{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JETWKLJPEV6NADVRGSMLL7YCX5","short_pith_number":"pith:JETWKLJP","schema_version":"1.0","canonical_sha256":"4927652d2f257cd00eb13498b5ff02bf48125ae1d24292d995ed4d0f04058802","source":{"kind":"arxiv","id":"2605.16077","version":1},"attestation_state":"computed","paper":{"title":"Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eiji Aramaki, Lenard Paulo Tamayo, Shaowen Peng, Shohei Hisada, Shoko Wakamiya, Si-Belkacem Yamine Ketir","submitted_at":"2026-05-15T15:39:22Z","abstract_excerpt":"Accurate assessment of cognitive decline from spontaneous speech remains challenging due to limited dataset size and class imbalance. In this work, we propose a large language model (LLM)-driven data augmentation framework to improve the prediction of cognitive scores from speech. Experiments are conducted on a Japanese corpus in which each participant provides both a spontaneous oral narrative and a written response to the same clinical prompt. The written responses serve as semantic anchors to generate multiple oral-like monologues in different styles using GPT-5. We then predict Hasegawa De"},"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":"2605.16077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T15:39:22Z","cross_cats_sorted":[],"title_canon_sha256":"516086c8297fe23529e3efe88cdcc6aee9e52f0d88ef178085bda4ff2a4e9bf2","abstract_canon_sha256":"c2153e20ba58c3c2cfb6ef258fad3e2f929384b6a2dc3150dc3655a68c7ca4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:51.646013Z","signature_b64":"cq0mAMik4AleL4Z3EM4ISLSvkoARu2OCEWW/wLTsvDjznbP8laycWajUm+le7AJAaDVz7/3tPufbMyGuv0w5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4927652d2f257cd00eb13498b5ff02bf48125ae1d24292d995ed4d0f04058802","last_reissued_at":"2026-05-20T00:01:51.645394Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:51.645394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eiji Aramaki, Lenard Paulo Tamayo, Shaowen Peng, Shohei Hisada, Shoko Wakamiya, Si-Belkacem Yamine Ketir","submitted_at":"2026-05-15T15:39:22Z","abstract_excerpt":"Accurate assessment of cognitive decline from spontaneous speech remains challenging due to limited dataset size and class imbalance. In this work, we propose a large language model (LLM)-driven data augmentation framework to improve the prediction of cognitive scores from speech. Experiments are conducted on a Japanese corpus in which each participant provides both a spontaneous oral narrative and a written response to the same clinical prompt. The written responses serve as semantic anchors to generate multiple oral-like monologues in different styles using GPT-5. We then predict Hasegawa De"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16077","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/2605.16077/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:41.539243Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.507984Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e4212a30c500a98a3e9e9d227801483a134b7684f47b438a765e0d008f7c2cad"},"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":"2605.16077","created_at":"2026-05-20T00:01:51.645473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16077v1","created_at":"2026-05-20T00:01:51.645473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16077","created_at":"2026-05-20T00:01:51.645473+00:00"},{"alias_kind":"pith_short_12","alias_value":"JETWKLJPEV6N","created_at":"2026-05-20T00:01:51.645473+00:00"},{"alias_kind":"pith_short_16","alias_value":"JETWKLJPEV6NADVR","created_at":"2026-05-20T00:01:51.645473+00:00"},{"alias_kind":"pith_short_8","alias_value":"JETWKLJP","created_at":"2026-05-20T00:01:51.645473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16077","citing_title":"Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5","json":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5.json","graph_json":"https://pith.science/api/pith-number/JETWKLJPEV6NADVRGSMLL7YCX5/graph.json","events_json":"https://pith.science/api/pith-number/JETWKLJPEV6NADVRGSMLL7YCX5/events.json","paper":"https://pith.science/paper/JETWKLJP"},"agent_actions":{"view_html":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5","download_json":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5.json","view_paper":"https://pith.science/paper/JETWKLJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16077&json=true","fetch_graph":"https://pith.science/api/pith-number/JETWKLJPEV6NADVRGSMLL7YCX5/graph.json","fetch_events":"https://pith.science/api/pith-number/JETWKLJPEV6NADVRGSMLL7YCX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5/action/storage_attestation","attest_author":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5/action/author_attestation","sign_citation":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5/action/citation_signature","submit_replication":"https://pith.science/pith/JETWKLJPEV6NADVRGSMLL7YCX5/action/replication_record"}},"created_at":"2026-05-20T00:01:51.645473+00:00","updated_at":"2026-05-20T00:01:51.645473+00:00"}