{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DZDTJU6IPQVX4AJYH36BFH65OL","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":"fc74fb62f2e606352b1c60056f22633473cd194f83b92a9dd4959625313648f5","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T15:28:10Z","title_canon_sha256":"2b1833c239b6346ab613c48cf099d42718095cf7b0f7754e3b492c8c1a0d8ce3"},"schema_version":"1.0","source":{"id":"2306.07848","kind":"arxiv","version":10}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07848","created_at":"2026-07-05T07:19:46Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07848v10","created_at":"2026-07-05T07:19:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07848","created_at":"2026-07-05T07:19:46Z"},{"alias_kind":"pith_short_12","alias_value":"DZDTJU6IPQVX","created_at":"2026-07-05T07:19:46Z"},{"alias_kind":"pith_short_16","alias_value":"DZDTJU6IPQVX4AJY","created_at":"2026-07-05T07:19:46Z"},{"alias_kind":"pith_short_8","alias_value":"DZDTJU6I","created_at":"2026-07-05T07:19:46Z"}],"graph_snapshots":[{"event_id":"sha256:bed4e50dba4f8987d5d5080eab554135827f5e504d69508fe3e431083eb400fd","target":"graph","created_at":"2026-07-05T07:19:46Z","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/2306.07848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive cross-modality pretraining has recently exhibited impressive success in diverse fields, whereas there is limited research on their merits in speech emotion recognition (SER). In this paper, we propose GEmo-CLAP, a kind of gender-attribute-enhanced contrastive language-audio pretraining (CLAP) method for SER. Specifically, we first construct an effective emotion CLAP (Emo-CLAP) for SER, using pre-trained text and audio encoders. Second, given the significance of gender information in SER, two novel multi-task learning based GEmo-CLAP (ML-GEmo-CLAP) and soft label based GEmo-CLAP (SL","authors_text":"Heng Lu, Jianjun Zhao, Jixun Yao, Lei Ma, Wen Fei, Yanni Hu, Yuguang Yang, Yu Pan","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T15:28:10Z","title":"GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07848","kind":"arxiv","version":10},"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:f2074e487dc8258b064582f96497be3c8a0a6f5e1ccffe74d3ccf8a2849040d5","target":"record","created_at":"2026-07-05T07:19:46Z","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":"fc74fb62f2e606352b1c60056f22633473cd194f83b92a9dd4959625313648f5","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T15:28:10Z","title_canon_sha256":"2b1833c239b6346ab613c48cf099d42718095cf7b0f7754e3b492c8c1a0d8ce3"},"schema_version":"1.0","source":{"id":"2306.07848","kind":"arxiv","version":10}},"canonical_sha256":"1e4734d3c87c2b7e01383efc129fdd72eb552d5c8244dca7dc709289a09b3b4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e4734d3c87c2b7e01383efc129fdd72eb552d5c8244dca7dc709289a09b3b4b","first_computed_at":"2026-07-05T07:19:46.086299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:46.086299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QjhsTyqC+vY5nnle1NSRvBHaOvlD5ZI2buxR6IDrJQUPFIUsEyjyOw9681uXr1EEex24FDgh1IjOWLTUMgWJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:46.086797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07848","source_kind":"arxiv","source_version":10}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2074e487dc8258b064582f96497be3c8a0a6f5e1ccffe74d3ccf8a2849040d5","sha256:bed4e50dba4f8987d5d5080eab554135827f5e504d69508fe3e431083eb400fd"],"state_sha256":"e385189f3bfed3572677862c5c6ee593c788498f43753f261194c5005c4d4d6e"}