{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q4DNCYEBFMPY5AVOVOAENA6SB4","short_pith_number":"pith:Q4DNCYEB","schema_version":"1.0","canonical_sha256":"8706d160812b1f8e82aeab804683d20f0a1566a0b22bacc1087f1a50f7484d61","source":{"kind":"arxiv","id":"2608.03419","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Multi-Frame Visual Piano Transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","eess.IV"],"primary_cat":"cs.SD","authors_text":"Alexander Lerch, Hoyeol Sohn, Juhan Nam, Yonghyun Kim","submitted_at":"2026-08-04T10:11:45Z","abstract_excerpt":"Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extended offsets rather than physical key release. Yet existing Visual Piano Transcription (VPT) systems focus on onset detection from short video windows, offset accuracy lags onset by a wide margin, and note-level velocity has not been reported. To address these gaps, we present V2N (Video to Notes), the first complete VPT system: a shared temporal backbone feeds task-specific heads for onset, offset, key hold, and veloci"},"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":"2608.03419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-04T10:11:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.IV"],"title_canon_sha256":"c8c62d68b6b0be9bfeaadd50ff8b2a1749c17d80a2dc9cbe5c74c2bd4f2f0b48","abstract_canon_sha256":"81287a84b9b42c9150c22b90cacf26a9399968e6f11abd4fcbf384d07e9e5d55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:48.904416Z","signature_b64":"5wBBBHt4zWadXujMHb0uJi4MmREJgjDe5xwDIYgoM8hNuSJEu+OgxM/bYSL3JdGoJPV1j4hRsmdOkVTHnbs0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8706d160812b1f8e82aeab804683d20f0a1566a0b22bacc1087f1a50f7484d61","last_reissued_at":"2026-08-05T01:35:48.902947Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:48.902947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Multi-Frame Visual Piano Transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","eess.IV"],"primary_cat":"cs.SD","authors_text":"Alexander Lerch, Hoyeol Sohn, Juhan Nam, Yonghyun Kim","submitted_at":"2026-08-04T10:11:45Z","abstract_excerpt":"Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extended offsets rather than physical key release. Yet existing Visual Piano Transcription (VPT) systems focus on onset detection from short video windows, offset accuracy lags onset by a wide margin, and note-level velocity has not been reported. To address these gaps, we present V2N (Video to Notes), the first complete VPT system: a shared temporal backbone feeds task-specific heads for onset, offset, key hold, and veloci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03419","kind":"arxiv","version":1},"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/2608.03419/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":"2608.03419","created_at":"2026-08-05T01:35:48.903405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03419v1","created_at":"2026-08-05T01:35:48.903405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03419","created_at":"2026-08-05T01:35:48.903405+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4DNCYEBFMPY","created_at":"2026-08-05T01:35:48.903405+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4DNCYEBFMPY5AVO","created_at":"2026-08-05T01:35:48.903405+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4DNCYEB","created_at":"2026-08-05T01:35:48.903405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03419","citing_title":"Multi-Task Multi-Frame Visual Piano Transcription","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4","json":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4.json","graph_json":"https://pith.science/api/pith-number/Q4DNCYEBFMPY5AVOVOAENA6SB4/graph.json","events_json":"https://pith.science/api/pith-number/Q4DNCYEBFMPY5AVOVOAENA6SB4/events.json","paper":"https://pith.science/paper/Q4DNCYEB"},"agent_actions":{"view_html":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4","download_json":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4.json","view_paper":"https://pith.science/paper/Q4DNCYEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03419&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4DNCYEBFMPY5AVOVOAENA6SB4/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4DNCYEBFMPY5AVOVOAENA6SB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4/action/storage_attestation","attest_author":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4/action/author_attestation","sign_citation":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4/action/citation_signature","submit_replication":"https://pith.science/pith/Q4DNCYEBFMPY5AVOVOAENA6SB4/action/replication_record"}},"created_at":"2026-08-05T01:35:48.903405+00:00","updated_at":"2026-08-05T01:35:48.903405+00:00"}