{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z7X3PEH2MCTT33CJ3TKVXJIAEF","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":"a495d993bdf1d057a7f8cc8d2e6bb484947b5d3d9e71c90d49967e98b530c5a4","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-23T15:53:21Z","title_canon_sha256":"e3c03d9f622e7901d18daa35d882faea1cfed8af5952a66c791a72b23f07a720"},"schema_version":"1.0","source":{"id":"2412.17667","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17667","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17667v2","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17667","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"Z7X3PEH2MCTT","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_16","alias_value":"Z7X3PEH2MCTT33CJ","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_8","alias_value":"Z7X3PEH2","created_at":"2026-07-05T10:40:15Z"}],"graph_snapshots":[{"event_id":"sha256:e5ed34eec54fedd3d19ec3e44a798198871aeb74fd4f842d978072b8601e6f26","target":"graph","created_at":"2026-07-05T10:40:15Z","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/2412.17667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-23T15:53:21Z","title":"VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17667","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":"sha256:80f36d8c36135cdfb74c5e7dc5c05f771e2c4f4bdc1965df7422bd99166e41af","target":"record","created_at":"2026-07-05T10:40:15Z","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":"a495d993bdf1d057a7f8cc8d2e6bb484947b5d3d9e71c90d49967e98b530c5a4","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-23T15:53:21Z","title_canon_sha256":"e3c03d9f622e7901d18daa35d882faea1cfed8af5952a66c791a72b23f07a720"},"schema_version":"1.0","source":{"id":"2412.17667","kind":"arxiv","version":2}},"canonical_sha256":"cfefb790fa60a73dec49dcd55ba50021733f2defbb8c18e8f6911c7353b63a87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfefb790fa60a73dec49dcd55ba50021733f2defbb8c18e8f6911c7353b63a87","first_computed_at":"2026-07-05T10:40:15.865858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:15.865858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gSD8G2JPmF+OEROeEdbx2kmKP4cGyLilvOaCPyt1ez3LPZFsY/jUYPYzsEIN3WLUdiHMk9CEkHEmFQ3Xnv5wDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:15.866387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17667","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80f36d8c36135cdfb74c5e7dc5c05f771e2c4f4bdc1965df7422bd99166e41af","sha256:e5ed34eec54fedd3d19ec3e44a798198871aeb74fd4f842d978072b8601e6f26"],"state_sha256":"bd2b26469a8d28e22d3946fbe92bc5d9ea128acfe708b415de3099097d22329d"}