{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z7X3PEH2MCTT33CJ3TKVXJIAEF","short_pith_number":"pith:Z7X3PEH2","schema_version":"1.0","canonical_sha256":"cfefb790fa60a73dec49dcd55ba50021733f2defbb8c18e8f6911c7353b63a87","source":{"kind":"arxiv","id":"2412.17667","version":2},"attestation_state":"computed","paper":{"title":"VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Dareen Safar Alharthi, Darius Petermann, Haibin Wu, Hye-Jin Shim, Jia Qi Yip, Jiatong Shi, Jinchuan Tian, Jionghao Han, Koichi Saito, Shinji Watanabe, Siddhant Arora, Wangyou Zhang, Yichen Huang, Yiwen Zhao, You Zhang, Yuxun Tang","submitted_at":"2024-12-23T15:53:21Z","abstract_excerpt":"In this work, we introduce VERSA, a unified and standardized evaluation toolkit designed for various speech, audio, and music signals. The toolkit features a Pythonic interface with flexible configuration and dependency control, making it user-friendly and efficient. With full installation, VERSA offers 65 metrics with 729 metric variations based on different configurations. These metrics encompass evaluations utilizing diverse external resources, including matching and non-matching reference audio, text transcriptions, and text captions. As a lightweight yet comprehensive toolkit, VERSA is ve"},"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":"2412.17667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-23T15:53:21Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"e3c03d9f622e7901d18daa35d882faea1cfed8af5952a66c791a72b23f07a720","abstract_canon_sha256":"a495d993bdf1d057a7f8cc8d2e6bb484947b5d3d9e71c90d49967e98b530c5a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:15.866387Z","signature_b64":"gSD8G2JPmF+OEROeEdbx2kmKP4cGyLilvOaCPyt1ez3LPZFsY/jUYPYzsEIN3WLUdiHMk9CEkHEmFQ3Xnv5wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfefb790fa60a73dec49dcd55ba50021733f2defbb8c18e8f6911c7353b63a87","last_reissued_at":"2026-07-05T10:40:15.865858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:15.865858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chris Donahue, Dareen Safar Alharthi, Darius Petermann, Haibin Wu, Hye-Jin Shim, Jia Qi Yip, Jiatong Shi, Jinchuan Tian, Jionghao Han, Koichi Saito, Shinji Watanabe, Siddhant Arora, Wangyou Zhang, Yichen Huang, Yiwen Zhao, You Zhang, Yuxun Tang","submitted_at":"2024-12-23T15:53:21Z","abstract_excerpt":"In this work, we introduce VERSA, a unified and standardized evaluation toolkit designed for various speech, audio, and music signals. The toolkit features a Pythonic interface with flexible configuration and dependency control, making it user-friendly and efficient. With full installation, VERSA offers 65 metrics with 729 metric variations based on different configurations. These metrics encompass evaluations utilizing diverse external resources, including matching and non-matching reference audio, text transcriptions, and text captions. As a lightweight yet comprehensive toolkit, VERSA is ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17667","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/2412.17667/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":"2412.17667","created_at":"2026-07-05T10:40:15.865920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17667v2","created_at":"2026-07-05T10:40:15.865920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17667","created_at":"2026-07-05T10:40:15.865920+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7X3PEH2MCTT","created_at":"2026-07-05T10:40:15.865920+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7X3PEH2MCTT33CJ","created_at":"2026-07-05T10:40:15.865920+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7X3PEH2","created_at":"2026-07-05T10:40:15.865920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02349","citing_title":"AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF","json":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF.json","graph_json":"https://pith.science/api/pith-number/Z7X3PEH2MCTT33CJ3TKVXJIAEF/graph.json","events_json":"https://pith.science/api/pith-number/Z7X3PEH2MCTT33CJ3TKVXJIAEF/events.json","paper":"https://pith.science/paper/Z7X3PEH2"},"agent_actions":{"view_html":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF","download_json":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF.json","view_paper":"https://pith.science/paper/Z7X3PEH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17667&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7X3PEH2MCTT33CJ3TKVXJIAEF/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7X3PEH2MCTT33CJ3TKVXJIAEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF/action/storage_attestation","attest_author":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF/action/author_attestation","sign_citation":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF/action/citation_signature","submit_replication":"https://pith.science/pith/Z7X3PEH2MCTT33CJ3TKVXJIAEF/action/replication_record"}},"created_at":"2026-07-05T10:40:15.865920+00:00","updated_at":"2026-07-05T10:40:15.865920+00:00"}