{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q4DNCYEBFMPY5AVOVOAENA6SB4","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":"81287a84b9b42c9150c22b90cacf26a9399968e6f11abd4fcbf384d07e9e5d55","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-04T10:11:45Z","title_canon_sha256":"c8c62d68b6b0be9bfeaadd50ff8b2a1749c17d80a2dc9cbe5c74c2bd4f2f0b48"},"schema_version":"1.0","source":{"id":"2608.03419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03419","created_at":"2026-08-05T01:35:48Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03419v1","created_at":"2026-08-05T01:35:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03419","created_at":"2026-08-05T01:35:48Z"},{"alias_kind":"pith_short_12","alias_value":"Q4DNCYEBFMPY","created_at":"2026-08-05T01:35:48Z"},{"alias_kind":"pith_short_16","alias_value":"Q4DNCYEBFMPY5AVO","created_at":"2026-08-05T01:35:48Z"},{"alias_kind":"pith_short_8","alias_value":"Q4DNCYEB","created_at":"2026-08-05T01:35:48Z"}],"graph_snapshots":[{"event_id":"sha256:a1dbce6ba0bd7e191675e0ecd0353c6b0d3254b777df24f8c3ce78b2adb84449","target":"graph","created_at":"2026-08-05T01:35:48Z","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/2608.03419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Lerch, Hoyeol Sohn, Juhan Nam, Yonghyun Kim","cross_cats":["cs.AI","cs.CV","cs.MM","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-04T10:11:45Z","title":"Multi-Task Multi-Frame Visual Piano Transcription"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03419","kind":"arxiv","version":1},"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":"sha256:681021cfe3fbb6ceb2926024b212db3a1310630b5da635adb4507549613e89ea","target":"record","created_at":"2026-08-05T01:35:48Z","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":"81287a84b9b42c9150c22b90cacf26a9399968e6f11abd4fcbf384d07e9e5d55","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-04T10:11:45Z","title_canon_sha256":"c8c62d68b6b0be9bfeaadd50ff8b2a1749c17d80a2dc9cbe5c74c2bd4f2f0b48"},"schema_version":"1.0","source":{"id":"2608.03419","kind":"arxiv","version":1}},"canonical_sha256":"8706d160812b1f8e82aeab804683d20f0a1566a0b22bacc1087f1a50f7484d61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8706d160812b1f8e82aeab804683d20f0a1566a0b22bacc1087f1a50f7484d61","first_computed_at":"2026-08-05T01:35:48.902947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:48.902947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5wBBBHt4zWadXujMHb0uJi4MmREJgjDe5xwDIYgoM8hNuSJEu+OgxM/bYSL3JdGoJPV1j4hRsmdOkVTHnbs0Aw==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:48.904416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:681021cfe3fbb6ceb2926024b212db3a1310630b5da635adb4507549613e89ea","sha256:a1dbce6ba0bd7e191675e0ecd0353c6b0d3254b777df24f8c3ce78b2adb84449"],"state_sha256":"f45420d159362cbe55ff064ae9ef36407a7025040ba7aa2c907335fea0824417"}