{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TBYGUU24PNF75FI7XPTV35WFQQ","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":"f028a0307546c1f5473748ca68e53e6db502264dc4352c5ebbd797b6d981b41e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T17:01:51Z","title_canon_sha256":"3a6570fe7a7e282cf65b9458b914bc4881ab34c54f7c44ef94162e2e0f712ff0"},"schema_version":"1.0","source":{"id":"2306.17103","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17103","created_at":"2026-07-05T08:48:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17103v4","created_at":"2026-07-05T08:48:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17103","created_at":"2026-07-05T08:48:10Z"},{"alias_kind":"pith_short_12","alias_value":"TBYGUU24PNF7","created_at":"2026-07-05T08:48:10Z"},{"alias_kind":"pith_short_16","alias_value":"TBYGUU24PNF75FI7","created_at":"2026-07-05T08:48:10Z"},{"alias_kind":"pith_short_8","alias_value":"TBYGUU24","created_at":"2026-07-05T08:48:10Z"}],"graph_snapshots":[{"event_id":"sha256:c04a0e7a283e8d5a64903cc21d62792ccad869bd4057a0ed5f57322c60db95fb","target":"graph","created_at":"2026-07-05T08:48:10Z","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/2306.17103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock and metal. Our novel, training-free approach utilizes Whisper, a weakly supervised robust speech recognition model, and GPT-4, today's most performant chat-based large language model. In the proposed method, Whisper functions as the \"ear\" by transcribing the audio, while GPT-4 serves as the \"brain,\" acting as an annotator with a strong performance for contextualized output sel","authors_text":"Chenghua Lin, Emmanouil Benetos, Ge Zhang, Jiahao Pan, Jie Fu, Le Zhuo, Roger Dannenberg, Ruibin Yuan, Si Liu, Wei Xue, Yike Guo, Yinghao Ma, Yizhi Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T17:01:51Z","title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17103","kind":"arxiv","version":4},"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":"sha256:0d19a109e6cad45f9ca1f17781df36de79d3e43c6b6c11a1d163336015c6f492","target":"record","created_at":"2026-07-05T08:48:10Z","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":"f028a0307546c1f5473748ca68e53e6db502264dc4352c5ebbd797b6d981b41e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T17:01:51Z","title_canon_sha256":"3a6570fe7a7e282cf65b9458b914bc4881ab34c54f7c44ef94162e2e0f712ff0"},"schema_version":"1.0","source":{"id":"2306.17103","kind":"arxiv","version":4}},"canonical_sha256":"98706a535c7b4bfe951fbbe75df6c5840f9258765e0d8c0f1c7e054f45606371","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98706a535c7b4bfe951fbbe75df6c5840f9258765e0d8c0f1c7e054f45606371","first_computed_at":"2026-07-05T08:48:10.721137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:10.721137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RaV6DNEkwTvhp5CknEeaVCtQFujPRABuEM3NUpGDury9jYhyA0ZleFbjWu2jdWpVTDNvpy9x3TQ51T5phl+hDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:10.721526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17103","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d19a109e6cad45f9ca1f17781df36de79d3e43c6b6c11a1d163336015c6f492","sha256:c04a0e7a283e8d5a64903cc21d62792ccad869bd4057a0ed5f57322c60db95fb"],"state_sha256":"c1fa8920ada15b67446ffb79ef1affaac40977c7d7bb42b64ffc6d497a4e0f50"}