{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3S6OC6K7SKEXDR54HHALHHEJBF","short_pith_number":"pith:3S6OC6K7","schema_version":"1.0","canonical_sha256":"dcbce1795f928971c7bc39c0b39c89095315663d938a884929dfdc33bcc949f4","source":{"kind":"arxiv","id":"2507.01810","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Nikita Neveditsin, Pawan Lingras, Vijay Mago","submitted_at":"2025-07-02T15:27:41Z","abstract_excerpt":"We present a comparative analysis of the parseability of structured outputs generated by small language models for open attribute-value extraction from clinical notes. We evaluate three widely used serialization formats: JSON, YAML, and XML, and find that JSON consistently yields the highest parseability. Structural robustness improves with targeted prompting and larger models, but declines for longer documents and certain note types. Our error analysis identifies recurring format-specific failure patterns. These findings offer practical guidance for selecting serialization formats and designi"},"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":"2507.01810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T15:27:41Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"cde4a624ae861340616c8751f6ddb2f67699ac1e65e0cd97a92edd1e4e3fcd15","abstract_canon_sha256":"a37f2cc3ebf7ab7de4fc6463aaa26ae72b18884f3980bb3c7041148109fd3ddd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:51.028672Z","signature_b64":"tF7/y0zfBPanIUS1R1GIUm+lbABnA24bQfABxPAnH3lmAzO23+qX7wZzP5wWgIKdx/jADuXcUH2W0hPfL54NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbce1795f928971c7bc39c0b39c89095315663d938a884929dfdc33bcc949f4","last_reissued_at":"2026-07-05T11:48:51.028239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:51.028239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Nikita Neveditsin, Pawan Lingras, Vijay Mago","submitted_at":"2025-07-02T15:27:41Z","abstract_excerpt":"We present a comparative analysis of the parseability of structured outputs generated by small language models for open attribute-value extraction from clinical notes. We evaluate three widely used serialization formats: JSON, YAML, and XML, and find that JSON consistently yields the highest parseability. Structural robustness improves with targeted prompting and larger models, but declines for longer documents and certain note types. Our error analysis identifies recurring format-specific failure patterns. These findings offer practical guidance for selecting serialization formats and designi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01810","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/2507.01810/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":"2507.01810","created_at":"2026-07-05T11:48:51.028308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01810v1","created_at":"2026-07-05T11:48:51.028308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01810","created_at":"2026-07-05T11:48:51.028308+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S6OC6K7SKEX","created_at":"2026-07-05T11:48:51.028308+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S6OC6K7SKEXDR54","created_at":"2026-07-05T11:48:51.028308+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S6OC6K7","created_at":"2026-07-05T11:48:51.028308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08182","citing_title":"XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocols","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF","json":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF.json","graph_json":"https://pith.science/api/pith-number/3S6OC6K7SKEXDR54HHALHHEJBF/graph.json","events_json":"https://pith.science/api/pith-number/3S6OC6K7SKEXDR54HHALHHEJBF/events.json","paper":"https://pith.science/paper/3S6OC6K7"},"agent_actions":{"view_html":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF","download_json":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF.json","view_paper":"https://pith.science/paper/3S6OC6K7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01810&json=true","fetch_graph":"https://pith.science/api/pith-number/3S6OC6K7SKEXDR54HHALHHEJBF/graph.json","fetch_events":"https://pith.science/api/pith-number/3S6OC6K7SKEXDR54HHALHHEJBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF/action/storage_attestation","attest_author":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF/action/author_attestation","sign_citation":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF/action/citation_signature","submit_replication":"https://pith.science/pith/3S6OC6K7SKEXDR54HHALHHEJBF/action/replication_record"}},"created_at":"2026-07-05T11:48:51.028308+00:00","updated_at":"2026-07-05T11:48:51.028308+00:00"}