{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZZH72XYFRYN7ZUNSXUL4T6LTXC","short_pith_number":"pith:ZZH72XYF","schema_version":"1.0","canonical_sha256":"ce4ffd5f058e1bfcd1b2bd17c9f973b89f0d79b803feafa14628e5f0963fdd69","source":{"kind":"arxiv","id":"2010.01815","version":3},"attestation_state":"computed","paper":{"title":"High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bochen Li, Qiuqiang Kong, Xuchen Song, Yuan Wan, Yuxuan Wang","submitted_at":"2020-10-05T06:57:11Z","abstract_excerpt":"Automatic music transcription (AMT) is the task of transcribing audio recordings into symbolic representations. Recently, neural network-based methods have been applied to AMT, and have achieved state-of-the-art results. However, many previous systems only detect the onset and offset of notes frame-wise, so the transcription resolution is limited to the frame hop size. There is a lack of research on using different strategies to encode onset and offset targets for training. In addition, previous AMT systems are sensitive to the misaligned onset and offset labels of audio recordings. Furthermor"},"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":"2010.01815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-10-05T06:57:11Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"640d4b64c370797ea0a1663820b1459e89b8a88d0f91a6b8c9aeb9db4923ab98","abstract_canon_sha256":"38a84422ce9ed9f12762eceb1be5a514f05a9b4696d6b10559009056c28d622b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:09.078229Z","signature_b64":"wl1Oe8wqjVBfQo4tQ1GIh3RDgVffLWz9A8I5Ismil6RxuBTDrHmBGiNZtn16PUNgww8L32S/3KIJgYdnCEdFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce4ffd5f058e1bfcd1b2bd17c9f973b89f0d79b803feafa14628e5f0963fdd69","last_reissued_at":"2026-07-05T03:02:09.077803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:09.077803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bochen Li, Qiuqiang Kong, Xuchen Song, Yuan Wan, Yuxuan Wang","submitted_at":"2020-10-05T06:57:11Z","abstract_excerpt":"Automatic music transcription (AMT) is the task of transcribing audio recordings into symbolic representations. Recently, neural network-based methods have been applied to AMT, and have achieved state-of-the-art results. However, many previous systems only detect the onset and offset of notes frame-wise, so the transcription resolution is limited to the frame hop size. There is a lack of research on using different strategies to encode onset and offset targets for training. In addition, previous AMT systems are sensitive to the misaligned onset and offset labels of audio recordings. Furthermor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01815","kind":"arxiv","version":3},"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/2010.01815/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":"2010.01815","created_at":"2026-07-05T03:02:09.077861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01815v3","created_at":"2026-07-05T03:02:09.077861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01815","created_at":"2026-07-05T03:02:09.077861+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZH72XYFRYN7","created_at":"2026-07-05T03:02:09.077861+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZH72XYFRYN7ZUNS","created_at":"2026-07-05T03:02:09.077861+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZH72XYF","created_at":"2026-07-05T03:02:09.077861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24193","citing_title":"Music Transcription with (Almost) No Supervision","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC","json":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC.json","graph_json":"https://pith.science/api/pith-number/ZZH72XYFRYN7ZUNSXUL4T6LTXC/graph.json","events_json":"https://pith.science/api/pith-number/ZZH72XYFRYN7ZUNSXUL4T6LTXC/events.json","paper":"https://pith.science/paper/ZZH72XYF"},"agent_actions":{"view_html":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC","download_json":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC.json","view_paper":"https://pith.science/paper/ZZH72XYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01815&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZH72XYFRYN7ZUNSXUL4T6LTXC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZH72XYFRYN7ZUNSXUL4T6LTXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC/action/storage_attestation","attest_author":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC/action/author_attestation","sign_citation":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC/action/citation_signature","submit_replication":"https://pith.science/pith/ZZH72XYFRYN7ZUNSXUL4T6LTXC/action/replication_record"}},"created_at":"2026-07-05T03:02:09.077861+00:00","updated_at":"2026-07-05T03:02:09.077861+00:00"}