{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WQKZIVXCJC6ELFJJ7SWJSIX3S6","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":"dcb793949e4f4dd0a4c0b1809ea7041f373ee44ab951f2e1b521cd739d869764","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-26T13:51:56Z","title_canon_sha256":"407893d1519021490f81e1854209b49c1ba9351d4d30145ff667b5b542daa42b"},"schema_version":"1.0","source":{"id":"2209.12702","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12702","created_at":"2026-07-05T05:10:58Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12702v4","created_at":"2026-07-05T05:10:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12702","created_at":"2026-07-05T05:10:58Z"},{"alias_kind":"pith_short_12","alias_value":"WQKZIVXCJC6E","created_at":"2026-07-05T05:10:58Z"},{"alias_kind":"pith_short_16","alias_value":"WQKZIVXCJC6ELFJJ","created_at":"2026-07-05T05:10:58Z"},{"alias_kind":"pith_short_8","alias_value":"WQKZIVXC","created_at":"2026-07-05T05:10:58Z"}],"graph_snapshots":[{"event_id":"sha256:db8eb7b4acb494d932ff4966324fe1ce266dea80edfdc636e1fc80e9528509af","target":"graph","created_at":"2026-07-05T05:10:58Z","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/2209.12702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lyrics recognition is an important task in music processing. Despite traditional algorithms such as the hybrid HMM- TDNN model achieving good performance, studies on applying end-to-end models and self-supervised learning (SSL) are limited. In this paper, we first establish an end-to-end baseline for lyrics recognition and then explore the performance of SSL models on lyrics recognition task. We evaluate a variety of upstream SSL models with different training methods (masked reconstruction, masked prediction, autoregressive reconstruction, and contrastive learning). Our end-to-end self-superv","authors_text":"Leibny Paola Garcia, Roberto Togneri, Shuyue Stella Li, Xiangyu Zhang, Zhanhong He","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-26T13:51:56Z","title":"End-to-End Lyrics Recognition with Self-supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12702","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":"sha256:5ca50a4dd91df2f57bf68c54e0ad89ec52fef6a3dcca68f493e56cae9a199b2e","target":"record","created_at":"2026-07-05T05:10:58Z","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":"dcb793949e4f4dd0a4c0b1809ea7041f373ee44ab951f2e1b521cd739d869764","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-26T13:51:56Z","title_canon_sha256":"407893d1519021490f81e1854209b49c1ba9351d4d30145ff667b5b542daa42b"},"schema_version":"1.0","source":{"id":"2209.12702","kind":"arxiv","version":4}},"canonical_sha256":"b4159456e248bc459529fcac9922fb979075d9bfcee02d431d3c0bb43efa02b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4159456e248bc459529fcac9922fb979075d9bfcee02d431d3c0bb43efa02b4","first_computed_at":"2026-07-05T05:10:58.418009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:58.418009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LoiDgHeoplqAdzfPHsE3XU1bCrKKdI7O8jnZBYpdKobv3XP74CCIZ5BzamuxDmD+tpMfpbA7f4CJWMC4WLbJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:58.418438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.12702","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ca50a4dd91df2f57bf68c54e0ad89ec52fef6a3dcca68f493e56cae9a199b2e","sha256:db8eb7b4acb494d932ff4966324fe1ce266dea80edfdc636e1fc80e9528509af"],"state_sha256":"2f3ff78d8019a868af3b4e684fafd0794365cbe58f7c74d843c6f903c9716c7e"}