{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PNAANOF3XB7G6TBUJGATVBNWLT","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":"8c8901af6dc1cdfb4820a9cfbd58f352e1fffefe7bc5c1f38b3e8fdff05934d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T09:41:23Z","title_canon_sha256":"7b9010c3fb9e495799106fdfe23b6e9ae28acfb03a8961c1d55104126526a9d6"},"schema_version":"1.0","source":{"id":"2506.09556","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09556","created_at":"2026-07-05T12:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09556v2","created_at":"2026-07-05T12:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09556","created_at":"2026-07-05T12:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"PNAANOF3XB7G","created_at":"2026-07-05T12:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"PNAANOF3XB7G6TBU","created_at":"2026-07-05T12:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"PNAANOF3","created_at":"2026-07-05T12:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:38c41b6227659c498e01ef8bfd71c7ffc3d9071a48641738089b5e8ad984dfef","target":"graph","created_at":"2026-07-05T12:04:36Z","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/2506.09556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"SER is a challenging task due to the subjective nature of human emotions and their uneven representation under naturalistic conditions. We propose MEDUSA, a multimodal framework with a four-stage training pipeline, which effectively handles class imbalance and emotion ambiguity. The first two stages train an ensemble of classifiers that utilize DeepSER, a novel extension of a deep cross-modal transformer fusion mechanism from pretrained self-supervised acoustic and linguistic representations. Manifold MixUp is employed for further regularization. The last two stages optimize a trainable meta-c","authors_text":"Alexandros Potamianos, Anastasia Poulopoulou, Antonios Kritikos, Athanasios Katsamanis, Despoina Kosmopoulou, Efthymios Georgiou, Georgios Chatzichristodoulou, Vassilis Katsouros","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T09:41:23Z","title":"MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09556","kind":"arxiv","version":2},"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:a0654726f3159f35f2ff4498288d7154a783f6840fff0732154423aec887fb19","target":"record","created_at":"2026-07-05T12:04:36Z","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":"8c8901af6dc1cdfb4820a9cfbd58f352e1fffefe7bc5c1f38b3e8fdff05934d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T09:41:23Z","title_canon_sha256":"7b9010c3fb9e495799106fdfe23b6e9ae28acfb03a8961c1d55104126526a9d6"},"schema_version":"1.0","source":{"id":"2506.09556","kind":"arxiv","version":2}},"canonical_sha256":"7b4006b8bbb87e6f4c3449813a85b65ceef44b24274b073b6e67580295ad0ec1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b4006b8bbb87e6f4c3449813a85b65ceef44b24274b073b6e67580295ad0ec1","first_computed_at":"2026-07-05T12:04:36.312826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:36.312826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"osBgrOSi8rOa6GI2UHrAN8p7E4G5NKb2pMzF1RvcyyB6kjC6RAOphpJKsw1rnil2fGy0tKAszHfn/8fGLTN3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:36.313409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09556","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0654726f3159f35f2ff4498288d7154a783f6840fff0732154423aec887fb19","sha256:38c41b6227659c498e01ef8bfd71c7ffc3d9071a48641738089b5e8ad984dfef"],"state_sha256":"24484b2e8d8e3a993cb35253db413ff9e7cb9005e255d63610ab9615593d0cb6"}