{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ","short_pith_number":"pith:UE4ROT4D","schema_version":"1.0","canonical_sha256":"a139174f834ed3688e035986e1773acc11f177e4b242d87c73133789ae85ec3e","source":{"kind":"arxiv","id":"2409.19042","version":1},"attestation_state":"computed","paper":{"title":"Probing mental health information in speech foundation models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Adrien Lesage, Cyrille Dakhlia, Marc de Gennes, Martin Denais, Pierre Van Remoortere, Rachid Riad, Simon Chang, Xuan-Nga Cao","submitted_at":"2024-09-27T17:38:34Z","abstract_excerpt":"Non-invasive methods for diagnosing mental health conditions, such as speech analysis, offer promising potential in modern medicine. Recent advancements in machine learning, particularly speech foundation models, have shown significant promise in detecting mental health states by capturing diverse features. This study investigates which pretext tasks in these models best transfer to mental health detection and examines how different model layers encode features relevant to mental health conditions. We also probed the optimal length of audio segments and the best pooling strategies to improve d"},"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":"2409.19042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-27T17:38:34Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8e21fc998e0bca4a4b14d76adfb090065bc896e4dee82dc4638ba10672759603","abstract_canon_sha256":"1b60380fdb66a61121742b11be1813a84e081a8cde0a9f1ec1c62e0a309b3576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:09.873872Z","signature_b64":"aO2AHpiKZyvnzDf+TU4BLMoRDtTnhvZsel8r/QAcNh7KMBk7wkre/X/vf+JxDpFXMIs7O37hWTnJRVKqzagdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a139174f834ed3688e035986e1773acc11f177e4b242d87c73133789ae85ec3e","last_reissued_at":"2026-07-05T09:13:09.873370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:09.873370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing mental health information in speech foundation models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Adrien Lesage, Cyrille Dakhlia, Marc de Gennes, Martin Denais, Pierre Van Remoortere, Rachid Riad, Simon Chang, Xuan-Nga Cao","submitted_at":"2024-09-27T17:38:34Z","abstract_excerpt":"Non-invasive methods for diagnosing mental health conditions, such as speech analysis, offer promising potential in modern medicine. Recent advancements in machine learning, particularly speech foundation models, have shown significant promise in detecting mental health states by capturing diverse features. This study investigates which pretext tasks in these models best transfer to mental health detection and examines how different model layers encode features relevant to mental health conditions. We also probed the optimal length of audio segments and the best pooling strategies to improve d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19042","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/2409.19042/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":"2409.19042","created_at":"2026-07-05T09:13:09.873429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19042v1","created_at":"2026-07-05T09:13:09.873429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19042","created_at":"2026-07-05T09:13:09.873429+00:00"},{"alias_kind":"pith_short_12","alias_value":"UE4ROT4DJ3JW","created_at":"2026-07-05T09:13:09.873429+00:00"},{"alias_kind":"pith_short_16","alias_value":"UE4ROT4DJ3JWRDQD","created_at":"2026-07-05T09:13:09.873429+00:00"},{"alias_kind":"pith_short_8","alias_value":"UE4ROT4D","created_at":"2026-07-05T09:13:09.873429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05561","citing_title":"InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ","json":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ.json","graph_json":"https://pith.science/api/pith-number/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/graph.json","events_json":"https://pith.science/api/pith-number/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/events.json","paper":"https://pith.science/paper/UE4ROT4D"},"agent_actions":{"view_html":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ","download_json":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ.json","view_paper":"https://pith.science/paper/UE4ROT4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19042&json=true","fetch_graph":"https://pith.science/api/pith-number/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/action/storage_attestation","attest_author":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/action/author_attestation","sign_citation":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/action/citation_signature","submit_replication":"https://pith.science/pith/UE4ROT4DJ3JWRDQDLGDOC5Z2ZQ/action/replication_record"}},"created_at":"2026-07-05T09:13:09.873429+00:00","updated_at":"2026-07-05T09:13:09.873429+00:00"}