{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E7FSBVEFZARIN5HMVEI66U3LWD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"172cfb676ceba420b1195d411313137bc6a886ad43f4a0c88b51c377df50f8dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T16:25:07Z","title_canon_sha256":"3a6c065996f56b3e4c50f5016062c371bcb30d5241a334dda3a4eafd87d9f725"},"schema_version":"1.0","source":{"id":"2602.17513","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17513","created_at":"2026-06-02T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17513v2","created_at":"2026-06-02T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17513","created_at":"2026-06-02T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"E7FSBVEFZARI","created_at":"2026-06-02T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"E7FSBVEFZARIN5HM","created_at":"2026-06-02T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"E7FSBVEF","created_at":"2026-06-02T01:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:7667472f7792b0ea8db7b0af374de933f8c7f9513ebe1161aa08da96328b39dd","target":"graph","created_at":"2026-06-02T01:03:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"f84110bdb8561e7df3e0ccbe2c5f9530ae2e610cdccf4a587f35660397e0db1d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.17513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Barbara Di Eugenio, Baris Karacan, Patrick Thornton","cross_cats":[],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T16:25:07Z","title":"Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics"},"references":{"count":24,"internal_anchors":4,"resolved_work":24,"sample":[{"cited_arxiv_id":"2602.17513","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics","work_id":"ee048cf4-d010-48bb-82ab-878826013785","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"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","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"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","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"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","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"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","year":2008}],"snapshot_sha256":"f758c4cf6c8f2a5907b749623bce36c2fd023bd4213a9ff7564c9be6cd31ca33"},"source":{"id":"2602.17513","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T20:51:55.012614Z","id":"606d2148-e22b-4e64-bf15-5e66a636719a","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"606d2148-e22b-4e64-bf15-5e66a636719a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:784e29593ace7cd4b4fa33e12d43727e994fa237cd71c36e1e551589805625c1","target":"record","created_at":"2026-06-02T01:03:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"172cfb676ceba420b1195d411313137bc6a886ad43f4a0c88b51c377df50f8dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T16:25:07Z","title_canon_sha256":"3a6c065996f56b3e4c50f5016062c371bcb30d5241a334dda3a4eafd87d9f725"},"schema_version":"1.0","source":{"id":"2602.17513","kind":"arxiv","version":2}},"canonical_sha256":"27cb20d485c82286f4eca911ef536bb0f0a6e4131f8ce8fecb5c5ca78973da14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27cb20d485c82286f4eca911ef536bb0f0a6e4131f8ce8fecb5c5ca78973da14","first_computed_at":"2026-06-02T01:03:43.870982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:43.870982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T4+WNFbStzeTllxVzRT/A3MSEdrWThyLtaTMmXWr/+FgNxpilvPJkpl+2qxBL6qFd0f/niCGil6ykV/75j71Dg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:43.871513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17513","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:784e29593ace7cd4b4fa33e12d43727e994fa237cd71c36e1e551589805625c1","sha256:7667472f7792b0ea8db7b0af374de933f8c7f9513ebe1161aa08da96328b39dd"],"state_sha256":"bfe608b4b31b71dd6097f27d2eb289adab436580ab78f5b18a2f8ab65bfb6d02"}