{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","short_pith_number":"pith:XE6ZBCEG","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"},"canonical_sha256":"b93d908886d2a302b1bb0ab46d7a11b64ecffc008a8f4bf73734c6b60b448f32","source":{"kind":"arxiv","id":"2608.04351","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04351","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04351v1","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04351","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"pith_short_12","alias_value":"XE6ZBCEG2KRQ","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"XE6ZBCEG2KRQFMN3","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"XE6ZBCEG","created_at":"2026-08-06T01:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","target":"record","payload":{"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"},"canonical_sha256":"b93d908886d2a302b1bb0ab46d7a11b64ecffc008a8f4bf73734c6b60b448f32","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"},"source_kind":"arxiv","source_id":"2608.04351","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:33:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIt/jLqLLo6XmZ7jy2jmTpKHcpnwBU8tKYKkJxjMRqICi3xpFImTNjuIksbyd5ZNlJN1B0EBipX03u+gbiD/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:38.438666Z"},"content_sha256":"a0dc9dc5ad40f8a83c23e097854942011603b898e0b3cebf4c1f2e7560b6b868","schema_version":"1.0","event_id":"sha256:a0dc9dc5ad40f8a83c23e097854942011603b898e0b3cebf4c1f2e7560b6b868"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:33:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uQGmvpAouJbWqOtGsXIoPzKPYh+FPtZ9gW8t142rmTHEmYq4kWd9RPjglcPxHlvycc6dht/qQKMd51ixiQvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:38.439163Z"},"content_sha256":"a7fdc4d6b5afcb3c3cf3e3c01fd16dda90a2cd10b6592af35a27cddbfdd02ea0","schema_version":"1.0","event_id":"sha256:a7fdc4d6b5afcb3c3cf3e3c01fd16dda90a2cd10b6592af35a27cddbfdd02ea0"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2025.emnlp-main.514) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Chih-Kai Yang, Neo S. Ho, and Hung-yi Lee. 2025. Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey. InProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. Association for C","arxiv_id":"2608.04351","detector":"doi_compliance","evidence":{"ref_index":41,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/","reconstructed_doi":"10.18653/v1/2025.emnlp-main.514"},"severity":"advisory","ref_index":41,"audited_at":"2026-08-08T19:18:26.497914Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2025.emnlp-main.514","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"25e0e27aeda97f4709d8cbf2b81939154ebdf34957a40be7fdc2094fe6d71b0e","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18721,"payload_sha256":"5fe26b8294312a666d04b753be7e450649c3313f8de9d6d95c5b46c37f62acf5","signature_b64":"R1DskoEmLuEttcLa1hr1phjjUd69twL6p8FAJZCcfZXch0NIzhOD5jjyd2v/0Ay2c69PaBsdQgQIXau2H7tEAQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-08T19:18:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/oy0gJyJPnzcDZfhBmMUVPPXKi9TzCG9PG5DTA4QsFQk6F9OAWK5TaZ+dTRqkgDj9tNy9JfolXkrCpQynloDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:38.444228Z"},"content_sha256":"2ad5a962fe9e3fa01fe7024bd620767091559c2f05440b441a350e4a71c8fd6b","schema_version":"1.0","event_id":"sha256:2ad5a962fe9e3fa01fe7024bd620767091559c2f05440b441a350e4a71c8fd6b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1037/0033-2909.99.2.143 resolves to 'Vocal affect expression: A review and a model for future research.'. A reader following the printed text alone cannot reach it.","snippet":"Klaus R. Scherer. 1986. Vocal affect expression: A review and a model for future research.Psychological Bulletin99, 2 (1986), 143–165. doi:10.1037/0033-2909.99.2. 143","arxiv_id":"2608.04351","detector":"doi_compliance","evidence":{"ref_index":35,"verdict_class":"incontrovertible","resolved_title":"Vocal affect expression: A review and a model for future research.","printed_excerpt":"10.1037/0033-2909.99.2","reconstructed_doi":"10.1037/0033-2909.99.2.143"},"severity":"advisory","ref_index":35,"audited_at":"2026-08-08T19:18:26.497914Z","event_type":"pith.integrity.v1","detected_doi":"10.1037/0033-2909.99.2.143","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"1ff633d3e1d681f2b5feaed3a14728c7b8419f0986a892bff5919d74b0d64635","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"Vocal affect expression: A review and a model for future research.","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18720,"payload_sha256":"cbff081c959b691a724b874b69663b2c6d1e40b4f1fa9a3d24f55b260b00615b","signature_b64":"HrF06SZb+XaCfoowl0UaDDtz2pVL4Vrw1rc8v8digRx73kPfvZtoeTetakjRBksOtYZb6Uv2UAbeDlqAHwshDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-08T19:18:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oyL5dcMzEWXyMtz5x8NZlqgKDz2cjF+bfrPYM5V5we/P9dBQthlRglEA2/3ZSkP2HDSXdcXNruQoFncdcggSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:38.444620Z"},"content_sha256":"abdad718ba21a9a007af8ae3d04521de21a8f889a4f405713d5dfbb625481793","schema_version":"1.0","event_id":"sha256:abdad718ba21a9a007af8ae3d04521de21a8f889a4f405713d5dfbb625481793"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/ARXIV.2409.05566) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Soumya Dutta and Sriram Ganapathy. 2024. Leveraging Content and Acoustic Representations for Speech Emotion Recognition. doi:10.48550/ARXIV.2409. 05566","arxiv_id":"2608.04351","detector":"doi_compliance","evidence":{"ref_index":10,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.48550/arxiv.2409","reconstructed_doi":"10.48550/ARXIV.2409.05566"},"severity":"advisory","ref_index":10,"audited_at":"2026-08-08T19:18:26.497914Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/ARXIV.2409.05566","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"18604e03855d6bf035e5e44cfe15ab11272d3c419614fbd3aed56fccf87f5fa8","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18719,"payload_sha256":"082b20dfcc5257f211e30793483decca6e7a3812cab5476f638e2f1624fc9965","signature_b64":"Tj45vbttUOu+53Vq1+C7vd24hpDVc1E02W3UhC6RmQz5sVWjbWUyRRl1FXcQvYezhp+G0t7iTx4wkV2k0e9eCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-08T19:18:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChnOsERWLCH9yKD3jmN/fmqeVvj6HHijZ/pGh8GR1VQbLsf9mSy/pyF+vIhZKftLV85/Dq16UYEmcRWREgieDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:38.444980Z"},"content_sha256":"cfec91a51e41adbacd927454328b0d192be91418ea0f4f7363c675f938afb133","schema_version":"1.0","event_id":"sha256:cfec91a51e41adbacd927454328b0d192be91418ea0f4f7363c675f938afb133"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.21437/Interspeech.2025-1232) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Hongfei Du, Sidi Lu, Gang Zhou, and Ye Gao. 2025. EAA: Emotion-Aware Audio Large Language Models with Dual Cross-Attention and Context-Aware Instruction Tuning. InInterspeech 2025. 5433–5437. doi:10.21437/Interspeech. 2025-1232","arxiv_id":"2608.04351","detector":"doi_compliance","evidence":{"ref_index":9,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.21437/interspeech","reconstructed_doi":"10.21437/Interspeech.2025-1232"},"severity":"advisory","ref_index":9,"audited_at":"2026-08-08T19:18:26.497914Z","event_type":"pith.integrity.v1","detected_doi":"10.21437/Interspeech.2025-1232","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"db6abb1da5719eb79430c0cf58a5aee9fc8609ffaad70afa28f0a066e77e6ef6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18718,"payload_sha256":"a7045006d8ac37a3d74f19506d0aaea1a72ee8239bd1561e73ab3b10c6b671f4","signature_b64":"1Ra95CUQ84GjfzysIY63svExwSChJFOpaN5wkT59QGCzOAVB6Zi5UezXxiV22U2VY342obglYsruquMNPij0Aw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-08T19:18:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6BeWQAkCBsUPCgH2l63+4x3+lRjiOk5PrkyDnSi8PPchcOgFkOTi15nmD1882+gi6FuPvF8tFyX4+bmUf7GFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:38.445344Z"},"content_sha256":"e906411e6e7360b2f6dd0ffd8978872f7ed4473f65e02e977eba86ea1011914c","schema_version":"1.0","event_id":"sha256:e906411e6e7360b2f6dd0ffd8978872f7ed4473f65e02e977eba86ea1011914c"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/s10579-008-9076-6) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N. Chang, Sungbok Lee, and Shrikanth S. Narayanan. 2008. IEMOCAP: interactive emotional dyadic motion capture database.Language Resources and Eval","arxiv_id":"2608.04351","detector":"doi_compliance","evidence":{"ref_index":3,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/s10579-008-","reconstructed_doi":"10.1007/s10579-008-9076-6"},"severity":"advisory","ref_index":3,"audited_at":"2026-08-08T19:18:26.497914Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/s10579-008-9076-6","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"01634170154144e344c0f3f255bc560a9452bbe2f295ead29ed7d0090e10f92f","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18717,"payload_sha256":"6e93178bb01071def27825cfa7f9b2dfada2d8b7bf3946a5c289dcd788be038f","signature_b64":"x9gMSzcyNj/x+ZX5qq2Uxdx7e5vMGfbC6HVHgDOyYDsOG3T3zaiE1XmDPU75FtGwybBQ4LqycWNiNfHaN9rlCg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-08T19:18:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+y4CQLxcxh4AiYDy5aVD2JsweJMpHolgVP8NcJh0DPFVxc0WHoizZZIGOQbTfAPd2uR1ESF/FNrYtrYHyAy2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:29:38.445699Z"},"content_sha256":"a57c4f86283869c37eb9b47d0994caac4c5ba5777877c9653aa09f77f4b28a71","schema_version":"1.0","event_id":"sha256:a57c4f86283869c37eb9b47d0994caac4c5ba5777877c9653aa09f77f4b28a71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/bundle.json","state_url":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T22:29:38Z","links":{"resolver":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ","bundle":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/bundle.json","state":"https://pith.science/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XE6ZBCEG2KRQFMN3BK2G26QRWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XE6ZBCEG2KRQFMN3BK2G26QRWZ","merge_version":"pith-open-graph-merge-v1","event_count":7,"valid_event_count":7,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9e72f5637003c08f494b3ccf5583b2b55c64c5e32aa54ead8146c05de6bc1d12","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T01:50:37Z","title_canon_sha256":"bb21dea8386fe0fff19ba64f298d2c29f6e6e2d49b1ce58db1617e1dde9b0dd5"},"schema_version":"1.0","source":{"id":"2608.04351","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04351","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04351v1","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04351","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"pith_short_12","alias_value":"XE6ZBCEG2KRQ","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"XE6ZBCEG2KRQFMN3","created_at":"2026-08-06T01:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"XE6ZBCEG","created_at":"2026-08-06T01:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:a7fdc4d6b5afcb3c3cf3e3c01fd16dda90a2cd10b6592af35a27cddbfdd02ea0","target":"graph","created_at":"2026-08-06T01:33:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.04351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ding Luo, Jin Zeng, Ruikang Zhang, Tian Jin, Zefeng Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T01:50:37Z","title":"HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04351","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a0dc9dc5ad40f8a83c23e097854942011603b898e0b3cebf4c1f2e7560b6b868","target":"record","created_at":"2026-08-06T01:33:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9e72f5637003c08f494b3ccf5583b2b55c64c5e32aa54ead8146c05de6bc1d12","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T01:50:37Z","title_canon_sha256":"bb21dea8386fe0fff19ba64f298d2c29f6e6e2d49b1ce58db1617e1dde9b0dd5"},"schema_version":"1.0","source":{"id":"2608.04351","kind":"arxiv","version":1}},"canonical_sha256":"b93d908886d2a302b1bb0ab46d7a11b64ecffc008a8f4bf73734c6b60b448f32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b93d908886d2a302b1bb0ab46d7a11b64ecffc008a8f4bf73734c6b60b448f32","first_computed_at":"2026-08-06T01:33:30.599623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:33:30.599623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6M7uoVwYBGkcuGYsk+W+7waoFq8pKS3gInL9xBU2GK2EYu8Cg0N7EH/8RllnBmnPibgJFl2PrR0HX/QZRRygBw==","signature_status":"signed_v1","signed_at":"2026-08-06T01:33:30.601281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04351","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:2ad5a962fe9e3fa01fe7024bd620767091559c2f05440b441a350e4a71c8fd6b","sha256:a57c4f86283869c37eb9b47d0994caac4c5ba5777877c9653aa09f77f4b28a71","sha256:abdad718ba21a9a007af8ae3d04521de21a8f889a4f405713d5dfbb625481793","sha256:cfec91a51e41adbacd927454328b0d192be91418ea0f4f7363c675f938afb133","sha256:e906411e6e7360b2f6dd0ffd8978872f7ed4473f65e02e977eba86ea1011914c"]}],"invalid_events":[],"applied_event_ids":["sha256:a0dc9dc5ad40f8a83c23e097854942011603b898e0b3cebf4c1f2e7560b6b868","sha256:a7fdc4d6b5afcb3c3cf3e3c01fd16dda90a2cd10b6592af35a27cddbfdd02ea0"],"state_sha256":"8714bdfcd9400abf2d91b69749657bf02c0e92b4b88854f9fde8c9945da92d47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VavxtNzRnH9lp4CNkWC2zD6S2IzRVxGyAM2Hc4f+iP9/u7XGbO0wxIZkW/ujS6g7xtduN9R9gv4NmHC8/jfnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:29:38.449204Z","bundle_sha256":"4aa7905b5d1daa22218e5d95b6307ca79f7d603c22e31a3f127784173bf0f1da"}}