{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:2ZR35L32LXZ5MOMWFZQD2HCKAT","short_pith_number":"pith:2ZR35L32","schema_version":"1.0","canonical_sha256":"d663beaf7a5df3d639962e603d1c4a04d2a1c6ea6f6a5092a895eb8f44d8b1c1","source":{"kind":"arxiv","id":"1606.07137","version":1},"attestation_state":"computed","paper":{"title":"Automated Extraction of Number of Subjects in Randomised Controlled Trials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Abeed Sarker","submitted_at":"2016-06-22T23:35:59Z","abstract_excerpt":"We present a simple approach for automatically extracting the number of subjects involved in randomised controlled trials (RCT). Our approach first applies a set of rule-based techniques to extract candidate study sizes from the abstracts of the articles. Supervised classification is then performed over the candidates with support vector machines, using a small set of lexical, structural, and contextual features. With only a small annotated training set of 201 RCTs, we obtained an accuracy of 88\\%. We believe that this system will aid complex medical text processing tasks such as summarisation"},"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":"1606.07137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-22T23:35:59Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"4b341a1ca119b715f9a6dd8d3c61ec48bd5950fb1ab13515f6a20cc83c1d63ed","abstract_canon_sha256":"60494e199a68254d5dcc5cd84dc74631882fe1a53860c97edf45d7fb4bd95131"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:58.591246Z","signature_b64":"B20panOKW3RzmLI/ilQS/xTQsHbHMflKfvm+1ZJSPC6pkXlL0BRTtOSPpYEiJE1sQ5UWvt1fZ3m30rOsNoQrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d663beaf7a5df3d639962e603d1c4a04d2a1c6ea6f6a5092a895eb8f44d8b1c1","last_reissued_at":"2026-05-18T01:11:58.590902Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:58.590902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Extraction of Number of Subjects in Randomised Controlled Trials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Abeed Sarker","submitted_at":"2016-06-22T23:35:59Z","abstract_excerpt":"We present a simple approach for automatically extracting the number of subjects involved in randomised controlled trials (RCT). Our approach first applies a set of rule-based techniques to extract candidate study sizes from the abstracts of the articles. Supervised classification is then performed over the candidates with support vector machines, using a small set of lexical, structural, and contextual features. With only a small annotated training set of 201 RCTs, we obtained an accuracy of 88\\%. We believe that this system will aid complex medical text processing tasks such as summarisation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07137","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":"1606.07137","created_at":"2026-05-18T01:11:58.590956+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.07137v1","created_at":"2026-05-18T01:11:58.590956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07137","created_at":"2026-05-18T01:11:58.590956+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZR35L32LXZ5","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZR35L32LXZ5MOMW","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZR35L32","created_at":"2026-05-18T12:29:55.572404+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/2ZR35L32LXZ5MOMWFZQD2HCKAT","json":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT.json","graph_json":"https://pith.science/api/pith-number/2ZR35L32LXZ5MOMWFZQD2HCKAT/graph.json","events_json":"https://pith.science/api/pith-number/2ZR35L32LXZ5MOMWFZQD2HCKAT/events.json","paper":"https://pith.science/paper/2ZR35L32"},"agent_actions":{"view_html":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT","download_json":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT.json","view_paper":"https://pith.science/paper/2ZR35L32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.07137&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZR35L32LXZ5MOMWFZQD2HCKAT/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZR35L32LXZ5MOMWFZQD2HCKAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT/action/storage_attestation","attest_author":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT/action/author_attestation","sign_citation":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT/action/citation_signature","submit_replication":"https://pith.science/pith/2ZR35L32LXZ5MOMWFZQD2HCKAT/action/replication_record"}},"created_at":"2026-05-18T01:11:58.590956+00:00","updated_at":"2026-05-18T01:11:58.590956+00:00"}