{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BINEPZWWOJA7VMGBWSZDAVW4HS","short_pith_number":"pith:BINEPZWW","schema_version":"1.0","canonical_sha256":"0a1a47e6d67241fab0c1b4b23056dc3c8d04292e9b1285ab5df045c711764d80","source":{"kind":"arxiv","id":"1710.06071","version":1},"attestation_state":"computed","paper":{"title":"PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Ji Young Lee","submitted_at":"2017-10-17T03:22:00Z","abstract_excerpt":"We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following classes: background, objective, method, result, or conclusion. The purpose of releasing this dataset is twofold. First, the majority of datasets for sequential short-text classification (i.e., classification of short texts that appear in sequences) are small: we hope that releasi"},"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":"1710.06071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-17T03:22:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"70977eec1b5630de2577fd05d1fc0901adf074ef98e21389fb85144c766d6126","abstract_canon_sha256":"f3d92786242769798f96c28470d1c3a6ac9cbcee0f2adbda1e71988e3a888d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:37.858065Z","signature_b64":"0CV6M0wsQl/Gv9taK7R9gkpU+8cQA6iaSbwNzXnTkZxit7wyAsEQ+XcUz7VeVGVUAesfpSbCsLMAfV5mD5hDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a1a47e6d67241fab0c1b4b23056dc3c8d04292e9b1285ab5df045c711764d80","last_reissued_at":"2026-05-18T00:32:37.857393Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:37.857393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Ji Young Lee","submitted_at":"2017-10-17T03:22:00Z","abstract_excerpt":"We present PubMed 200k RCT, a new dataset based on PubMed for sequential sentence classification. The dataset consists of approximately 200,000 abstracts of randomized controlled trials, totaling 2.3 million sentences. Each sentence of each abstract is labeled with their role in the abstract using one of the following classes: background, objective, method, result, or conclusion. The purpose of releasing this dataset is twofold. First, the majority of datasets for sequential short-text classification (i.e., classification of short texts that appear in sequences) are small: we hope that releasi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06071","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":""},"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":"1710.06071","created_at":"2026-05-18T00:32:37.857496+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.06071v1","created_at":"2026-05-18T00:32:37.857496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06071","created_at":"2026-05-18T00:32:37.857496+00:00"},{"alias_kind":"pith_short_12","alias_value":"BINEPZWWOJA7","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BINEPZWWOJA7VMGB","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BINEPZWW","created_at":"2026-05-18T12:31:08.081275+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/BINEPZWWOJA7VMGBWSZDAVW4HS","json":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS.json","graph_json":"https://pith.science/api/pith-number/BINEPZWWOJA7VMGBWSZDAVW4HS/graph.json","events_json":"https://pith.science/api/pith-number/BINEPZWWOJA7VMGBWSZDAVW4HS/events.json","paper":"https://pith.science/paper/BINEPZWW"},"agent_actions":{"view_html":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS","download_json":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS.json","view_paper":"https://pith.science/paper/BINEPZWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.06071&json=true","fetch_graph":"https://pith.science/api/pith-number/BINEPZWWOJA7VMGBWSZDAVW4HS/graph.json","fetch_events":"https://pith.science/api/pith-number/BINEPZWWOJA7VMGBWSZDAVW4HS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS/action/storage_attestation","attest_author":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS/action/author_attestation","sign_citation":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS/action/citation_signature","submit_replication":"https://pith.science/pith/BINEPZWWOJA7VMGBWSZDAVW4HS/action/replication_record"}},"created_at":"2026-05-18T00:32:37.857496+00:00","updated_at":"2026-05-18T00:32:37.857496+00:00"}