{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:URNTM67I6U6VZE2B6YWRDMN3IJ","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":"40019a74e34f81fb025a3d6d14d67af70961299b6691feb878bdcc8ec4e4a433","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-10T12:43:35Z","title_canon_sha256":"9cb415fd876ea3a4e05aeb1b0d28b67a64746a8a0de8ff1ae5fd2a45f284f967"},"schema_version":"1.0","source":{"id":"2105.04309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04309","created_at":"2026-07-05T02:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04309v1","created_at":"2026-07-05T02:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04309","created_at":"2026-07-05T02:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"URNTM67I6U6V","created_at":"2026-07-05T02:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"URNTM67I6U6VZE2B","created_at":"2026-07-05T02:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"URNTM67I","created_at":"2026-07-05T02:38:55Z"}],"graph_snapshots":[{"event_id":"sha256:e0129211cfaa1816c249a7b0d55ea20ddd259f635d336ed7e5106895345c7351","target":"graph","created_at":"2026-07-05T02:38:55Z","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/2105.04309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the problem of sheet-image-based on-line audio-to-score alignment also known as score following. Drawing inspiration from object detection, a conditional neural network architecture is proposed that directly predicts x,y coordinates of the matching positions in a complete score sheet image at each point in time for a given musical performance. Experiments are conducted on a synthetic polyphonic piano benchmark dataset and the new method is compared to several existing approaches from the literature for sheet-image-based score following as well as an Optical Music Recogniti","authors_text":"Florian Henkel, Gerhard Widmer","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-10T12:43:35Z","title":"Multi-modal Conditional Bounding Box Regression for Music Score Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04309","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:c57713e444f74fa5786f1911544aabeba020b7cab8f1ab6e1a01463ac0d77d69","target":"record","created_at":"2026-07-05T02:38:55Z","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":"40019a74e34f81fb025a3d6d14d67af70961299b6691feb878bdcc8ec4e4a433","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-10T12:43:35Z","title_canon_sha256":"9cb415fd876ea3a4e05aeb1b0d28b67a64746a8a0de8ff1ae5fd2a45f284f967"},"schema_version":"1.0","source":{"id":"2105.04309","kind":"arxiv","version":1}},"canonical_sha256":"a45b367be8f53d5c9341f62d11b1bb425ae70c501e9388494dd7b0fec2d5f598","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a45b367be8f53d5c9341f62d11b1bb425ae70c501e9388494dd7b0fec2d5f598","first_computed_at":"2026-07-05T02:38:55.790208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:55.790208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"saBWpzBcxwpL4mQq2vjY+l8ALQBUaNLTkqHBPHyM/rAkWSDINjHetMM6yfr5jg2NuKnm7oFpslmXKrLNet/UAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:55.790642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.04309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c57713e444f74fa5786f1911544aabeba020b7cab8f1ab6e1a01463ac0d77d69","sha256:e0129211cfaa1816c249a7b0d55ea20ddd259f635d336ed7e5106895345c7351"],"state_sha256":"9d827d6e11a1059791d2958f235a89517fd667cf8a4b23b23a560ae447953717"}