{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","short_pith_number":"pith:XE6ZBCEG","schema_version":"1.0","canonical_sha256":"b93d908886d2a302b1bb0ab46d7a11b64ecffc008a8f4bf73734c6b60b448f32","source":{"kind":"arxiv","id":"2608.04351","version":1},"attestation_state":"computed","paper":{"title":"HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Ding Luo, Jin Zeng, Ruikang Zhang, Tian Jin, Zefeng Zhao","submitted_at":"2026-08-05T01:50:37Z","abstract_excerpt":"Large Audio-Language Models (LALMs) excel at general speech understanding; however, adapting them to fine-grained tasks like Speech Emotion Recognition (SER) remains a significant bottleneck. Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate in flat Euclidean space, and this geometry fails to capture the multi-granularity nature of emotion cues, which range from low-level prosody to high-level semantics. To address this, we propose HyPASE, a hyperbolic PEFT framework for LALM-based SER. HyPASE leverages the Poincare ball model, using the hyperbolic radius as an explicit "},"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":"2608.04351","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T01:50:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb21dea8386fe0fff19ba64f298d2c29f6e6e2d49b1ce58db1617e1dde9b0dd5","abstract_canon_sha256":"9e72f5637003c08f494b3ccf5583b2b55c64c5e32aa54ead8146c05de6bc1d12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:33:30.601281Z","signature_b64":"6M7uoVwYBGkcuGYsk+W+7waoFq8pKS3gInL9xBU2GK2EYu8Cg0N7EH/8RllnBmnPibgJFl2PrR0HX/QZRRygBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b93d908886d2a302b1bb0ab46d7a11b64ecffc008a8f4bf73734c6b60b448f32","last_reissued_at":"2026-08-06T01:33:30.599623Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:33:30.599623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Ding Luo, Jin Zeng, Ruikang Zhang, Tian Jin, Zefeng Zhao","submitted_at":"2026-08-05T01:50:37Z","abstract_excerpt":"Large Audio-Language Models (LALMs) excel at general speech understanding; however, adapting them to fine-grained tasks like Speech Emotion Recognition (SER) remains a significant bottleneck. Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate in flat Euclidean space, and this geometry fails to capture the multi-granularity nature of emotion cues, which range from low-level prosody to high-level semantics. To address this, we propose HyPASE, a hyperbolic PEFT framework for LALM-based SER. HyPASE leverages the Poincare ball model, using the hyperbolic radius as an explicit "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04351","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/2608.04351/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":"2608.04351","created_at":"2026-08-06T01:33:30.601558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04351v1","created_at":"2026-08-06T01:33:30.601558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04351","created_at":"2026-08-06T01:33:30.601558+00:00"},{"alias_kind":"pith_short_12","alias_value":"XE6ZBCEG2KRQ","created_at":"2026-08-06T01:33:30.601558+00:00"},{"alias_kind":"pith_short_16","alias_value":"XE6ZBCEG2KRQFMN3","created_at":"2026-08-06T01:33:30.601558+00:00"},{"alias_kind":"pith_short_8","alias_value":"XE6ZBCEG","created_at":"2026-08-06T01:33:30.601558+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/XE6ZBCEG2KRQFMN3BK2G26QRWZ","json":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ.json","graph_json":"https://pith.science/api/pith-number/XE6ZBCEG2KRQFMN3BK2G26QRWZ/graph.json","events_json":"https://pith.science/api/pith-number/XE6ZBCEG2KRQFMN3BK2G26QRWZ/events.json","paper":"https://pith.science/paper/XE6ZBCEG"},"agent_actions":{"view_html":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ","download_json":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ.json","view_paper":"https://pith.science/paper/XE6ZBCEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04351&json=true","fetch_graph":"https://pith.science/api/pith-number/XE6ZBCEG2KRQFMN3BK2G26QRWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XE6ZBCEG2KRQFMN3BK2G26QRWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/action/storage_attestation","attest_author":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/action/author_attestation","sign_citation":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/action/citation_signature","submit_replication":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/action/replication_record"}},"created_at":"2026-08-06T01:33:30.601558+00:00","updated_at":"2026-08-06T01:33:30.601558+00:00"}