{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7LDQTKHA5YGVLBV5A7KGVDGL77","short_pith_number":"pith:7LDQTKHA","canonical_record":{"source":{"id":"2505.20007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T13:58:12Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1a73d21f1861ee8f91903a300fe83f8e7e03f31d0cd51b97baa3a66cdf13035e","abstract_canon_sha256":"835616fa23c76c3fcca34ab31b8ef427f4a34cd752a825d9cbeb3a004fff4de5"},"schema_version":"1.0"},"canonical_sha256":"fac709a8e0ee0d5586bd07d46a8ccbffe6c9c925841205996d9bceb147eb95df","source":{"kind":"arxiv","id":"2505.20007","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20007","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20007v2","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20007","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"7LDQTKHA5YGV","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"7LDQTKHA5YGVLBV5","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"7LDQTKHA","created_at":"2026-07-05T11:13:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7LDQTKHA5YGVLBV5A7KGVDGL77","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T13:58:12Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1a73d21f1861ee8f91903a300fe83f8e7e03f31d0cd51b97baa3a66cdf13035e","abstract_canon_sha256":"835616fa23c76c3fcca34ab31b8ef427f4a34cd752a825d9cbeb3a004fff4de5"},"schema_version":"1.0"},"canonical_sha256":"fac709a8e0ee0d5586bd07d46a8ccbffe6c9c925841205996d9bceb147eb95df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:27.036841Z","signature_b64":"WlYn5iKe009l77LG44TnlYgK91lgaR7g4d/ejiS8ffwkQZE6wkYLtYSDUCD7rBoVuos8VHX+1zPZir/KdbdlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fac709a8e0ee0d5586bd07d46a8ccbffe6c9c925841205996d9bceb147eb95df","last_reissued_at":"2026-07-05T11:13:27.036342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:27.036342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20007","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8mNSulwuH9/mWtrWACCfO11iaO7pbmeZFP8VRQ7/qUvK1Lqr8Znh7JpQ1gt2Urdfw2BAp2egXdZDQ0r9kdZtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:18:19.638705Z"},"content_sha256":"f61d2ce7852500c41d4f2ea24fab12a0894bbf488cb813d00045860a2f68fa20","schema_version":"1.0","event_id":"sha256:f61d2ce7852500c41d4f2ea24fab12a0894bbf488cb813d00045860a2f68fa20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7LDQTKHA5YGVLBV5A7KGVDGL77","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jo\\~ao Lima, Leonardo Marques, Lucas Ueda, Paula Costa","submitted_at":"2025-05-26T13:58:12Z","abstract_excerpt":"Emotion plays a fundamental role in human interaction, and therefore systems capable of identifying emotions in speech are crucial in the context of human-computer interaction. Speech emotion recognition (SER) is a challenging problem, particularly in natural speech and when the available data is imbalanced across emotions. This paper presents our proposed system in the context of the 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge. Our proposed architecture leverages cross-modality, utilizing cross-modal attention to fuse representations from different modalities. To addr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20007","kind":"arxiv","version":2},"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/2505.20007/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xsaj+rhBxSPntgeMyNAenzM74eIKZG7kUD2F6W+qQ6tVNbj0uhqA+ZNQrK9Ws6qc32blQxFopxLCfMMlIXCvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:18:19.639079Z"},"content_sha256":"b44d22456a149d1a671ef25ea6f8e1e7b291f4d4d336040d69dc02974ef008b0","schema_version":"1.0","event_id":"sha256:b44d22456a149d1a671ef25ea6f8e1e7b291f4d4d336040d69dc02974ef008b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7LDQTKHA5YGVLBV5A7KGVDGL77/bundle.json","state_url":"https://pith.science/pith/7LDQTKHA5YGVLBV5A7KGVDGL77/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7LDQTKHA5YGVLBV5A7KGVDGL77/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T05:18:19Z","links":{"resolver":"https://pith.science/pith/7LDQTKHA5YGVLBV5A7KGVDGL77","bundle":"https://pith.science/pith/7LDQTKHA5YGVLBV5A7KGVDGL77/bundle.json","state":"https://pith.science/pith/7LDQTKHA5YGVLBV5A7KGVDGL77/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7LDQTKHA5YGVLBV5A7KGVDGL77/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7LDQTKHA5YGVLBV5A7KGVDGL77","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":"835616fa23c76c3fcca34ab31b8ef427f4a34cd752a825d9cbeb3a004fff4de5","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T13:58:12Z","title_canon_sha256":"1a73d21f1861ee8f91903a300fe83f8e7e03f31d0cd51b97baa3a66cdf13035e"},"schema_version":"1.0","source":{"id":"2505.20007","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20007","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20007v2","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20007","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"7LDQTKHA5YGV","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"7LDQTKHA5YGVLBV5","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"7LDQTKHA","created_at":"2026-07-05T11:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:b44d22456a149d1a671ef25ea6f8e1e7b291f4d4d336040d69dc02974ef008b0","target":"graph","created_at":"2026-07-05T11:13:27Z","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/2505.20007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotion plays a fundamental role in human interaction, and therefore systems capable of identifying emotions in speech are crucial in the context of human-computer interaction. Speech emotion recognition (SER) is a challenging problem, particularly in natural speech and when the available data is imbalanced across emotions. This paper presents our proposed system in the context of the 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge. Our proposed architecture leverages cross-modality, utilizing cross-modal attention to fuse representations from different modalities. To addr","authors_text":"Jo\\~ao Lima, Leonardo Marques, Lucas Ueda, Paula Costa","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T13:58:12Z","title":"Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20007","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:f61d2ce7852500c41d4f2ea24fab12a0894bbf488cb813d00045860a2f68fa20","target":"record","created_at":"2026-07-05T11:13:27Z","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":"835616fa23c76c3fcca34ab31b8ef427f4a34cd752a825d9cbeb3a004fff4de5","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T13:58:12Z","title_canon_sha256":"1a73d21f1861ee8f91903a300fe83f8e7e03f31d0cd51b97baa3a66cdf13035e"},"schema_version":"1.0","source":{"id":"2505.20007","kind":"arxiv","version":2}},"canonical_sha256":"fac709a8e0ee0d5586bd07d46a8ccbffe6c9c925841205996d9bceb147eb95df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fac709a8e0ee0d5586bd07d46a8ccbffe6c9c925841205996d9bceb147eb95df","first_computed_at":"2026-07-05T11:13:27.036342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:27.036342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WlYn5iKe009l77LG44TnlYgK91lgaR7g4d/ejiS8ffwkQZE6wkYLtYSDUCD7rBoVuos8VHX+1zPZir/KdbdlDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:27.036841Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20007","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f61d2ce7852500c41d4f2ea24fab12a0894bbf488cb813d00045860a2f68fa20","sha256:b44d22456a149d1a671ef25ea6f8e1e7b291f4d4d336040d69dc02974ef008b0"],"state_sha256":"563c65d0cc011c5d4b473b614cf994f9e68e1c79a54ca355384b54ca958c2962"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BOR9IQxx4xqsTPVcgcQutlCmiGcoEEwBqm9x3nIgcCDJp47/HopF71rJ7hG8VF9WrHmsUu2pSZDug2959F5dAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T05:18:19.641561Z","bundle_sha256":"7ab12615f80a8c157b9f90699cb3d52291c36b0e6f42106b69351bbe442e46e9"}}