{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KP3VZS3QL2GP6CBXHP2GQOUAWG","short_pith_number":"pith:KP3VZS3Q","schema_version":"1.0","canonical_sha256":"53f75ccb705e8cff08373bf4683a80b19d7cc3ede71ccb876dcb14562703baf8","source":{"kind":"arxiv","id":"1712.00069","version":1},"attestation_state":"computed","paper":{"title":"On the importance of normative data in speech-based assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chlo\\'e Pou-Prom, Frank Rudzicz, Zeinab Noorian","submitted_at":"2017-11-30T20:36:50Z","abstract_excerpt":"Data sets for identifying Alzheimer's disease (AD) are often relatively sparse, which limits their ability to train generalizable models. Here, we augment such a data set, DementiaBank, with each of two normative data sets, the Wisconsin Longitudinal Study and Talk2Me, each of which employs a speech-based picture-description assessment. Through minority class oversampling with ADASYN, we outperform state-of-the-art results in binary classification of people with and without AD in DementiaBank. This work highlights the effectiveness of combining sparse and difficult-to-acquire patient data with"},"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":"1712.00069","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-30T20:36:50Z","cross_cats_sorted":[],"title_canon_sha256":"d8847f02b196a48c08450d5fca2fcb1b333a396f60aee045b4b7b4e92378f5ef","abstract_canon_sha256":"738664064c1c43ec4c14324aa1eee95c9e025bfda77d59fa4f24181cfe0c5c38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:07.483464Z","signature_b64":"CrYuoPgP5RR1hoivn65if84Bt9wuMm+bC3kSF6P2BhhLyY7VmCOM/GM+5Z1Ro1A3CsFD4oDUrfVAQkAARIe6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53f75ccb705e8cff08373bf4683a80b19d7cc3ede71ccb876dcb14562703baf8","last_reissued_at":"2026-05-18T00:29:07.482613Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:07.482613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the importance of normative data in speech-based assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chlo\\'e Pou-Prom, Frank Rudzicz, Zeinab Noorian","submitted_at":"2017-11-30T20:36:50Z","abstract_excerpt":"Data sets for identifying Alzheimer's disease (AD) are often relatively sparse, which limits their ability to train generalizable models. Here, we augment such a data set, DementiaBank, with each of two normative data sets, the Wisconsin Longitudinal Study and Talk2Me, each of which employs a speech-based picture-description assessment. Through minority class oversampling with ADASYN, we outperform state-of-the-art results in binary classification of people with and without AD in DementiaBank. This work highlights the effectiveness of combining sparse and difficult-to-acquire patient data with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00069","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":"1712.00069","created_at":"2026-05-18T00:29:07.482715+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00069v1","created_at":"2026-05-18T00:29:07.482715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00069","created_at":"2026-05-18T00:29:07.482715+00:00"},{"alias_kind":"pith_short_12","alias_value":"KP3VZS3QL2GP","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KP3VZS3QL2GP6CBX","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KP3VZS3Q","created_at":"2026-05-18T12:31:24.725408+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/KP3VZS3QL2GP6CBXHP2GQOUAWG","json":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG.json","graph_json":"https://pith.science/api/pith-number/KP3VZS3QL2GP6CBXHP2GQOUAWG/graph.json","events_json":"https://pith.science/api/pith-number/KP3VZS3QL2GP6CBXHP2GQOUAWG/events.json","paper":"https://pith.science/paper/KP3VZS3Q"},"agent_actions":{"view_html":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG","download_json":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG.json","view_paper":"https://pith.science/paper/KP3VZS3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00069&json=true","fetch_graph":"https://pith.science/api/pith-number/KP3VZS3QL2GP6CBXHP2GQOUAWG/graph.json","fetch_events":"https://pith.science/api/pith-number/KP3VZS3QL2GP6CBXHP2GQOUAWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG/action/storage_attestation","attest_author":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG/action/author_attestation","sign_citation":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG/action/citation_signature","submit_replication":"https://pith.science/pith/KP3VZS3QL2GP6CBXHP2GQOUAWG/action/replication_record"}},"created_at":"2026-05-18T00:29:07.482715+00:00","updated_at":"2026-05-18T00:29:07.482715+00:00"}