{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FV7WEMEY5KRV7MVC4NNRBMGUMH","short_pith_number":"pith:FV7WEMEY","schema_version":"1.0","canonical_sha256":"2d7f623098eaa35fb2a2e35b10b0d461ed15a8b3a0e6ca46e8a769f73b623865","source":{"kind":"arxiv","id":"2606.11361","version":1},"attestation_state":"computed","paper":{"title":"A PubMed-Scale Dataset of Structured Biomedical Abstracts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Brian Ondov, Chia-Hsuan Chang, Haerin Song, Hua Xu","submitted_at":"2026-06-09T18:42:20Z","abstract_excerpt":"Structured abstracts are important for biomedical literature processing, by facilitating information retrieval, text mining, and knowledge synthesis. However, a vast portion of abstracts indexed in PubMed remain unstructured, presenting a significant bottleneck for downstream text-processing workflows and applications. To resolve this limitation, we introduce Structured PubMed, a comprehensive corpus of section-labeled biomedical abstracts compiled from the complete PubMed database, encompassing over 23.2 million research-article records. The corpus is divided into two distinct subsets: a coll"},"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":"2606.11361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T18:42:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"32227685af7c523dc569d6d571bb833743e38e0f1532e23b362fca6122385c65","abstract_canon_sha256":"d49bf40e910fd8b00c447d5478fd6189e00bdd1be8c9c56edad51e3397a93e1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:21.672248Z","signature_b64":"nXjIv7Jaeo94Rgujxoyct4N0NCfNB9j1m1EGfz407U4bG/WItNjzvqcNd/7kpPur1CL0Mp4CPQi9OLsGYLfNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d7f623098eaa35fb2a2e35b10b0d461ed15a8b3a0e6ca46e8a769f73b623865","last_reissued_at":"2026-06-11T00:08:21.671380Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:21.671380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A PubMed-Scale Dataset of Structured Biomedical Abstracts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Brian Ondov, Chia-Hsuan Chang, Haerin Song, Hua Xu","submitted_at":"2026-06-09T18:42:20Z","abstract_excerpt":"Structured abstracts are important for biomedical literature processing, by facilitating information retrieval, text mining, and knowledge synthesis. However, a vast portion of abstracts indexed in PubMed remain unstructured, presenting a significant bottleneck for downstream text-processing workflows and applications. To resolve this limitation, we introduce Structured PubMed, a comprehensive corpus of section-labeled biomedical abstracts compiled from the complete PubMed database, encompassing over 23.2 million research-article records. The corpus is divided into two distinct subsets: a coll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11361","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/2606.11361/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":"2606.11361","created_at":"2026-06-11T00:08:21.671531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11361v1","created_at":"2026-06-11T00:08:21.671531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11361","created_at":"2026-06-11T00:08:21.671531+00:00"},{"alias_kind":"pith_short_12","alias_value":"FV7WEMEY5KRV","created_at":"2026-06-11T00:08:21.671531+00:00"},{"alias_kind":"pith_short_16","alias_value":"FV7WEMEY5KRV7MVC","created_at":"2026-06-11T00:08:21.671531+00:00"},{"alias_kind":"pith_short_8","alias_value":"FV7WEMEY","created_at":"2026-06-11T00:08:21.671531+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/FV7WEMEY5KRV7MVC4NNRBMGUMH","json":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH.json","graph_json":"https://pith.science/api/pith-number/FV7WEMEY5KRV7MVC4NNRBMGUMH/graph.json","events_json":"https://pith.science/api/pith-number/FV7WEMEY5KRV7MVC4NNRBMGUMH/events.json","paper":"https://pith.science/paper/FV7WEMEY"},"agent_actions":{"view_html":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH","download_json":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH.json","view_paper":"https://pith.science/paper/FV7WEMEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11361&json=true","fetch_graph":"https://pith.science/api/pith-number/FV7WEMEY5KRV7MVC4NNRBMGUMH/graph.json","fetch_events":"https://pith.science/api/pith-number/FV7WEMEY5KRV7MVC4NNRBMGUMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH/action/storage_attestation","attest_author":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH/action/author_attestation","sign_citation":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH/action/citation_signature","submit_replication":"https://pith.science/pith/FV7WEMEY5KRV7MVC4NNRBMGUMH/action/replication_record"}},"created_at":"2026-06-11T00:08:21.671531+00:00","updated_at":"2026-06-11T00:08:21.671531+00:00"}