{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:66CYTZEZEZ5UMV7PEXYAD7OHEX","short_pith_number":"pith:66CYTZEZ","schema_version":"1.0","canonical_sha256":"f78589e499267b4657ef25f001fdc725fde37f0b836af1fd14203c358fee2e57","source":{"kind":"arxiv","id":"2606.31811","version":1},"attestation_state":"computed","paper":{"title":"MuSViT: A Foundation Vision Model for Sheet Music Representation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Rios-Vila, Carlos Penarrubia, Eliseo Fuentes-Martinez, Francisco J. Castellanos, Jorge Calvo-Zaragoza, Juan C. Martinez-Sevilla, Mar\\'ia Alfaro-Contreras","submitted_at":"2026-06-30T15:27:12Z","abstract_excerpt":"Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce MuSViT (Music Score Vision Transformer): the first foundation vision model for sheet music representation -- a ViT encoder pre-trained via Masked Autoencoders on 9.7 million pages from the IMSLP. To handle the complexity of real-world scores, we adopt a two-stage curriculum: a synthetic warm-up on typeset scores followed by large-scale tr"},"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":"2606.31811","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T15:27:12Z","cross_cats_sorted":[],"title_canon_sha256":"87cb7522ab55597de1f284db053381520515c0daa47334c63a5d7d24a9e31f60","abstract_canon_sha256":"3e19f4f348cc966c3c0d967c28789f1a92548a79fc983b9259ec253597ad8113"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:16.357108Z","signature_b64":"zF1eA7Duo/kRWHbTiB5HPn8Pw1xfcOjZt5nJzTGN7cDaiJVZNX40lV0Mk1lwWdF23BtZM6+NonwZeINAIeCMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f78589e499267b4657ef25f001fdc725fde37f0b836af1fd14203c358fee2e57","last_reissued_at":"2026-07-01T01:18:16.356568Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:16.356568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuSViT: A Foundation Vision Model for Sheet Music Representation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Rios-Vila, Carlos Penarrubia, Eliseo Fuentes-Martinez, Francisco J. Castellanos, Jorge Calvo-Zaragoza, Juan C. Martinez-Sevilla, Mar\\'ia Alfaro-Contreras","submitted_at":"2026-06-30T15:27:12Z","abstract_excerpt":"Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce MuSViT (Music Score Vision Transformer): the first foundation vision model for sheet music representation -- a ViT encoder pre-trained via Masked Autoencoders on 9.7 million pages from the IMSLP. To handle the complexity of real-world scores, we adopt a two-stage curriculum: a synthetic warm-up on typeset scores followed by large-scale tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31811","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/2606.31811/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":"2606.31811","created_at":"2026-07-01T01:18:16.356644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31811v1","created_at":"2026-07-01T01:18:16.356644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31811","created_at":"2026-07-01T01:18:16.356644+00:00"},{"alias_kind":"pith_short_12","alias_value":"66CYTZEZEZ5U","created_at":"2026-07-01T01:18:16.356644+00:00"},{"alias_kind":"pith_short_16","alias_value":"66CYTZEZEZ5UMV7P","created_at":"2026-07-01T01:18:16.356644+00:00"},{"alias_kind":"pith_short_8","alias_value":"66CYTZEZ","created_at":"2026-07-01T01:18:16.356644+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/66CYTZEZEZ5UMV7PEXYAD7OHEX","json":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX.json","graph_json":"https://pith.science/api/pith-number/66CYTZEZEZ5UMV7PEXYAD7OHEX/graph.json","events_json":"https://pith.science/api/pith-number/66CYTZEZEZ5UMV7PEXYAD7OHEX/events.json","paper":"https://pith.science/paper/66CYTZEZ"},"agent_actions":{"view_html":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX","download_json":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX.json","view_paper":"https://pith.science/paper/66CYTZEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31811&json=true","fetch_graph":"https://pith.science/api/pith-number/66CYTZEZEZ5UMV7PEXYAD7OHEX/graph.json","fetch_events":"https://pith.science/api/pith-number/66CYTZEZEZ5UMV7PEXYAD7OHEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX/action/storage_attestation","attest_author":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX/action/author_attestation","sign_citation":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX/action/citation_signature","submit_replication":"https://pith.science/pith/66CYTZEZEZ5UMV7PEXYAD7OHEX/action/replication_record"}},"created_at":"2026-07-01T01:18:16.356644+00:00","updated_at":"2026-07-01T01:18:16.356644+00:00"}