":"2026-06-02T03:05:07.595343+00:00","updated_at":"2026-06-02T03:05:07.595343+00:00"}