{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MET3RT2MA2EH3DF7FG6WQSLVO5","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":"f89a8c6a81dd5d872d075f6f65cd8330ce0e6e52a19defd7523f329a759a7f75","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-26T02:54:14Z","title_canon_sha256":"9ab5fffeca2f5226c79ae83e7f07cf18a9bebe7ad9b9e4b2d1fdb756ff8cc8da"},"schema_version":"1.0","source":{"id":"2505.19437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19437","created_at":"2026-07-05T11:09:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19437v1","created_at":"2026-07-05T11:09:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19437","created_at":"2026-07-05T11:09:30Z"},{"alias_kind":"pith_short_12","alias_value":"MET3RT2MA2EH","created_at":"2026-07-05T11:09:30Z"},{"alias_kind":"pith_short_16","alias_value":"MET3RT2MA2EH3DF7","created_at":"2026-07-05T11:09:30Z"},{"alias_kind":"pith_short_8","alias_value":"MET3RT2M","created_at":"2026-07-05T11:09:30Z"}],"graph_snapshots":[{"event_id":"sha256:3d44b980addae129c7dbdb3dd6ef94a334c860e560c905ee0a6980aeb3c5f3a3","target":"graph","created_at":"2026-07-05T11:09:30Z","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/2505.19437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Contrastive Language-Audio Pretraining (CLAP) model has demonstrated excellent performance in general audio description-related tasks, such as audio retrieval. However, in the emerging field of emotional speaking style description (ESSD), cross-modal contrastive pretraining remains largely unexplored. In this paper, we propose a novel speech retrieval task called emotional speaking style retrieval (ESSR), and ESS-CLAP, an emotional speaking style CLAP model tailored for learning relationship between speech and natural language descriptions. In addition, we further propose relation-augmente","authors_text":"Desheng Hu, Haoqin Sun, Hui Wang, Jiabei He, Jiaming Zhou, Jingguang Tian, Shiwan Zhao, Xiangyu Kong, Xinhui Hu, Xinkang Xu, Yong Qin","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-26T02:54:14Z","title":"RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19437","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:bb558e7648e036e32a046767f23a56290225e39d31dc8a8fdbdb479960115064","target":"record","created_at":"2026-07-05T11:09:30Z","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":"f89a8c6a81dd5d872d075f6f65cd8330ce0e6e52a19defd7523f329a759a7f75","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-26T02:54:14Z","title_canon_sha256":"9ab5fffeca2f5226c79ae83e7f07cf18a9bebe7ad9b9e4b2d1fdb756ff8cc8da"},"schema_version":"1.0","source":{"id":"2505.19437","kind":"arxiv","version":1}},"canonical_sha256":"6127b8cf4c06887d8cbf29bd684975776c62297ef080ed9ef57ac705bbfe62c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6127b8cf4c06887d8cbf29bd684975776c62297ef080ed9ef57ac705bbfe62c8","first_computed_at":"2026-07-05T11:09:30.256132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:30.256132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sVP4QxyyzXJvnNie1In1QFmQBgg5MWpv+1xg0Jczu9o5yApG5nBSxd/LQhm7JIK75sTUgD4i6hElmduNfaNTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:30.256653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb558e7648e036e32a046767f23a56290225e39d31dc8a8fdbdb479960115064","sha256:3d44b980addae129c7dbdb3dd6ef94a334c860e560c905ee0a6980aeb3c5f3a3"],"state_sha256":"cfa7fa8aa03a9f09bc97412b7c6a0c3d651f732ac6c156a29e65ba3f218877e8"}