{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EFJY4OYWCEYCH7VPW2Z6R3NTZK","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":"388aa6fd458beaef0e6b08dec8a8e021002fb66e920e7cd67d0e1eada17a318c","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-06T14:26:00Z","title_canon_sha256":"30f20c28ee8e49ced075e2f7555970a04cb6e2bd1bb2d290b4264566ddbde861"},"schema_version":"1.0","source":{"id":"2501.03038","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03038","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03038v2","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03038","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_12","alias_value":"EFJY4OYWCEYC","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_16","alias_value":"EFJY4OYWCEYCH7VP","created_at":"2026-07-05T09:57:50Z"},{"alias_kind":"pith_short_8","alias_value":"EFJY4OYW","created_at":"2026-07-05T09:57:50Z"}],"graph_snapshots":[{"event_id":"sha256:baf910ea89902f4dc54715476f79802c9113f07576aac4a5fc2dfec400a84b58","target":"graph","created_at":"2026-07-05T09:57:50Z","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/2501.03038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Music Transcription (AMT), aiming to get musical notes from raw audio, typically uses frame-level systems with piano-roll outputs or language model (LM)-based systems with note-level predictions. However, frame-level systems require manual thresholding, while the LM-based systems struggle with long sequences. In this paper, we propose a hybrid method combining pre-trained roll-based encoders with an LM decoder to leverage the strengths of both methods. Besides, our approach employs a hierarchical prediction strategy, first predicting onset and pitch, then velocity, and finally offset","authors_text":"Dichucheng Li, Qiuqiang Kong, Yongyi Zang","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-06T14:26:00Z","title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03038","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":"sha256:2d728fe7b7f65fc68894296aa2f0e24314cef02f7a7b9b2707a31b256718967d","target":"record","created_at":"2026-07-05T09:57:50Z","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":"388aa6fd458beaef0e6b08dec8a8e021002fb66e920e7cd67d0e1eada17a318c","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-06T14:26:00Z","title_canon_sha256":"30f20c28ee8e49ced075e2f7555970a04cb6e2bd1bb2d290b4264566ddbde861"},"schema_version":"1.0","source":{"id":"2501.03038","kind":"arxiv","version":2}},"canonical_sha256":"21538e3b16113023feafb6b3e8edb3ca8e2eed98600c776959f592c5df354d04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21538e3b16113023feafb6b3e8edb3ca8e2eed98600c776959f592c5df354d04","first_computed_at":"2026-07-05T09:57:50.952834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:50.952834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3sE7/C5FWrGADVjSK2LQz8L8kolQAyhuWjP/PUWja+S8VQhrx366iMMi1WRqtXn370Q4YBwUfQTai0Bu2+wWAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:50.953275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03038","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d728fe7b7f65fc68894296aa2f0e24314cef02f7a7b9b2707a31b256718967d","sha256:baf910ea89902f4dc54715476f79802c9113f07576aac4a5fc2dfec400a84b58"],"state_sha256":"d8b2a98c033cf6ed34d8bfb4df5ed4a5861a4c8aaeaa8c02d85eae900b6e4522"}