{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ENOUB6WMCS7BGTL7SD45AUC267","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":"25ddf99219978035c71646b0d8a206a2af1ed0bce8273f3bcc82ce7fb8d087f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:56:55Z","title_canon_sha256":"c8a985b13a13656ced87861b9feaee916009648e4cd80e5f2dddde04cf18c467"},"schema_version":"1.0","source":{"id":"2505.23732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23732","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23732v1","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23732","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_12","alias_value":"ENOUB6WMCS7B","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_16","alias_value":"ENOUB6WMCS7BGTL7","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_8","alias_value":"ENOUB6WM","created_at":"2026-07-05T11:12:13Z"}],"graph_snapshots":[{"event_id":"sha256:e2b4f6a320bf583b0160701616092d2e5500daae4e921e7ffd127d0e7cbf66b2","target":"graph","created_at":"2026-07-05T11:12:13Z","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/2505.23732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Berrak Sisman, Carlos Busso, Junchen Lu, Lucas Goncalves, Shreeram Suresh Chandra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:56:55Z","title":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23732","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:f1888d87263c4f02eb6282f62372d832d865c1858795324759a5832e4d4049e6","target":"record","created_at":"2026-07-05T11:12:13Z","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":"25ddf99219978035c71646b0d8a206a2af1ed0bce8273f3bcc82ce7fb8d087f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:56:55Z","title_canon_sha256":"c8a985b13a13656ced87861b9feaee916009648e4cd80e5f2dddde04cf18c467"},"schema_version":"1.0","source":{"id":"2505.23732","kind":"arxiv","version":1}},"canonical_sha256":"235d40facc14be134d7f90f9d0505af7e0abb84aee526605413e23823b9ba4b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"235d40facc14be134d7f90f9d0505af7e0abb84aee526605413e23823b9ba4b8","first_computed_at":"2026-07-05T11:12:13.412155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:13.412155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TMrLSNkAp3VeaZYi7gODj73nhJGvXw4spb8L3HacC5asMF+hxE4Qb9aboCGQm4jUJjf5psqY/ByMaem/C4gRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:13.412635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1888d87263c4f02eb6282f62372d832d865c1858795324759a5832e4d4049e6","sha256:e2b4f6a320bf583b0160701616092d2e5500daae4e921e7ffd127d0e7cbf66b2"],"state_sha256":"e312b0bd2e2e0822d38e104bb5093cf724f5f9a18a7d57b56de5f5626af828d3"}