{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CUWITIEF75UNQBBJTFNOVBJKEM","short_pith_number":"pith:CUWITIEF","schema_version":"1.0","canonical_sha256":"152c89a085ff68d80429995aea852a230aed5bd398886d9d7c9ad17c9a959234","source":{"kind":"arxiv","id":"2506.02258","version":1},"attestation_state":"computed","paper":{"title":"Are Mamba-based Audio Foundation Models the Best Fit for Non-Verbal Emotion Recognition?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ananda Chandra Nayak, Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Orchid Chetia Phukan, Rajesh Sharma, Sanjib Kumar Nayak, Swarup Ranjan Behera","submitted_at":"2025-06-02T21:04:29Z","abstract_excerpt":"In this work, we focus on non-verbal vocal sounds emotion recognition (NVER). We investigate mamba-based audio foundation models (MAFMs) for the first time for NVER and hypothesize that MAFMs will outperform attention-based audio foundation models (AAFMs) for NVER by leveraging its state-space modeling to capture intrinsic emotional structures more effectively. Unlike AAFMs, which may amplify irrelevant patterns due to their attention mechanisms, MAFMs will extract more stable and context-aware representations, enabling better differentiation of subtle non-verbal emotional cues. Our experiment"},"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":"2506.02258","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T21:04:29Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b1ceef9d760da407f7ccdeb23a7ed76203d73dc55e88026fbca3968a4a6b689b","abstract_canon_sha256":"28c318cd80823a91456826c2b086803b70dbdd47e1fbc37b4d3a48bb72b5047a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:35.477861Z","signature_b64":"WSveV2SswtL9H1Ne9IYcENEyf1dg2lQ+vCGP4zXHCC312J89pi7Bhwjc/7ejb0en9ubgE4QJKXOxG73sHf4kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"152c89a085ff68d80429995aea852a230aed5bd398886d9d7c9ad17c9a959234","last_reissued_at":"2026-07-05T11:14:35.477398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:35.477398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Mamba-based Audio Foundation Models the Best Fit for Non-Verbal Emotion Recognition?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ananda Chandra Nayak, Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Orchid Chetia Phukan, Rajesh Sharma, Sanjib Kumar Nayak, Swarup Ranjan Behera","submitted_at":"2025-06-02T21:04:29Z","abstract_excerpt":"In this work, we focus on non-verbal vocal sounds emotion recognition (NVER). We investigate mamba-based audio foundation models (MAFMs) for the first time for NVER and hypothesize that MAFMs will outperform attention-based audio foundation models (AAFMs) for NVER by leveraging its state-space modeling to capture intrinsic emotional structures more effectively. Unlike AAFMs, which may amplify irrelevant patterns due to their attention mechanisms, MAFMs will extract more stable and context-aware representations, enabling better differentiation of subtle non-verbal emotional cues. Our experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02258","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/2506.02258/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":"2506.02258","created_at":"2026-07-05T11:14:35.477455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02258v1","created_at":"2026-07-05T11:14:35.477455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02258","created_at":"2026-07-05T11:14:35.477455+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUWITIEF75UN","created_at":"2026-07-05T11:14:35.477455+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUWITIEF75UNQBBJ","created_at":"2026-07-05T11:14:35.477455+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUWITIEF","created_at":"2026-07-05T11:14:35.477455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM","json":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM.json","graph_json":"https://pith.science/api/pith-number/CUWITIEF75UNQBBJTFNOVBJKEM/graph.json","events_json":"https://pith.science/api/pith-number/CUWITIEF75UNQBBJTFNOVBJKEM/events.json","paper":"https://pith.science/paper/CUWITIEF"},"agent_actions":{"view_html":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM","download_json":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM.json","view_paper":"https://pith.science/paper/CUWITIEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02258&json=true","fetch_graph":"https://pith.science/api/pith-number/CUWITIEF75UNQBBJTFNOVBJKEM/graph.json","fetch_events":"https://pith.science/api/pith-number/CUWITIEF75UNQBBJTFNOVBJKEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM/action/storage_attestation","attest_author":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM/action/author_attestation","sign_citation":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM/action/citation_signature","submit_replication":"https://pith.science/pith/CUWITIEF75UNQBBJTFNOVBJKEM/action/replication_record"}},"created_at":"2026-07-05T11:14:35.477455+00:00","updated_at":"2026-07-05T11:14:35.477455+00:00"}