{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E7FSBVEFZARIN5HMVEI66U3LWD","short_pith_number":"pith:E7FSBVEF","schema_version":"1.0","canonical_sha256":"27cb20d485c82286f4eca911ef536bb0f0a6e4131f8ce8fecb5c5ca78973da14","source":{"kind":"arxiv","id":"2602.17513","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Supervised clinical section segmentation models drop in performance when moving from MIMIC-III to obstetrics notes, while zero-shot models remain robust after correcting for hallucinated headers.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Di Eugenio, Baris Karacan, Patrick Thornton","submitted_at":"2026-02-19T16:25:07Z","abstract_excerpt":"Clinical free-text notes contain vital patient information. They are structured into labelled sections; recognizing these sections has been shown to support clinical decision-making and downstream NLP tasks. In this paper, we advance clinical section segmentation through three key contributions. First, we curate a new de-identified, section-labeled obstetrics notes dataset, to supplement the medical domains covered in public corpora such as MIMIC-III, on which most existing segmentation approaches are trained. Second, we systematically evaluate transformer-based supervised models for section s"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.17513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T16:25:07Z","cross_cats_sorted":[],"title_canon_sha256":"3a6c065996f56b3e4c50f5016062c371bcb30d5241a334dda3a4eafd87d9f725","abstract_canon_sha256":"172cfb676ceba420b1195d411313137bc6a886ad43f4a0c88b51c377df50f8dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:43.871513Z","signature_b64":"T4+WNFbStzeTllxVzRT/A3MSEdrWThyLtaTMmXWr/+FgNxpilvPJkpl+2qxBL6qFd0f/niCGil6ykV/75j71Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27cb20d485c82286f4eca911ef536bb0f0a6e4131f8ce8fecb5c5ca78973da14","last_reissued_at":"2026-06-02T01:03:43.870982Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:43.870982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Supervised clinical section segmentation models drop in performance when moving from MIMIC-III to obstetrics notes, while zero-shot models remain robust after correcting for hallucinated headers.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Di Eugenio, Baris Karacan, Patrick Thornton","submitted_at":"2026-02-19T16:25:07Z","abstract_excerpt":"Clinical free-text notes contain vital patient information. They are structured into labelled sections; recognizing these sections has been shown to support clinical decision-making and downstream NLP tasks. In this paper, we advance clinical section segmentation through three key contributions. First, we curate a new de-identified, section-labeled obstetrics notes dataset, to supplement the medical domains covered in public corpora such as MIMIC-III, on which most existing segmentation approaches are trained. Second, we systematically evaluate transformer-based supervised models for section s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"while supervised models perform strongly in-domain, their performance drops substantially out-of-domain. In contrast, zero-shot models demonstrate robust out-of-domain adaptability once hallucinated section headers are corrected.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The new obstetrics dataset is representative of the broader domain and that manual correction of hallucinations provides a fair, scalable basis for comparing model performance.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Supervised clinical section segmentation models perform strongly in-domain on MIMIC-III but degrade substantially out-of-domain on a new obstetrics dataset, whereas zero-shot LLMs show robust cross-domain performance after hallucination correction.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Supervised clinical section segmentation models drop in performance when moving from MIMIC-III to obstetrics notes, while zero-shot models remain robust after correcting for hallucinated headers.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f84110bdb8561e7df3e0ccbe2c5f9530ae2e610cdccf4a587f35660397e0db1d"},"source":{"id":"2602.17513","kind":"arxiv","version":2},"verdict":{"id":"606d2148-e22b-4e64-bf15-5e66a636719a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:51:55.012614Z","strongest_claim":"while supervised models perform strongly in-domain, their performance drops substantially out-of-domain. In contrast, zero-shot models demonstrate robust out-of-domain adaptability once hallucinated section headers are corrected.","one_line_summary":"Supervised clinical section segmentation models perform strongly in-domain on MIMIC-III but degrade substantially out-of-domain on a new obstetrics dataset, whereas zero-shot LLMs show robust cross-domain performance after hallucination correction.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The new obstetrics dataset is representative of the broader domain and that manual correction of hallucinations provides a fair, scalable basis for comparing model performance.","pith_extraction_headline":"Supervised clinical section segmentation models drop in performance when moving from MIMIC-III to obstetrics notes, while zero-shot models remain robust after correcting for hallucinated headers."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.17513/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":24,"sample":[{"doi":"","year":2021,"title":"Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics","work_id":"ee048cf4-d010-48bb-82ab-878826013785","ref_index":1,"cited_arxiv_id":"2602.17513","is_internal_anchor":true},{"doi":"","year":null,"title":"ONC serves as a realistic benchmark for studying section segmentation in underexplored clinical subdo- mains and is intended for community reuse","work_id":"b73dc831-2aa8-45d8-b8c0-c0868edd642a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Domain-Specific Evaluation of Supervised Models:We assess whether transformer- based supervised models originally trained on public datasets can effectively generalize to obstetrics notes. By comparin","work_id":"47784246-752b-4e2f-b0be-ff9762b50c18","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Our exper- iments reveal challenges (e.g., hallucinated section headers) as well as the potential ben- efits of zero-shot strategies, especially when annotated data are scarce","work_id":"5eba15b0-04d0-4ec6-8f68-5343728be72a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"Related Work Before the emergence of advanced machine learn- ing and NLP techniques, early approaches to clin- ical section segmentation primarily relied on rule- based methods. Denny et al. (2008), f","work_id":"bcadcf55-8118-41dd-847c-788503519ce6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":24,"snapshot_sha256":"f758c4cf6c8f2a5907b749623bce36c2fd023bd4213a9ff7564c9be6cd31ca33","internal_anchors":4},"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":"2602.17513","created_at":"2026-06-02T01:03:43.871048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.17513v2","created_at":"2026-06-02T01:03:43.871048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17513","created_at":"2026-06-02T01:03:43.871048+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7FSBVEFZARI","created_at":"2026-06-02T01:03:43.871048+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7FSBVEFZARIN5HM","created_at":"2026-06-02T01:03:43.871048+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7FSBVEF","created_at":"2026-06-02T01:03:43.871048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2602.17513","citing_title":"Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23059","citing_title":"Implicit Framing in Obstetric Counseling Notes: A Grounded LLM Pipeline on a VBAC-Eligible Cohort","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD","json":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD.json","graph_json":"https://pith.science/api/pith-number/E7FSBVEFZARIN5HMVEI66U3LWD/graph.json","events_json":"https://pith.science/api/pith-number/E7FSBVEFZARIN5HMVEI66U3LWD/events.json","paper":"https://pith.science/paper/E7FSBVEF"},"agent_actions":{"view_html":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD","download_json":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD.json","view_paper":"https://pith.science/paper/E7FSBVEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.17513&json=true","fetch_graph":"https://pith.science/api/pith-number/E7FSBVEFZARIN5HMVEI66U3LWD/graph.json","fetch_events":"https://pith.science/api/pith-number/E7FSBVEFZARIN5HMVEI66U3LWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD/action/storage_attestation","attest_author":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD/action/author_attestation","sign_citation":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD/action/citation_signature","submit_replication":"https://pith.science/pith/E7FSBVEFZARIN5HMVEI66U3LWD/action/replication_record"}},"created_at":"2026-06-02T01:03:43.871048+00:00","updated_at":"2026-06-02T01:03:43.871048+00:00"}