{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GRAN644GY3PSVHODSF76HIIZU4","short_pith_number":"pith:GRAN644G","schema_version":"1.0","canonical_sha256":"3440df7386c6df2a9dc3917fe3a119a7292cfded990251cce6a69f5dcdbf6a8d","source":{"kind":"arxiv","id":"2106.15684","version":1},"attestation_state":"computed","paper":{"title":"Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Julian Hough, Matthew Purver, Morteza Rohanian","submitted_at":"2021-06-29T19:24:29Z","abstract_excerpt":"We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree, evaluating the ADReSSo challenge 2021 data. Our best model, a BiLSTM with highway layers using words, word probabilities, disfluency features, pause information, and a variety of acoustic features, achieves an accuracy of 84% and RSME error prediction of 4.26 on MMSE cognitive scores. While predicting cognitive decline is more challenging, our models show improve"},"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":"2106.15684","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-29T19:24:29Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"51610aa64d175d2b77afe0a3b27ae3f8aa805bb4495ed386e21142329de68907","abstract_canon_sha256":"b6c32f75340cc880eda649215ae430446763eb083050106f0be2118746d80316"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:59.257842Z","signature_b64":"eipi3Pt7/a/YcpH9KVkANo/ED1uX0F3Ii/cGjycSi+ai9xy9HUTqH8yux7302qx1v0xGRC5r5z6EAXkA/+InBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3440df7386c6df2a9dc3917fe3a119a7292cfded990251cce6a69f5dcdbf6a8d","last_reissued_at":"2026-07-05T02:53:59.257411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:59.257411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Julian Hough, Matthew Purver, Morteza Rohanian","submitted_at":"2021-06-29T19:24:29Z","abstract_excerpt":"We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree, evaluating the ADReSSo challenge 2021 data. Our best model, a BiLSTM with highway layers using words, word probabilities, disfluency features, pause information, and a variety of acoustic features, achieves an accuracy of 84% and RSME error prediction of 4.26 on MMSE cognitive scores. While predicting cognitive decline is more challenging, our models show improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15684","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/2106.15684/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":"2106.15684","created_at":"2026-07-05T02:53:59.257465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15684v1","created_at":"2026-07-05T02:53:59.257465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15684","created_at":"2026-07-05T02:53:59.257465+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRAN644GY3PS","created_at":"2026-07-05T02:53:59.257465+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRAN644GY3PSVHOD","created_at":"2026-07-05T02:53:59.257465+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRAN644G","created_at":"2026-07-05T02:53:59.257465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19446","citing_title":"Leveraging Cascaded Binary Classification and Multimodal Fusion for Dementia Detection through Spontaneous Speech","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4","json":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4.json","graph_json":"https://pith.science/api/pith-number/GRAN644GY3PSVHODSF76HIIZU4/graph.json","events_json":"https://pith.science/api/pith-number/GRAN644GY3PSVHODSF76HIIZU4/events.json","paper":"https://pith.science/paper/GRAN644G"},"agent_actions":{"view_html":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4","download_json":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4.json","view_paper":"https://pith.science/paper/GRAN644G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15684&json=true","fetch_graph":"https://pith.science/api/pith-number/GRAN644GY3PSVHODSF76HIIZU4/graph.json","fetch_events":"https://pith.science/api/pith-number/GRAN644GY3PSVHODSF76HIIZU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4/action/storage_attestation","attest_author":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4/action/author_attestation","sign_citation":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4/action/citation_signature","submit_replication":"https://pith.science/pith/GRAN644GY3PSVHODSF76HIIZU4/action/replication_record"}},"created_at":"2026-07-05T02:53:59.257465+00:00","updated_at":"2026-07-05T02:53:59.257465+00:00"}