{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RKEUS4ZUGZB7OMJ7RJJRJFRXZ6","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":"0ab62eec94e863b6e2a3133546b10f200e476da4080d7807b70cbccb955b5e1d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T13:46:02Z","title_canon_sha256":"6e0375a4b8f4f1b1dc2305c91dd8d63fcf7e382e819944f4c82d3f4f92acdd11"},"schema_version":"1.0","source":{"id":"2506.02088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02088","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02088v1","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02088","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"RKEUS4ZUGZB7","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"RKEUS4ZUGZB7OMJ7","created_at":"2026-07-05T11:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"RKEUS4ZU","created_at":"2026-07-05T11:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:b45954b0e5cadf24113e05c4d8aa99269b44bb239418f1922e1c9c4ad883c8ee","target":"graph","created_at":"2026-07-05T11:14:32Z","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/2506.02088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training SER models in natural, spontaneous speech is especially challenging due to the subtle expression of emotions and the unpredictable nature of real-world audio. In this paper, we present a robust system for the INTERSPEECH 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge, focusing on categorical emotion recognition. Our method combines state-of-the-art audio models with text features enriched by prosodic and spectral cues. In particular, we investigate the effectiveness of Fundamental Frequency (F0) quantization and the use of a pretrained audio tagging model. We als","authors_text":"Alef Iury Siqueira Ferreira, Alexandre Ferro Filho, Arlindo Galv\\~ao Filho, Daniel Ribeiro, Fernanda Lustosa, Frederico Santos de Oliveira, Lucas \\'Olives, Lucas Rafael Gris, Luiz Fernando, Rodrigo Tanaka","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T13:46:02Z","title":"Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02088","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:dd266dc496ce00d9b84523345cff4a83d628f3a5a47d7c61e872e08519b6e590","target":"record","created_at":"2026-07-05T11:14:32Z","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":"0ab62eec94e863b6e2a3133546b10f200e476da4080d7807b70cbccb955b5e1d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T13:46:02Z","title_canon_sha256":"6e0375a4b8f4f1b1dc2305c91dd8d63fcf7e382e819944f4c82d3f4f92acdd11"},"schema_version":"1.0","source":{"id":"2506.02088","kind":"arxiv","version":1}},"canonical_sha256":"8a894973343643f7313f8a53149637cf9c258067beb76ab633cdac84e36ee48b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a894973343643f7313f8a53149637cf9c258067beb76ab633cdac84e36ee48b","first_computed_at":"2026-07-05T11:14:32.229773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:32.229773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"izKI2CIGA7a49AB/hVhRUAopCkPHmLQnFa2rTvmPlIoCZsos7C0oQGUZUv57v5puk1J80p4O3odxwneYLv/HAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:32.230183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd266dc496ce00d9b84523345cff4a83d628f3a5a47d7c61e872e08519b6e590","sha256:b45954b0e5cadf24113e05c4d8aa99269b44bb239418f1922e1c9c4ad883c8ee"],"state_sha256":"2791c372309ae6a0d9ec1206b58c3fa6bfe25427a70bdd4b189621384563885c"}