{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:THACARPVGVXBOLWZYCNKR6GDHU","short_pith_number":"pith:THACARPV","schema_version":"1.0","canonical_sha256":"99c02045f5356e172ed9c09aa8f8c33d3414b7571ea43115f489ddc023591caa","source":{"kind":"arxiv","id":"2402.13018","version":4},"attestation_state":"computed","paper":{"title":"EMO-SUPERB: An In-depth Look at Speech Emotion Recognition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chi-Chun Lee, Haibin Wu, Huang-Cheng Chou, Hung-yi Lee, Jiawei Du, Jyh-Shing Roger Jang, Kai-Wei Chang, Lucas Goncalves","submitted_at":"2024-02-20T14:00:53Z","abstract_excerpt":"Speech emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-d"},"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":"2402.13018","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-20T14:00:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"bb6f10618ec4fb9d386b7eac1b89899719920b6fca13d692f9079c3bae2794ba","abstract_canon_sha256":"7d288c9122c2977ea1f9dd1ef377c23edeaa7b5df7e9b0db33a6a91608276140"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:54.968306Z","signature_b64":"EoD5KkfAXBoGnZQwM5MckKDkHLXPALki3zxFAw4dmN+AIkW8TbGr1ZQWRF7P+IKDoetq/+OWwLKnBYixlF2lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99c02045f5356e172ed9c09aa8f8c33d3414b7571ea43115f489ddc023591caa","last_reissued_at":"2026-07-05T07:54:54.967889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:54.967889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMO-SUPERB: An In-depth Look at Speech Emotion Recognition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chi-Chun Lee, Haibin Wu, Huang-Cheng Chou, Hung-yi Lee, Jiawei Du, Jyh-Shing Roger Jang, Kai-Wei Chang, Lucas Goncalves","submitted_at":"2024-02-20T14:00:53Z","abstract_excerpt":"Speech emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13018","kind":"arxiv","version":4},"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/2402.13018/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":"2402.13018","created_at":"2026-07-05T07:54:54.967948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13018v4","created_at":"2026-07-05T07:54:54.967948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13018","created_at":"2026-07-05T07:54:54.967948+00:00"},{"alias_kind":"pith_short_12","alias_value":"THACARPVGVXB","created_at":"2026-07-05T07:54:54.967948+00:00"},{"alias_kind":"pith_short_16","alias_value":"THACARPVGVXBOLWZ","created_at":"2026-07-05T07:54:54.967948+00:00"},{"alias_kind":"pith_short_8","alias_value":"THACARPV","created_at":"2026-07-05T07:54:54.967948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.12672","citing_title":"Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01597","citing_title":"Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU","json":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU.json","graph_json":"https://pith.science/api/pith-number/THACARPVGVXBOLWZYCNKR6GDHU/graph.json","events_json":"https://pith.science/api/pith-number/THACARPVGVXBOLWZYCNKR6GDHU/events.json","paper":"https://pith.science/paper/THACARPV"},"agent_actions":{"view_html":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU","download_json":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU.json","view_paper":"https://pith.science/paper/THACARPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13018&json=true","fetch_graph":"https://pith.science/api/pith-number/THACARPVGVXBOLWZYCNKR6GDHU/graph.json","fetch_events":"https://pith.science/api/pith-number/THACARPVGVXBOLWZYCNKR6GDHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU/action/storage_attestation","attest_author":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU/action/author_attestation","sign_citation":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU/action/citation_signature","submit_replication":"https://pith.science/pith/THACARPVGVXBOLWZYCNKR6GDHU/action/replication_record"}},"created_at":"2026-07-05T07:54:54.967948+00:00","updated_at":"2026-07-05T07:54:54.967948+00:00"}