{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:URNTM67I6U6VZE2B6YWRDMN3IJ","short_pith_number":"pith:URNTM67I","schema_version":"1.0","canonical_sha256":"a45b367be8f53d5c9341f62d11b1bb425ae70c501e9388494dd7b0fec2d5f598","source":{"kind":"arxiv","id":"2105.04309","version":1},"attestation_state":"computed","paper":{"title":"Multi-modal Conditional Bounding Box Regression for Music Score Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Henkel, Gerhard Widmer","submitted_at":"2021-05-10T12:43:35Z","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"},"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":"2105.04309","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-10T12:43:35Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"9cb415fd876ea3a4e05aeb1b0d28b67a64746a8a0de8ff1ae5fd2a45f284f967","abstract_canon_sha256":"40019a74e34f81fb025a3d6d14d67af70961299b6691feb878bdcc8ec4e4a433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:55.790642Z","signature_b64":"saBWpzBcxwpL4mQq2vjY+l8ALQBUaNLTkqHBPHyM/rAkWSDINjHetMM6yfr5jg2NuKnm7oFpslmXKrLNet/UAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a45b367be8f53d5c9341f62d11b1bb425ae70c501e9388494dd7b0fec2d5f598","last_reissued_at":"2026-07-05T02:38:55.790208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:55.790208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Conditional Bounding Box Regression for Music Score Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Henkel, Gerhard Widmer","submitted_at":"2021-05-10T12:43:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04309","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/2105.04309/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":"2105.04309","created_at":"2026-07-05T02:38:55.790263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04309v1","created_at":"2026-07-05T02:38:55.790263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04309","created_at":"2026-07-05T02:38:55.790263+00:00"},{"alias_kind":"pith_short_12","alias_value":"URNTM67I6U6V","created_at":"2026-07-05T02:38:55.790263+00:00"},{"alias_kind":"pith_short_16","alias_value":"URNTM67I6U6VZE2B","created_at":"2026-07-05T02:38:55.790263+00:00"},{"alias_kind":"pith_short_8","alias_value":"URNTM67I","created_at":"2026-07-05T02:38:55.790263+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/URNTM67I6U6VZE2B6YWRDMN3IJ","json":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ.json","graph_json":"https://pith.science/api/pith-number/URNTM67I6U6VZE2B6YWRDMN3IJ/graph.json","events_json":"https://pith.science/api/pith-number/URNTM67I6U6VZE2B6YWRDMN3IJ/events.json","paper":"https://pith.science/paper/URNTM67I"},"agent_actions":{"view_html":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ","download_json":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ.json","view_paper":"https://pith.science/paper/URNTM67I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04309&json=true","fetch_graph":"https://pith.science/api/pith-number/URNTM67I6U6VZE2B6YWRDMN3IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/URNTM67I6U6VZE2B6YWRDMN3IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ/action/storage_attestation","attest_author":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ/action/author_attestation","sign_citation":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ/action/citation_signature","submit_replication":"https://pith.science/pith/URNTM67I6U6VZE2B6YWRDMN3IJ/action/replication_record"}},"created_at":"2026-07-05T02:38:55.790263+00:00","updated_at":"2026-07-05T02:38:55.790263+00:00"}