{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PWEOIPQFYRZLAQXS6NAAS52IGT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fd7ebc5e00f337f1533f6c34c4bc2e5c11b89e20c6557ae207a9cbdf97b96950","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-05-03T14:58:46Z","title_canon_sha256":"7e9cd2c80a6f88939318fc006fe8995bc3400aec1a973cc03574fa7236f75eac"},"schema_version":"1.0","source":{"id":"2405.02151","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02151","created_at":"2026-07-05T09:10:30Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02151v3","created_at":"2026-07-05T09:10:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02151","created_at":"2026-07-05T09:10:30Z"},{"alias_kind":"pith_short_12","alias_value":"PWEOIPQFYRZL","created_at":"2026-07-05T09:10:30Z"},{"alias_kind":"pith_short_16","alias_value":"PWEOIPQFYRZLAQXS","created_at":"2026-07-05T09:10:30Z"},{"alias_kind":"pith_short_8","alias_value":"PWEOIPQF","created_at":"2026-07-05T09:10:30Z"}],"graph_snapshots":[{"event_id":"sha256:57724ea72be058716f7c25a601cf116743f0163ab2c3fbd07d5a6b6f38b305af","target":"graph","created_at":"2026-07-05T09:10:30Z","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/2405.02151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The continuous evolution of pre-trained speech models has greatly advanced Speech Emotion Recognition (SER). However, current research typically relies on utterance-level emotion labels, inadequately capturing the complexity of emotions within a single utterance. In this paper, we introduce GMP-TL, a novel SER framework that employs gender-augmented multi-scale pseudo-label (GMP) based transfer learning to mitigate this gap. Specifically, GMP-TL initially uses the pre-trained HuBERT, implementing multi-task learning and multi-scale k-means clustering to acquire frame-level GMPs. Subsequently, ","authors_text":"Heng Lu, Jianjun Zhao, Lei Ma, Yuguang Yang, Yu Pan","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-05-03T14:58:46Z","title":"GMP-TL: Gender-augmented Multi-scale Pseudo-label Enhanced Transfer Learning for Speech Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02151","kind":"arxiv","version":3},"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":"sha256:96e32a5509ea1a6b4c5f6eb9082dd048726c439ba786a8759c7b73ad523478b5","target":"record","created_at":"2026-07-05T09:10:30Z","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":"fd7ebc5e00f337f1533f6c34c4bc2e5c11b89e20c6557ae207a9cbdf97b96950","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-05-03T14:58:46Z","title_canon_sha256":"7e9cd2c80a6f88939318fc006fe8995bc3400aec1a973cc03574fa7236f75eac"},"schema_version":"1.0","source":{"id":"2405.02151","kind":"arxiv","version":3}},"canonical_sha256":"7d88e43e05c472b042f2f34009774834fb639d2b7f400cf1ce67223a4a3c1734","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d88e43e05c472b042f2f34009774834fb639d2b7f400cf1ce67223a4a3c1734","first_computed_at":"2026-07-05T09:10:30.871687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:30.871687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0qzP9ZacC5qRHAhDp492FzEK4938KI+qfdk1DACexwpe5MD1YeoXQjLCGckIj7OZsobhbuQjcCMxgFtxstTgBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:30.872103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02151","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96e32a5509ea1a6b4c5f6eb9082dd048726c439ba786a8759c7b73ad523478b5","sha256:57724ea72be058716f7c25a601cf116743f0163ab2c3fbd07d5a6b6f38b305af"],"state_sha256":"7f2a5254311c400a36eb0f1f5e2e4c934fc8032c0fcb028f16ce836f4dce4430"}