{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U5MS422GV5KCPJTTNR3Z22UTR2","short_pith_number":"pith:U5MS422G","schema_version":"1.0","canonical_sha256":"a7592e6b46af5427a6736c779d6a938ea25daa626a32777575d2cd186618d900","source":{"kind":"arxiv","id":"2203.06849","version":1},"attestation_state":"computed","paper":{"title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Andy T. Liu, Cheng-I Jeff Lai, Heng-Jui Chang, Hsiang-Sheng Tsai, Hsuan-Jui Chen, Hung-yi Lee, Jiatong Shi, Kushal Lakhotia, Phil Hall, Shang-Wen Li, Shinji Watanabe, Shu-wen Yang, Shuyan Dong, Wen-Chin Huang, Xuankai Chang, Zili Huang","submitted_at":"2022-03-14T04:26:40Z","abstract_excerpt":"Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabi"},"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":"2203.06849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-14T04:26:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5ca1132542000f0ab641a1fd96938a3a6ab76b38b89d4d027ee7f77f31441737","abstract_canon_sha256":"dc5496529c1ebdf291c22fa8e97a19076f8d03e19754a23837f8acf9897009f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:56.617999Z","signature_b64":"Kehvbv+wk6V/auV4vB/bJp3RI8c3eoTC5ByUj2JfoXuU94yQPLN1JXgzi17idYCNoWmHI6y67lvdP/wNc0bXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7592e6b46af5427a6736c779d6a938ea25daa626a32777575d2cd186618d900","last_reissued_at":"2026-07-05T04:04:56.617472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:56.617472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Andy T. Liu, Cheng-I Jeff Lai, Heng-Jui Chang, Hsiang-Sheng Tsai, Hsuan-Jui Chen, Hung-yi Lee, Jiatong Shi, Kushal Lakhotia, Phil Hall, Shang-Wen Li, Shinji Watanabe, Shu-wen Yang, Shuyan Dong, Wen-Chin Huang, Xuankai Chang, Zili Huang","submitted_at":"2022-03-14T04:26:40Z","abstract_excerpt":"Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06849","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/2203.06849/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":"2203.06849","created_at":"2026-07-05T04:04:56.617530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06849v1","created_at":"2026-07-05T04:04:56.617530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06849","created_at":"2026-07-05T04:04:56.617530+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5MS422GV5KC","created_at":"2026-07-05T04:04:56.617530+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5MS422GV5KCPJTT","created_at":"2026-07-05T04:04:56.617530+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5MS422G","created_at":"2026-07-05T04:04:56.617530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01482","citing_title":"A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10494","citing_title":"Multi-layer attentive probing improves transfer of audio representations for bioacoustics","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01381","citing_title":"A framework for analyzing concept representations in neural models","ref_index":204,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2","json":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2.json","graph_json":"https://pith.science/api/pith-number/U5MS422GV5KCPJTTNR3Z22UTR2/graph.json","events_json":"https://pith.science/api/pith-number/U5MS422GV5KCPJTTNR3Z22UTR2/events.json","paper":"https://pith.science/paper/U5MS422G"},"agent_actions":{"view_html":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2","download_json":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2.json","view_paper":"https://pith.science/paper/U5MS422G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06849&json=true","fetch_graph":"https://pith.science/api/pith-number/U5MS422GV5KCPJTTNR3Z22UTR2/graph.json","fetch_events":"https://pith.science/api/pith-number/U5MS422GV5KCPJTTNR3Z22UTR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2/action/storage_attestation","attest_author":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2/action/author_attestation","sign_citation":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2/action/citation_signature","submit_replication":"https://pith.science/pith/U5MS422GV5KCPJTTNR3Z22UTR2/action/replication_record"}},"created_at":"2026-07-05T04:04:56.617530+00:00","updated_at":"2026-07-05T04:04:56.617530+00:00"}