{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2FKZXMUENOR7ZTG6EVNVOKKLFH","short_pith_number":"pith:2FKZXMUE","schema_version":"1.0","canonical_sha256":"d1559bb2846ba3fcccde255b57294b29cd767d6b86975c51c27b33511f970daa","source":{"kind":"arxiv","id":"2607.02904","version":1},"attestation_state":"computed","paper":{"title":"Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Anisha Pattanayak, Huang-Cheng Chou, Shrikanth Narayanan, Sudarsana Reddy Kadiri","submitted_at":"2026-07-03T03:02:48Z","abstract_excerpt":"Speech-based depression detection compresses features from short audio segments into one speaker-level decision, a step called temporal aggregation rarely studied on its own. Most benchmarks fix a single self-supervised encoder and a single hand-picked layer, so a reported gain may reflect the pipeline rather than the aggregation method itself. We introduce DEPOOL, a controlled benchmark that compares six aggregation architectures with six frozen speech backbones on an English and a Mandarin depression corpus, where each configuration learns which backbone layers matter rather than fixing one "},"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":"2607.02904","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-03T03:02:48Z","cross_cats_sorted":[],"title_canon_sha256":"7f0587df57118f02f4e9dd0e594a98f3fb349bb955ab842e6538a8669bc9adac","abstract_canon_sha256":"9395f9d4f90f83bd8545dc6b100c53b5e33f671dc1f9aa5178a61c15fca916c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:36.026626Z","signature_b64":"29HsVGChe84C1yBCpDNTQsghz2zFnFOUFVGvEsikQp3oXj9AwQ/iFoLVTjwDcxSX/JBNMBzsfZy8RfqE8n0lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1559bb2846ba3fcccde255b57294b29cd767d6b86975c51c27b33511f970daa","last_reissued_at":"2026-07-07T01:16:36.026084Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:36.026084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Anisha Pattanayak, Huang-Cheng Chou, Shrikanth Narayanan, Sudarsana Reddy Kadiri","submitted_at":"2026-07-03T03:02:48Z","abstract_excerpt":"Speech-based depression detection compresses features from short audio segments into one speaker-level decision, a step called temporal aggregation rarely studied on its own. Most benchmarks fix a single self-supervised encoder and a single hand-picked layer, so a reported gain may reflect the pipeline rather than the aggregation method itself. We introduce DEPOOL, a controlled benchmark that compares six aggregation architectures with six frozen speech backbones on an English and a Mandarin depression corpus, where each configuration learns which backbone layers matter rather than fixing one "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02904","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/2607.02904/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":"2607.02904","created_at":"2026-07-07T01:16:36.026160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02904v1","created_at":"2026-07-07T01:16:36.026160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02904","created_at":"2026-07-07T01:16:36.026160+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FKZXMUENOR7","created_at":"2026-07-07T01:16:36.026160+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FKZXMUENOR7ZTG6","created_at":"2026-07-07T01:16:36.026160+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FKZXMUE","created_at":"2026-07-07T01:16:36.026160+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/2FKZXMUENOR7ZTG6EVNVOKKLFH","json":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH.json","graph_json":"https://pith.science/api/pith-number/2FKZXMUENOR7ZTG6EVNVOKKLFH/graph.json","events_json":"https://pith.science/api/pith-number/2FKZXMUENOR7ZTG6EVNVOKKLFH/events.json","paper":"https://pith.science/paper/2FKZXMUE"},"agent_actions":{"view_html":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH","download_json":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH.json","view_paper":"https://pith.science/paper/2FKZXMUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02904&json=true","fetch_graph":"https://pith.science/api/pith-number/2FKZXMUENOR7ZTG6EVNVOKKLFH/graph.json","fetch_events":"https://pith.science/api/pith-number/2FKZXMUENOR7ZTG6EVNVOKKLFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH/action/storage_attestation","attest_author":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH/action/author_attestation","sign_citation":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH/action/citation_signature","submit_replication":"https://pith.science/pith/2FKZXMUENOR7ZTG6EVNVOKKLFH/action/replication_record"}},"created_at":"2026-07-07T01:16:36.026160+00:00","updated_at":"2026-07-07T01:16:36.026160+00:00"}