{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X3ZY7WLWVIMN7O3BJI6IAYBDQK","short_pith_number":"pith:X3ZY7WLW","schema_version":"1.0","canonical_sha256":"bef38fd976aa18dfbb614a3c806023829004d867fe3d32ab96fac9f8ffb88b15","source":{"kind":"arxiv","id":"2407.19340","version":5},"attestation_state":"computed","paper":{"title":"Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification on the DAIC-WOZ","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Santosh V. Patapati","submitted_at":"2024-07-27T21:00:36Z","abstract_excerpt":"Major Depressive Disorder (MDD) is a pervasive mental health condition that affects 300 million people worldwide. This work presents a novel, BiLSTM-based tri-modal model-level fusion architecture for the binary classification of depression from clinical interview recordings. The proposed architecture incorporates Mel Frequency Cepstral Coefficients, Facial Action Units, and uses a two-shot learning based GPT-4 model to process text data. This is the first work to incorporate large language models into a multi-modal architecture for this task. It achieves impressive results on the DAIC-WOZ AVE"},"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":"2407.19340","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-27T21:00:36Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"ff4778e94d208f0882a9364ac364787ab3795f334baf95e306f1cae2b288fcb0","abstract_canon_sha256":"7e4970603c185f47b30ff2e14d8c93966ddc2a109b8ebe07b5ebad1e7b28b8da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:30.534770Z","signature_b64":"ys/lCa5e2jgcSWguVCCFP57tS+GovfVM4vCEgCSTNRK6RoJPa7RRCmxasriczmxoGPNWJS8YG1tbnxZAhaEABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef38fd976aa18dfbb614a3c806023829004d867fe3d32ab96fac9f8ffb88b15","last_reissued_at":"2026-07-05T09:19:30.534285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:30.534285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification on the DAIC-WOZ","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Santosh V. Patapati","submitted_at":"2024-07-27T21:00:36Z","abstract_excerpt":"Major Depressive Disorder (MDD) is a pervasive mental health condition that affects 300 million people worldwide. This work presents a novel, BiLSTM-based tri-modal model-level fusion architecture for the binary classification of depression from clinical interview recordings. The proposed architecture incorporates Mel Frequency Cepstral Coefficients, Facial Action Units, and uses a two-shot learning based GPT-4 model to process text data. This is the first work to incorporate large language models into a multi-modal architecture for this task. It achieves impressive results on the DAIC-WOZ AVE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19340","kind":"arxiv","version":5},"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/2407.19340/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":"2407.19340","created_at":"2026-07-05T09:19:30.534344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19340v5","created_at":"2026-07-05T09:19:30.534344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19340","created_at":"2026-07-05T09:19:30.534344+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3ZY7WLWVIMN","created_at":"2026-07-05T09:19:30.534344+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3ZY7WLWVIMN7O3B","created_at":"2026-07-05T09:19:30.534344+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3ZY7WLW","created_at":"2026-07-05T09:19:30.534344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21123","citing_title":"A Multi-Agent Audit Framework for High-Stakes Reasoning: Evaluation and Interpretability in Clinical Mental Health Screening","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11303","citing_title":"Predicting Psychological Well-Being from Spontaneous Speech using LLMs","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK","json":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK.json","graph_json":"https://pith.science/api/pith-number/X3ZY7WLWVIMN7O3BJI6IAYBDQK/graph.json","events_json":"https://pith.science/api/pith-number/X3ZY7WLWVIMN7O3BJI6IAYBDQK/events.json","paper":"https://pith.science/paper/X3ZY7WLW"},"agent_actions":{"view_html":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK","download_json":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK.json","view_paper":"https://pith.science/paper/X3ZY7WLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19340&json=true","fetch_graph":"https://pith.science/api/pith-number/X3ZY7WLWVIMN7O3BJI6IAYBDQK/graph.json","fetch_events":"https://pith.science/api/pith-number/X3ZY7WLWVIMN7O3BJI6IAYBDQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK/action/storage_attestation","attest_author":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK/action/author_attestation","sign_citation":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK/action/citation_signature","submit_replication":"https://pith.science/pith/X3ZY7WLWVIMN7O3BJI6IAYBDQK/action/replication_record"}},"created_at":"2026-07-05T09:19:30.534344+00:00","updated_at":"2026-07-05T09:19:30.534344+00:00"}