{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ENOUB6WMCS7BGTL7SD45AUC267","short_pith_number":"pith:ENOUB6WM","schema_version":"1.0","canonical_sha256":"235d40facc14be134d7f90f9d0505af7e0abb84aee526605413e23823b9ba4b8","source":{"kind":"arxiv","id":"2505.23732","version":1},"attestation_state":"computed","paper":{"title":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Berrak Sisman, Carlos Busso, Junchen Lu, Lucas Goncalves, Shreeram Suresh Chandra","submitted_at":"2025-05-29T17:56:55Z","abstract_excerpt":"Current emotion-based contrastive language-audio pretraining (CLAP) methods typically learn by na\\\"ively aligning audio samples with corresponding text prompts. Consequently, this approach fails to capture the ordinal nature of emotions, hindering inter-emotion understanding and often resulting in a wide modality gap between the audio and text embeddings due to insufficient alignment. To handle these drawbacks, we introduce EmotionRankCLAP, a supervised contrastive learning approach that uses dimensional attributes of emotional speech and natural language prompts to jointly capture fine-graine"},"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":"2505.23732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"c8a985b13a13656ced87861b9feaee916009648e4cd80e5f2dddde04cf18c467","abstract_canon_sha256":"25ddf99219978035c71646b0d8a206a2af1ed0bce8273f3bcc82ce7fb8d087f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:13.412635Z","signature_b64":"TMrLSNkAp3VeaZYi7gODj73nhJGvXw4spb8L3HacC5asMF+hxE4Qb9aboCGQm4jUJjf5psqY/ByMaem/C4gRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"235d40facc14be134d7f90f9d0505af7e0abb84aee526605413e23823b9ba4b8","last_reissued_at":"2026-07-05T11:12:13.412155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:13.412155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Berrak Sisman, Carlos Busso, Junchen Lu, Lucas Goncalves, Shreeram Suresh Chandra","submitted_at":"2025-05-29T17:56:55Z","abstract_excerpt":"Current emotion-based contrastive language-audio pretraining (CLAP) methods typically learn by na\\\"ively aligning audio samples with corresponding text prompts. Consequently, this approach fails to capture the ordinal nature of emotions, hindering inter-emotion understanding and often resulting in a wide modality gap between the audio and text embeddings due to insufficient alignment. To handle these drawbacks, we introduce EmotionRankCLAP, a supervised contrastive learning approach that uses dimensional attributes of emotional speech and natural language prompts to jointly capture fine-graine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23732","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/2505.23732/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":"2505.23732","created_at":"2026-07-05T11:12:13.412211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23732v1","created_at":"2026-07-05T11:12:13.412211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23732","created_at":"2026-07-05T11:12:13.412211+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENOUB6WMCS7B","created_at":"2026-07-05T11:12:13.412211+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENOUB6WMCS7BGTL7","created_at":"2026-07-05T11:12:13.412211+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENOUB6WM","created_at":"2026-07-05T11:12:13.412211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23732","citing_title":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267","json":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267.json","graph_json":"https://pith.science/api/pith-number/ENOUB6WMCS7BGTL7SD45AUC267/graph.json","events_json":"https://pith.science/api/pith-number/ENOUB6WMCS7BGTL7SD45AUC267/events.json","paper":"https://pith.science/paper/ENOUB6WM"},"agent_actions":{"view_html":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267","download_json":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267.json","view_paper":"https://pith.science/paper/ENOUB6WM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23732&json=true","fetch_graph":"https://pith.science/api/pith-number/ENOUB6WMCS7BGTL7SD45AUC267/graph.json","fetch_events":"https://pith.science/api/pith-number/ENOUB6WMCS7BGTL7SD45AUC267/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267/action/storage_attestation","attest_author":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267/action/author_attestation","sign_citation":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267/action/citation_signature","submit_replication":"https://pith.science/pith/ENOUB6WMCS7BGTL7SD45AUC267/action/replication_record"}},"created_at":"2026-07-05T11:12:13.412211+00:00","updated_at":"2026-07-05T11:12:13.412211+00:00"}