{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EFJY4OYWCEYCH7VPW2Z6R3NTZK","short_pith_number":"pith:EFJY4OYW","schema_version":"1.0","canonical_sha256":"21538e3b16113023feafb6b3e8edb3ca8e2eed98600c776959f592c5df354d04","source":{"kind":"arxiv","id":"2501.03038","version":2},"attestation_state":"computed","paper":{"title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dichucheng Li, Qiuqiang Kong, Yongyi Zang","submitted_at":"2025-01-06T14:26:00Z","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"},"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":"2501.03038","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-06T14:26:00Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"30f20c28ee8e49ced075e2f7555970a04cb6e2bd1bb2d290b4264566ddbde861","abstract_canon_sha256":"388aa6fd458beaef0e6b08dec8a8e021002fb66e920e7cd67d0e1eada17a318c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:50.953275Z","signature_b64":"3sE7/C5FWrGADVjSK2LQz8L8kolQAyhuWjP/PUWja+S8VQhrx366iMMi1WRqtXn370Q4YBwUfQTai0Bu2+wWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21538e3b16113023feafb6b3e8edb3ca8e2eed98600c776959f592c5df354d04","last_reissued_at":"2026-07-05T09:57:50.952834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:50.952834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dichucheng Li, Qiuqiang Kong, Yongyi Zang","submitted_at":"2025-01-06T14:26:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03038","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/2501.03038/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":"2501.03038","created_at":"2026-07-05T09:57:50.952891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03038v2","created_at":"2026-07-05T09:57:50.952891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03038","created_at":"2026-07-05T09:57:50.952891+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFJY4OYWCEYC","created_at":"2026-07-05T09:57:50.952891+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFJY4OYWCEYCH7VP","created_at":"2026-07-05T09:57:50.952891+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFJY4OYW","created_at":"2026-07-05T09:57:50.952891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK","json":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK.json","graph_json":"https://pith.science/api/pith-number/EFJY4OYWCEYCH7VPW2Z6R3NTZK/graph.json","events_json":"https://pith.science/api/pith-number/EFJY4OYWCEYCH7VPW2Z6R3NTZK/events.json","paper":"https://pith.science/paper/EFJY4OYW"},"agent_actions":{"view_html":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK","download_json":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK.json","view_paper":"https://pith.science/paper/EFJY4OYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03038&json=true","fetch_graph":"https://pith.science/api/pith-number/EFJY4OYWCEYCH7VPW2Z6R3NTZK/graph.json","fetch_events":"https://pith.science/api/pith-number/EFJY4OYWCEYCH7VPW2Z6R3NTZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK/action/storage_attestation","attest_author":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK/action/author_attestation","sign_citation":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK/action/citation_signature","submit_replication":"https://pith.science/pith/EFJY4OYWCEYCH7VPW2Z6R3NTZK/action/replication_record"}},"created_at":"2026-07-05T09:57:50.952891+00:00","updated_at":"2026-07-05T09:57:50.952891+00:00"}